{"as_of":"2026-08-05T23:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0dd2f78e8c494064d18bda268ce5832a97f6867d49e111c7ed9a194099d23b20","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T11:50:26.030339Z","state":"measured"},{"denominator":149,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":149,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":167,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T19:28:56.492871Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":5,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2206.07682","last_updated":"2022-10-26T05:06:24Z","snapshot_observed_at":"2026-08-02T15:56:35.249569Z","submitted_at":"2022-06-15T17:32:01Z","title":"Emergent Abilities of Large Language Models","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-05-11T07:38:37.734402Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2206.07682"},"observation_digest":"sha256:379a3a8212cc34bc771a8eaf20ebdab253dbfb02573815516d3378445afcc8de","observation_id":"8c9721d4-2582-4b35-b622-46b8cd1bcff6","resolution":{"observed_at":"2026-05-11T07:38:37.880668Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2207.05221","last_updated":"2022-11-21T16:38:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-07-11T22:59:39Z","title":"Language Models (Mostly) Know What They Know","version":4},"reference_index":210,"source":"arxiv_source","source_observed_at":"2026-05-10T15:42:47.274448Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2207.05221"},"observation_digest":"sha256:dc360bff728e6569dc448d66ec7ce1473e631a2bb18a5afa19ef94b6235298ce","observation_id":"6fd99ee7-4c87-40a3-8c88-2e151787f520","resolution":{"observed_at":"2026-05-10T23:26:25.883762Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2210.09261","last_updated":"2022-10-17T17:08:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-10-17T17:08:26Z","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-11T07:15:23.725397Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2210.09261"},"observation_digest":"sha256:3bff7115b55d4aaa0f901ca445ea4b876c52c83a1a23bd2262929b9bfdf17e5b","observation_id":"ca686e16-f7fd-4a9b-9aa8-209b6866ec99","resolution":{"observed_at":"2026-05-11T07:15:23.956384Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2210.11610","last_updated":"2022-10-25T17:45:17Z","snapshot_observed_at":"2026-07-06T14:08:26.493996Z","submitted_at":"2022-10-20T21:53:54Z","title":"Large Language Models Can Self-Improve","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-18T17:00:48.167441Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2210.11610"},"observation_digest":"sha256:4333d5b9bdaa8a894bc381cabc419f5979a0411fee35f0b318ad26d178eaa22e","observation_id":"fc9fc5b9-7fca-4383-8567-25f4e0934cd4","resolution":{"observed_at":"2026-05-18T17:00:48.297809Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2211.01910","last_updated":"2023-03-10T17:20:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-03T15:43:03Z","title":"Large Language Models Are Human-Level Prompt Engineers","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-24T09:43:26.288866Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2211.01910"},"observation_digest":"sha256:4e2634c2908c54d15654bc53b5663a6ad37991e028a1fcfdf516a20aa6ab691e","observation_id":"3fa233c2-a16c-462e-85c3-a27abbdd2d14","resolution":{"observed_at":"2026-05-24T09:43:26.345236Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2211.05100","last_updated":"2023-06-27T09:57:58Z","snapshot_observed_at":"2026-08-04T18:56:03.233715Z","submitted_at":"2022-11-09T18:48:09Z","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","version":4},"reference_index":141,"source":"arxiv_source","source_observed_at":"2026-05-12T00:51:10.919818Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2211.05100"},"observation_digest":"sha256:fff82016214a3a24c55a6be68149721c702a7cc69391863a3cff6a3f1e45c751","observation_id":"7d0a8613-2704-41d5-ac87-4d3d39eb0b24","resolution":{"observed_at":"2026-05-12T00:51:11.440917Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2211.09085","last_updated":"2022-11-16T18:06:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-16T18:06:33Z","title":"Galactica: A Large Language Model for Science","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-05-13T05:53:21.810346Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2211.09085"},"observation_digest":"sha256:8ce297eec83881705d3fee6db6403453909e9560e9b63bcf1389a853d489c4d8","observation_id":"81c0ff3f-125d-46a0-861a-946494458a01","resolution":{"observed_at":"2026-05-13T05:53:22.029283Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2211.09085","last_updated":"2022-11-16T18:06:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-16T18:06:33Z","title":"Galactica: A Large Language Model for Science","version":1},"reference_index":237,"source":"arxiv_source","source_observed_at":"2026-05-13T05:53:21.810346Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2211.09085"},"observation_digest":"sha256:b11bd918ccad3d1b1805a6f0b170fb8a4c47a87a1ae58b53dd3dc68f0866ab1f","observation_id":"ba537a72-2496-4e2e-910e-77c977d362ee","resolution":{"observed_at":"2026-05-13T05:53:22.261459Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2301.00234","last_updated":"2024-10-05T11:47:02Z","snapshot_observed_at":"2026-07-06T14:36:25.690733Z","submitted_at":"2022-12-31T15:57:09Z","title":"A Survey on In-context Learning","version":6},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-12T12:58:27.430374Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2301.00234"},"observation_digest":"sha256:c406f1dd9d212fbf945257cdb5bdaacfda725c845b9617031c7dc296d4f04e34","observation_id":"4648f200-ceaf-41e9-9635-e36dee31d635","resolution":{"observed_at":"2026-05-12T12:58:27.557343Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2301.05217","last_updated":"2023-10-19T21:25:32Z","snapshot_observed_at":"2026-08-02T10:20:00.635719Z","submitted_at":"2023-01-12T18:56:49Z","title":"Progress measures for grokking via mechanistic interpretability","version":3},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-05-14T21:52:56.040569Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2301.05217"},"observation_digest":"sha256:87e148222129fc6ed65dde1d933cb3679876f85120b1737cce34367ac0bd9c11","observation_id":"81c0c17a-e935-4f62-8c74-08f14b8f96bd","resolution":{"observed_at":"2026-05-14T21:52:56.172067Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2301.13688","last_updated":"2023-02-14T16:33:33Z","snapshot_observed_at":"2026-08-05T20:18:14.325590Z","submitted_at":"2023-01-31T15:03:44Z","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-24T09:13:30.054153Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2301.13688"},"observation_digest":"sha256:67cf337ac7ffd3d0d715f37ccda9b6d0222517066b23509698b5169cf57c5ad6","observation_id":"e208446e-2900-4851-90ab-8b131f407bb0","resolution":{"observed_at":"2026-05-24T09:14:16.494657Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2302.04023","last_updated":"2023-11-28T09:01:12Z","snapshot_observed_at":"2026-07-06T14:49:37.908412Z","submitted_at":"2023-02-08T12:35:34Z","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-17T19:58:48.066562Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2302.04023"},"observation_digest":"sha256:d76ec919dbd711ab38972959711529d53fa3c22a3997b8547646d98c2fddfad0","observation_id":"66c7c594-be97-4ee4-b1b0-a5f8e6b1f754","resolution":{"observed_at":"2026-05-17T19:58:48.116991Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2303.09014","last_updated":"2023-03-16T01:04:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-03-16T01:04:45Z","title":"ART: Automatic multi-step reasoning and tool-use for large language models","version":1},"reference_index":152,"source":"arxiv_source","source_observed_at":"2026-05-16T19:03:05.597295Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2303.09014"},"observation_digest":"sha256:95b015d121b1a94668445f13f9da4e9771fd9e3ea1346b9b107eede08546f8d9","observation_id":"7023981c-6e77-473f-80a4-3a3747e58a41","resolution":{"observed_at":"2026-05-16T19:03:06.252249Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2303.17564","last_updated":"2023-12-21T06:21:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-03-30T17:30:36Z","title":"BloombergGPT: A Large Language Model for Finance","version":3},"reference_index":107,"source":"arxiv_source","source_observed_at":"2026-05-13T23:19:46.231145Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2303.17564"},"observation_digest":"sha256:c23c3ee9e42d788be04225612723c8fe1b6aa2f7a449230be5111169936a4c9b","observation_id":"e0b65df4-9b71-448a-8545-f725732ae354","resolution":{"observed_at":"2026-05-13T23:19:46.804424Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2303.18223","last_updated":"2026-03-18T05:34:39Z","snapshot_observed_at":"2026-08-05T23:24:44.027417Z","submitted_at":"2023-03-31T17:28:46Z","title":"A Survey of Large Language Models","version":19},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-10T22:46:39.268353Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2303.18223"},"observation_digest":"sha256:712055a7882e8f139f472b0488bad887966353e6bee38323582292e32cbf2964","observation_id":"7da3c7be-ee12-4a6d-b4ec-5087c26ba17f","resolution":{"observed_at":"2026-05-10T23:26:25.883762Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2304.01373","last_updated":"2023-05-31T17:54:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-03T20:58:15Z","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","version":2},"reference_index":135,"source":"arxiv_source","source_observed_at":"2026-05-15T17:45:17.540282Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2304.01373"},"observation_digest":"sha256:68e56fac3fb2ffc8ae145a38eabd7e10efc9bbd8c27f95172e1277fed9358284","observation_id":"ff7e6c23-fc25-4246-bf2a-fecdeafdedf2","resolution":{"observed_at":"2026-05-15T17:45:17.678544Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2305.07759","last_updated":"2023-05-24T23:30:43Z","snapshot_observed_at":"2026-08-04T10:35:00.917001Z","submitted_at":"2023-05-12T20:56:48Z","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-25T07:36:55.087443Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2305.07759"},"observation_digest":"sha256:331ae35389624f44124a1b3ebb1ef1019a30776597612a462b447fbad351f149","observation_id":"3b189186-8328-4d9c-b3ac-e79d18a634c5","resolution":{"observed_at":"2026-05-25T07:36:55.166008Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2305.09617","last_updated":"2023-05-16T17:11:29Z","snapshot_observed_at":"2026-08-03T08:52:05.725675Z","submitted_at":"2023-05-16T17:11:29Z","title":"Towards Expert-Level Medical Question Answering with Large Language Models","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-05-24T04:32:33.271634Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2305.09617"},"observation_digest":"sha256:5e91f22698eafcf1bfe0254bbc6e57edf039173a290285520a9cc86e89080863","observation_id":"1651c060-1637-4d28-937d-eb8a4fc78425","resolution":{"observed_at":"2026-05-24T04:32:33.480460Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2305.10403","last_updated":"2023-09-13T20:35:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-17T17:46:53Z","title":"PaLM 2 Technical Report","version":3},"reference_index":255,"source":"arxiv_source","source_observed_at":"2026-05-12T11:59:25.813128Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2305.10403"},"observation_digest":"sha256:f5dd096e5e826f27970dd3ee9b5f44b2b57fb2d630575efbc3ea591aec9f9f04","observation_id":"6539ad68-7843-4cdc-9428-3fdda8b441bb","resolution":{"observed_at":"2026-05-12T11:59:27.339629Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2305.12474","last_updated":"2024-02-24T15:44:21Z","snapshot_observed_at":"2026-08-02T10:07:31.047425Z","submitted_at":"2023-05-21T14:39:28Z","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-17T12:28:32.395213Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2305.12474"},"observation_digest":"sha256:2584f8b1f457c6191a50f48f0665439353837b48a3202ea059d9235906267562","observation_id":"c48315cd-a1d6-454d-9eb1-1eb430b1ae93","resolution":{"observed_at":"2026-05-17T12:28:32.430613Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2305.14325","last_updated":"2023-05-23T17:55:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-23T17:55:11Z","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-12T03:01:45.164412Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2305.14325"},"observation_digest":"sha256:470c2e86307cca30d3c2c864087e64df5d8dc334533777e69977a6d57a42537b","observation_id":"9efdb8f6-6d40-4ddf-9f14-5b160c602898","resolution":{"observed_at":"2026-05-12T03:01:45.212602Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2305.16264","last_updated":"2025-06-28T00:00:06Z","snapshot_observed_at":"2026-07-06T15:33:27.761070Z","submitted_at":"2023-05-25T17:18:55Z","title":"Scaling Data-Constrained Language Models","version":5},"reference_index":110,"source":"pdf_text","source_observed_at":"2026-05-18T01:35:21.150772Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2305.16264"},"observation_digest":"sha256:6dab3c19fdb3355c0d6e4952bd6eab73fe15686f9cfdd4046005bd789a2978da","observation_id":"ae218b2d-079e-4134-93ef-583a70e09dd1","resolution":{"observed_at":"2026-05-18T01:35:21.380700Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2306.05685","last_updated":"2023-12-24T02:01:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-09T05:55:52Z","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T18:52:59.033645Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2306.05685"},"observation_digest":"sha256:ecd5f8b20fba1e769c34c0170f8f9c0df8d29d1981974dbaf9f406d84d9f1ba6","observation_id":"7e1adb2e-beef-4bda-b5ac-906e746478fb","resolution":{"observed_at":"2026-05-10T23:26:25.883762Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2308.03958","last_updated":"2024-02-15T01:03:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-07T23:48:36Z","title":"Simple synthetic data reduces sycophancy in large language models","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-05-16T14:48:08.508109Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2308.03958"},"observation_digest":"sha256:7f363366a88a50d9bf990eae4dc20a0c58be191f9f6209bc6842902a2a552ee3","observation_id":"dac4623a-7cb0-49db-a419-f0ab19f0786f","resolution":{"observed_at":"2026-05-16T14:48:08.687462Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2308.08998","last_updated":"2023-08-21T10:23:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-17T14:12:48Z","title":"Reinforced Self-Training (ReST) for Language Modeling","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-13T07:59:55.849296Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2308.08998"},"observation_digest":"sha256:83431d489a6838ab5c251f8e0c581f5a6470dfe8c18627000c3d0765a7fba585","observation_id":"e79ed1ad-f787-416f-aff3-fedc40d44e70","resolution":{"observed_at":"2026-05-13T07:59:55.956017Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2309.03409","last_updated":"2024-04-15T07:50:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-07T00:07:15Z","title":"Large Language Models as Optimizers","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-15T00:04:31.212102Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2309.03409"},"observation_digest":"sha256:f91100ac21e257148813a833b50eb15319b60ed0b8c3c3dce7cf78f2878d9ff1","observation_id":"3f47cb8c-b37d-47d8-93b2-3f79c3b0c7ac","resolution":{"observed_at":"2026-05-15T00:04:31.357861Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2309.07597","last_updated":"2024-09-24T03:01:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-14T10:57:50Z","title":"C-Pack: Packed Resources For General Chinese Embeddings","version":5},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-13T13:24:32.084878Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2309.07597"},"observation_digest":"sha256:682c8f3d192bbeea81909132570172ab857287be95100319553f0947d7d594a9","observation_id":"05828090-91fe-4df2-b661-0556f42135f3","resolution":{"observed_at":"2026-05-13T13:24:32.114886Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2309.10305","last_updated":"2025-04-17T08:34:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-19T04:13:22Z","title":"Baichuan 2: Open Large-scale Language Models","version":4},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-05-24T06:51:02.531751Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2309.10305"},"observation_digest":"sha256:1e0013a1f1b1e783cc1e71431f7a7a4ca67e6cd1540c9cfb78fb813c8ea25b12","observation_id":"06822792-59bc-492c-9d91-e34fd508279e","resolution":{"observed_at":"2026-05-24T06:54:03.661016Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2310.01801","last_updated":"2024-10-29T18:26:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-03T05:17:08Z","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","version":4},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-05-17T11:11:21.460613Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2310.01801"},"observation_digest":"sha256:1f000492343a17403477e9b53ee5ad9cf438c2eaa918fe4a077603ce2312fd56","observation_id":"bd11d899-2e47-4818-8557-8e38eaf432fc","resolution":{"observed_at":"2026-05-17T11:11:21.637241Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-05-24T05:00:28.453838Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2312.11805"},"observation_digest":"sha256:ccde1eb5f0a14a802d5fbacbb94bedb0f4429a214a408ffdfcbe30e9c09ba94f","observation_id":"fac13bf6-5b03-4344-ba03-85efd1e97681","resolution":{"observed_at":"2026-05-24T05:03:55.335301Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2401.02385","last_updated":"2024-06-04T02:05:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-04T17:54:59Z","title":"TinyLlama: An Open-Source Small Language Model","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-13T21:09:45.317768Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2401.02385"},"observation_digest":"sha256:eff2349449aec04d195627e25b2a761f69cd7b1ada40f7cdff3a828f88b35a5b","observation_id":"cbfa9301-0159-4477-94f7-fca74eb99e7e","resolution":{"observed_at":"2026-05-13T21:09:45.383248Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2401.10774","last_updated":"2024-06-14T23:32:32Z","snapshot_observed_at":"2026-07-06T17:17:56.276857Z","submitted_at":"2024-01-19T15:48:40Z","title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","version":3},"reference_index":114,"source":"arxiv_source","source_observed_at":"2026-05-13T10:36:17.764761Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2401.10774"},"observation_digest":"sha256:4f91c8f2c0cfff44daa84e82bc35161c747c736cd5f90a5d23b61be3882fd24c","observation_id":"cc313612-5b75-41e4-9f01-a621e387e9fb","resolution":{"observed_at":"2026-05-13T10:36:18.222392Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2402.01306","last_updated":"2024-11-19T18:12:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-02T10:53:36Z","title":"KTO: Model Alignment as Prospect Theoretic Optimization","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-12T12:17:53.478052Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2402.01306"},"observation_digest":"sha256:6c1e728637bcb538d8bcbd709fe0a3eeb858f254da034d32238b9c629bcdae39","observation_id":"0cab335d-348b-41e8-b28a-fdcf70ca187d","resolution":{"observed_at":"2026-05-12T12:17:53.570619Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2402.13228","last_updated":"2024-07-03T13:46:33Z","snapshot_observed_at":"2026-07-31T05:05:41.080329Z","submitted_at":"2024-02-20T18:42:34Z","title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","version":2},"reference_index":138,"source":"arxiv_source","source_observed_at":"2026-05-17T23:04:44.287660Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2402.13228"},"observation_digest":"sha256:7a4c3bd2c07fa6feb04c3f31d3b055dfd54317a214d99302ec0bef610456636e","observation_id":"4b20af0c-c671-447a-8d15-b69f1be61a32","resolution":{"observed_at":"2026-05-17T23:04:44.508501Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2403.07974","last_updated":"2024-06-06T17:41:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-03-12T17:58:04Z","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","version":2},"reference_index":124,"source":"arxiv_source","source_observed_at":"2026-05-10T17:34:42.565806Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2403.07974"},"observation_digest":"sha256:545401614ae0b074863c378259bd8991f1051e5112b3caae48a6b023c3770da9","observation_id":"26b56491-f2e6-4bf5-a2ac-0f9180e7a2b1","resolution":{"observed_at":"2026-05-10T23:26:25.883762Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2404.13076","last_updated":"2024-04-15T16:49:59Z","snapshot_observed_at":"2026-07-06T18:02:53.240463Z","submitted_at":"2024-04-15T16:49:59Z","title":"LLM Evaluators Recognize and Favor Their Own Generations","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-22T18:44:28.766639Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2404.13076"},"observation_digest":"sha256:16ff6ff837370e219db13ec219bdebcf79821d6d886edcba471c1691bd67f981","observation_id":"bc9ed97e-d90f-4a90-99fe-84a9c60fcef2","resolution":{"observed_at":"2026-05-22T18:44:28.879481Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2404.14219","last_updated":"2024-08-30T21:17:17Z","snapshot_observed_at":"2026-07-06T18:03:47.096406Z","submitted_at":"2024-04-22T14:32:33Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T20:19:27.255515Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2404.14219"},"observation_digest":"sha256:c9b45a3aa37efdb0da8e6707365445247905319bd35d059978982b2a6282691f","observation_id":"44b0fadf-d768-432a-9d07-5862ff58f81c","resolution":{"observed_at":"2026-05-10T23:26:25.883762Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2405.07987","last_updated":"2024-07-25T09:33:50Z","snapshot_observed_at":"2026-08-01T15:05:23.324854Z","submitted_at":"2024-05-13T17:58:30Z","title":"The Platonic Representation Hypothesis","version":5},"reference_index":162,"source":"arxiv_source","source_observed_at":"2026-05-15T06:03:56.328012Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2405.07987"},"observation_digest":"sha256:c9e6d9922ea3fb2d998bf5e7187275519d23173ac8d82686c5ff6ec1acc4967a","observation_id":"f5a0b5e5-b0c3-4d9a-9b54-f14466339c26","resolution":{"observed_at":"2026-05-15T06:03:56.647244Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2405.14782","last_updated":"2026-05-31T00:04:33Z","snapshot_observed_at":"2026-08-02T05:44:43.939336Z","submitted_at":"2024-05-23T16:50:49Z","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-05-16T18:44:49.519995Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2405.14782"},"observation_digest":"sha256:4bd82b56ea97a7179896461f76283b1ac4ddacd785ae9a0a34bce530628bc6cd","observation_id":"66bdd477-3ef2-4772-a211-3ee151b39f68","resolution":{"observed_at":"2026-05-16T18:44:49.728653Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2406.01574","last_updated":"2024-11-06T02:54:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-03T17:53:00Z","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","version":6},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-11T15:51:04.674346Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2406.01574"},"observation_digest":"sha256:b6ed6c0adb80a27ea530e5a2b01c3f2dcb034eff79262e6ac1c5e84573defb45","observation_id":"6dc02a4e-23d8-4905-8760-e3009390288a","resolution":{"observed_at":"2026-05-11T15:51:05.108235Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2406.12793","last_updated":"2024-07-30T03:58:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-18T16:58:21Z","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-11T08:08:09.444352Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2406.12793"},"observation_digest":"sha256:d038e0ebf03b7e4fe7d38a218f7ceb55dce68742561d2bf373fb0e99a15b22de","observation_id":"a1a0b8c6-96f0-4693-b834-2bcc59cefcec","resolution":{"observed_at":"2026-05-11T08:08:09.678351Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2406.19314","last_updated":"2025-04-18T19:36:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-27T16:47:42Z","title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-15T04:48:26.303240Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2406.19314"},"observation_digest":"sha256:a4eba32a09eb9d23db2400bbed2c5cb07546b343a5546743e0c9bcb860bb5b0d","observation_id":"298e6435-eb7e-4b40-96b6-51b5bf4bc50e","resolution":{"observed_at":"2026-05-15T04:48:26.484783Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2408.00724","last_updated":"2025-03-03T07:53:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-01T17:16:04Z","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","version":3},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-05-18T06:38:36.517935Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2408.00724"},"observation_digest":"sha256:e895c825ba967895e76483e13c2b2c616d4bde7b02d50061f300c12906f54c2d","observation_id":"f506b820-157b-43fa-9113-400f359ecf1b","resolution":{"observed_at":"2026-05-18T06:38:36.697127Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2410.17448","last_updated":"2026-04-16T15:22:12Z","snapshot_observed_at":"2026-08-03T00:27:15.111806Z","submitted_at":"2024-10-22T21:50:52Z","title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-05-23T18:50:40.378720Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2410.17448"},"observation_digest":"sha256:8ea3bfe8007052ce490ee41eb3607404e6872d1d73c5add3d526a46547ffa02f","observation_id":"3de9ad2b-c6f4-493e-8eee-02f35626dc37","resolution":{"observed_at":"2026-05-23T18:53:21.163360Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2411.01141","last_updated":"2026-05-20T04:50:41Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-11-02T05:10:50Z","title":"Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-05-23T18:03:19.212619Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2411.01141"},"observation_digest":"sha256:86875f29e78ad7eb6f33068420277c980b1d47d1b14c41b00f3637d550d1241d","observation_id":"8b070f90-0ee9-4746-900e-91bf360f1dd8","resolution":{"observed_at":"2026-05-23T18:05:44.713031Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2411.15594","last_updated":"2025-10-19T10:32:43Z","snapshot_observed_at":"2026-08-02T10:23:50.881300Z","submitted_at":"2024-11-23T16:03:35Z","title":"A Survey on LLM-as-a-Judge","version":6},"reference_index":137,"source":"pdf_text","source_observed_at":"2026-05-23T17:33:13.394338Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2411.15594"},"observation_digest":"sha256:cda237d985ca6244e4931e951348939fb4b5a3f0870ea6a4f10c54ee33591515","observation_id":"42f5d02c-d974-48c2-8473-d4b4e8d1beab","resolution":{"observed_at":"2026-05-23T17:35:44.194739Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2501.02378","last_updated":"2026-04-15T05:10:03Z","snapshot_observed_at":"2026-07-31T16:53:57.321287Z","submitted_at":"2025-01-04T20:49:20Z","title":"A ghost mechanism: An analytical model of abrupt learning in recurrent networks","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-23T06:31:21.006691Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2501.02378"},"observation_digest":"sha256:4783446544a7af20adbbc98fa664c99c63feb17d2f68ef69b43d505ae06aa7af","observation_id":"56f5e2ec-d951-42eb-9e15-3fbe4fc8bd70","resolution":{"observed_at":"2026-05-23T06:32:38.822685Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2501.05465","last_updated":"2026-05-14T16:52:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-03T19:53:57Z","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","version":2},"reference_index":120,"source":"pdf_text","source_observed_at":"2026-05-23T05:47:48.488826Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2501.05465"},"observation_digest":"sha256:378fa0231c00bbfdffc9c56c8c9ed6ffe92fb05f32bd792ec5cd382695ca983e","observation_id":"697f7b4d-c536-4372-a270-c84f7110c643","resolution":{"observed_at":"2026-05-23T05:52:37.669278Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2501.09038","last_updated":"2025-02-27T15:10:51Z","snapshot_observed_at":"2026-08-02T17:18:33.867969Z","submitted_at":"2025-01-14T20:59:37Z","title":"Do generative video models understand physical principles?","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-20T12:47:05.825659Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2501.09038"},"observation_digest":"sha256:88f8359cdaa5d678a1395f7f3047735da3a32a162780cddcf88b9f4709384810","observation_id":"412b4df4-37e4-4546-8fe9-9d919cadaec1","resolution":{"observed_at":"2026-05-20T12:47:05.894142Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2501.09686","last_updated":"2025-01-23T08:44:44Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-16T17:37:58Z","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","version":3},"reference_index":138,"source":"pdf_text","source_observed_at":"2026-05-15T21:20:59.128986Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2501.09686"},"observation_digest":"sha256:8e3562d018a813f1f0c0153cd4fede70fe7ae69786c4265db12671cc328ce840","observation_id":"af5e1950-1d1b-4cf1-9108-b245c7f21bcd","resolution":{"observed_at":"2026-05-15T21:20:59.288892Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2501.14249","last_updated":"2026-02-20T04:23:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-24T05:27:46Z","title":"Humanity's Last Exam","version":10},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-10T18:40:50.139345Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2501.14249"},"observation_digest":"sha256:66aaecc74370403dc9b4f1bd03a5b2ec5b5dd5b007c8d1702caa24ed309814ce","observation_id":"7ceabc31-aa91-46dd-97e1-43cef4c1a185","resolution":{"observed_at":"2026-05-10T23:26:25.883762Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2502.01941","last_updated":"2026-05-12T08:04:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-04T02:23:06Z","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","version":4},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-05-23T04:15:36.906263Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2502.01941"},"observation_digest":"sha256:835ea2b9dfe7c86c755088079b577b7f432bcb1d7821bb204c8726c9f881e09e","observation_id":"06984b8b-98b9-438c-aa10-b52545e32b64","resolution":{"observed_at":"2026-05-23T04:17:31.211761Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2502.18864","last_updated":"2025-02-26T06:17:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-26T06:17:13Z","title":"Towards an AI co-scientist","version":1},"reference_index":122,"source":"arxiv_source","source_observed_at":"2026-05-11T13:02:43.571234Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2502.18864"},"observation_digest":"sha256:8bae546e1559f9ebd4fb92046a5a49784dfc953ca189b28162f27e265ef052f5","observation_id":"a023a95d-9ed1-41f0-8143-ffd0049b7396","resolution":{"observed_at":"2026-05-11T13:02:44.826710Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2503.01743","last_updated":"2025-03-07T09:05:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-03T17:05:52Z","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-11T22:22:27.455361Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2503.01743"},"observation_digest":"sha256:ec16b5aa90328d56eaa8eee0f66ef512faece329df69814ff3348986d7272683","observation_id":"2ad8cbf1-a96d-4bee-a255-1e061f6aeede","resolution":{"observed_at":"2026-05-11T22:22:28.139480Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2504.11101","last_updated":"2026-05-06T07:49:45Z","snapshot_observed_at":"2026-07-06T21:09:40.867591Z","submitted_at":"2025-04-15T11:51:18Z","title":"Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-22T20:31:34.074705Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2504.11101"},"observation_digest":"sha256:9eb8b3c08f1eb70e54e401db35fb303e777b459602dda357fe06802b0dd53e21","observation_id":"0ddd7ef1-3f11-48bd-bd19-29aed95615ce","resolution":{"observed_at":"2026-05-22T20:32:04.650901Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2504.19678","last_updated":"2026-03-06T19:01:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-28T11:08:22Z","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","version":2},"reference_index":130,"source":"pdf_text","source_observed_at":"2026-05-15T02:57:37.873567Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2504.19678"},"observation_digest":"sha256:6d33ad2321c17702449939409f00af2305317af1aa51c8ae0360ac57f3f2854c","observation_id":"75e71827-cdf9-4db2-967e-915f3839ce01","resolution":{"observed_at":"2026-05-15T02:57:38.497701Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2506.04989","last_updated":"2026-04-09T13:09:20Z","snapshot_observed_at":"2026-07-06T21:37:13.957629Z","submitted_at":"2025-06-05T13:02:06Z","title":"BacPrep: Lessons from Deploying an LLM-Based Bacalaureat Assessment Platform","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-19T11:20:42.807705Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2506.04989"},"observation_digest":"sha256:d0e4f17d7bd9472e190d2ccbae412241986dc3ff66ff2ea69d84ae1868e36ead","observation_id":"2361ad68-2484-43e5-966c-7c8206d5f9a9","resolution":{"observed_at":"2026-05-19T11:22:16.448303Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2506.13674","last_updated":"2026-04-19T03:53:58Z","snapshot_observed_at":"2026-08-02T17:06:46.370930Z","submitted_at":"2025-06-16T16:30:26Z","title":"PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-19T09:24:04.289799Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2506.13674"},"observation_digest":"sha256:96fb9284b9c3fc8221841acd4a8451032b46e20f7a9d0a38261c021284c932c7","observation_id":"204b904e-2e3c-45b2-8acd-7be9f63e6e8a","resolution":{"observed_at":"2026-05-19T09:27:14.679600Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2507.10722","last_updated":"2026-04-10T03:29:37Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-14T18:43:05Z","title":"Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems","version":2},"reference_index":162,"source":"pdf_text","source_observed_at":"2026-05-19T04:37:33.928616Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2507.10722"},"observation_digest":"sha256:0510f9cd553446f64e3a76085329ade3bd7198ec959641cfe119901eaca79383","observation_id":"db9e0a50-6b49-499d-8873-ce9c82f4dc3b","resolution":{"observed_at":"2026-05-19T04:42:04.860990Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2507.23009","last_updated":"2026-05-11T11:47:15Z","snapshot_observed_at":"2026-07-06T22:05:22.373440Z","submitted_at":"2025-07-30T18:14:35Z","title":"Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-05-19T02:12:48.586913Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2507.23009"},"observation_digest":"sha256:b462a7643af4b0fa17755dda1de985ca579a5560869c65f3267f807e154aba6f","observation_id":"efceb3b3-d0ca-4cf2-af61-b6978a548905","resolution":{"observed_at":"2026-05-19T02:12:55.782077Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T19:28:56.492871Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.12464","last_updated":"2025-08-17T18:27:54Z","snapshot_observed_at":"2026-08-05T19:28:50.574948Z","submitted_at":"2025-08-17T18:27:54Z","title":"On the Fitness Landscape in the $NK$ Model","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T19:28:56.492871Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.12464"},"observation_digest":"sha256:e9ac1cacf0df95849b16f3b456968b81158ba70f1b1509c2b63104c8509de2af","observation_id":"e30c118b-69cd-4b7c-8904-701373841398","resolution":{"observed_at":"2026-08-05T19:28:56.492871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T17:37:55.701327Z","title":"Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16109","last_updated":"2025-08-22T05:54:11Z","snapshot_observed_at":"2026-08-05T17:37:36.785571Z","submitted_at":"2025-08-22T05:54:11Z","title":"From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-05T17:37:55.701327Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.16109"},"observation_digest":"sha256:ca0b73cf504b5321920c66f8b342deee0e8cacd6cc92502f3c196b56d786bd30","observation_id":"5f6540a8-3bba-4a13-b2d4-ae7ba72d7c58","resolution":{"observed_at":"2026-08-05T17:37:55.701327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T16:32:54.617595Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.18255","last_updated":"2025-09-02T17:12:12Z","snapshot_observed_at":"2026-08-05T16:32:51.675767Z","submitted_at":"2025-08-25T17:45:06Z","title":"Hermes 4 Technical Report","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T16:32:54.617595Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.18255"},"observation_digest":"sha256:ad3416f19b89c62f4d4ce2146b58d22c58c9d76b80f278d2285649f2321175aa","observation_id":"8fc494ae-05db-4b5a-8cbc-5580a31d71aa","resolution":{"observed_at":"2026-08-05T16:32:54.617595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T16:18:47.713752Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.18763","last_updated":"2025-08-26T07:41:33Z","snapshot_observed_at":"2026-08-05T16:18:30.204040Z","submitted_at":"2025-08-26T07:41:33Z","title":"Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-05T16:18:47.713752Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.18763"},"observation_digest":"sha256:1833c1c954e41100376f4b7af5850767270a7f368a2efc1dc62486768eebdce2","observation_id":"a23460fe-06c3-4ba8-9bd2-41b29e527746","resolution":{"observed_at":"2026-08-05T16:18:47.713752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T15:59:41.027509Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.19097","last_updated":"2025-08-26T14:59:19Z","snapshot_observed_at":"2026-08-05T15:59:39.757824Z","submitted_at":"2025-08-26T14:59:19Z","title":"Reasoning LLMs in the Medical Domain: A Literature Survey","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T15:59:41.027509Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.19097"},"observation_digest":"sha256:8356ce4939726f59d809c79f7037e943bf7696313e4bfbd27d7c44d47d0e4ec6","observation_id":"5315016e-8afe-40ef-90db-820f6ad3b11e","resolution":{"observed_at":"2026-08-05T15:59:41.027509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T15:54:13.387649Z","title":"Brown, Adam Santoro, Aditya Gupta, Adri\\` a Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.19221","last_updated":"2025-08-26T17:38:42Z","snapshot_observed_at":"2026-08-05T15:53:46.810306Z","submitted_at":"2025-08-26T17:38:42Z","title":"Evaluating the Evaluators: Are readability metrics good measures of readability?","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-05T15:54:13.387649Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.19221"},"observation_digest":"sha256:eb3b53b373df64061e544c5dc2ffb6b8ff5c60d6764e0697b461b18f655b362a","observation_id":"6a594cb1-b98e-4d5f-8528-16f03b91efb4","resolution":{"observed_at":"2026-08-05T15:54:13.387649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T15:38:53.017843Z","title":"Brown, Adam Santoro, Aditya Gupta, and Adrià Garriga-Alonso et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.19689","last_updated":"2025-08-27T08:52:47Z","snapshot_observed_at":"2026-08-05T22:14:58.306507Z","submitted_at":"2025-08-27T08:52:47Z","title":"Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality","version":1},"reference_index":155,"source":"arxiv_source","source_observed_at":"2026-08-05T15:38:53.017843Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.19689"},"observation_digest":"sha256:de2febd4d6401b5658bda64a4b4669d1976779fb7870f9056f69f15e982ea051","observation_id":"fd51c550-1561-4a14-9e7f-047059636e3d","resolution":{"observed_at":"2026-08-05T15:38:53.017843Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T15:18:04.692533Z","title":"Beyond the imitation game: Quanti- fying and extrapolating the capabilities of language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.20019","last_updated":"2025-08-27T16:27:57Z","snapshot_observed_at":"2026-08-05T15:18:04.163646Z","submitted_at":"2025-08-27T16:27:57Z","title":"Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T15:18:04.692533Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.20019"},"observation_digest":"sha256:9db6c746b579378ccf1852c6e5516aa4eb177e9bd1a899bba212194dc65c0f16","observation_id":"27445dd4-fed1-4a6c-bf1b-50c73c95e310","resolution":{"observed_at":"2026-08-05T15:18:04.692533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T15:09:57.600054Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models ( BIG -bench)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.20410","last_updated":"2025-09-03T23:48:21Z","snapshot_observed_at":"2026-08-05T15:09:32.902408Z","submitted_at":"2025-08-28T04:20:00Z","title":"UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools","version":3},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-05T15:09:57.600054Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.20410"},"observation_digest":"sha256:28c6c55f62226a40000674e14243843fc69c718ff9bb643f2dec7689e8e63c3d","observation_id":"4bc571d7-7ab6-4154-810c-63e8604c644e","resolution":{"observed_at":"2026-08-05T15:09:57.600054Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T14:23:46.003938Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.21368","last_updated":"2025-08-29T07:17:44Z","snapshot_observed_at":"2026-08-05T14:23:43.989428Z","submitted_at":"2025-08-29T07:17:44Z","title":"EconAgentic in DePIN Markets: A Large Language Model Approach to the Sharing Economy of Decentralized Physical Infrastructure","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T14:23:46.003938Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2508.21368"},"observation_digest":"sha256:a3a9c34cd66aeac77435f643efa6c4f3abe6b6a82ed8ce07e2bc89e99b681daf","observation_id":"4a9098ef-29ab-4c09-b6a2-d21341d7fa32","resolution":{"observed_at":"2026-08-05T14:23:46.003938Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2509.00081","last_updated":"2026-04-24T20:40:48Z","snapshot_observed_at":"2026-07-06T22:20:50.350336Z","submitted_at":"2025-08-26T23:17:33Z","title":"Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-18T20:31:49.857895Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2509.00081"},"observation_digest":"sha256:95bd695652d1320502bd58ac4e64ee2f34c3b28021fccd745ad95f269b94500e","observation_id":"e7d87052-6883-4476-9245-600fb22d3202","resolution":{"observed_at":"2026-05-18T20:32:50.792744Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T13:38:13.829092Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00465","last_updated":"2025-08-30T11:42:26Z","snapshot_observed_at":"2026-08-05T13:42:43.558974Z","submitted_at":"2025-08-30T11:42:26Z","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","version":1},"reference_index":209,"source":"pdf_text","source_observed_at":"2026-08-05T13:38:13.829092Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2509.00465"},"observation_digest":"sha256:cf0e4585c32cbd07327c0f7b9c740642237961e8b78348b559b99c18165cba3d","observation_id":"d5f5afae-f386-4fe8-b212-af161c2ad934","resolution":{"observed_at":"2026-08-05T13:38:13.829092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T10:50:29.767755Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models (arxiv: 2206.04615)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03644","last_updated":"2025-09-03T18:50:18Z","snapshot_observed_at":"2026-08-05T10:50:26.088684Z","submitted_at":"2025-09-03T18:50:18Z","title":"Towards a Neurosymbolic Reasoning System Grounded in Schematic Representations","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-05T10:50:29.767755Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2509.03644"},"observation_digest":"sha256:6b26c893543737cb6e1c166d4e9d29def5a62198418d7306ffd8f165e22fb882","observation_id":"ca2b94d9-0269-4cd1-8c6a-327474dc476c","resolution":{"observed_at":"2026-08-05T10:50:29.767755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T05:04:52.721966Z","title":"arXiv preprint arXiv:2206.04615 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05764","last_updated":"2025-09-06T16:29:42Z","snapshot_observed_at":"2026-08-05T05:04:52.222364Z","submitted_at":"2025-09-06T16:29:42Z","title":"DRF: LLM-AGENT Dynamic Reputation Filtering Framework","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T05:04:52.721966Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2509.05764"},"observation_digest":"sha256:4ab452451d4c3c0c3e4824e4802c91e73e413a594498156dcfc74130f85cac6d","observation_id":"1ff49f81-3b69-4131-93be-246f21f9f462","resolution":{"observed_at":"2026-08-05T05:04:52.721966Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-04T19:58:55.139238Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08960","last_updated":"2025-09-10T19:47:46Z","snapshot_observed_at":"2026-08-04T19:58:51.260565Z","submitted_at":"2025-09-10T19:47:46Z","title":"BRoverbs -- Measuring how much LLMs understand Portuguese proverbs","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-04T19:58:55.139238Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2509.08960"},"observation_digest":"sha256:17642b424e32755d7679905eba0b45050966accd3cdafb707463db42a76dbcbb","observation_id":"d94a7094-33a6-496c-8b91-fffe2a4e0777","resolution":{"observed_at":"2026-08-04T19:58:55.139238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2509.13324","last_updated":"2026-05-05T01:57:59Z","snapshot_observed_at":"2026-07-06T22:30:02.223630Z","submitted_at":"2025-08-17T21:56:06Z","title":"Designing Psychometric Bias Measures for ChatBots: An Application to Racial Bias Measurement","version":3},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-05-18T22:12:15.876447Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2509.13324"},"observation_digest":"sha256:7d38c0f76c5b824a873fc25e223a26f95017f462b7648b8f748824edc18fd8f2","observation_id":"f6bd6156-db78-4c68-96ac-890b8f526955","resolution":{"observed_at":"2026-05-18T22:12:51.645229Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2510.01409","last_updated":"2026-04-24T19:29:08Z","snapshot_observed_at":"2026-08-05T23:36:49.198317Z","submitted_at":"2025-10-01T19:46:15Z","title":"OntoLogX: Ontology-Guided Knowledge Graph Extraction from Cybersecurity Logs with Large Language Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-18T10:09:08.307199Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2510.01409"},"observation_digest":"sha256:323187327b1e9180add9e29a895b63e648e609111afb22e020d612e6dd5141eb","observation_id":"e7b4900c-c7d6-4aac-a18f-5b204c5e0ccd","resolution":{"observed_at":"2026-05-18T10:11:14.049897Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-04T12:45:26.750295Z","title":"Brown, Adam Santoro, Aditya Gupta, Adri\\` a Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.02480","last_updated":"2026-05-27T22:55:59Z","snapshot_observed_at":"2026-08-04T12:45:19.590090Z","submitted_at":"2025-10-02T18:36:10Z","title":"Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting","version":3},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-04T12:45:26.750295Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2510.02480"},"observation_digest":"sha256:2537097bffc15271334be2e7a9c30dfbe55b355b9f6d162a90e84311fec4946b","observation_id":"cde58f09-7efa-495d-8171-387b557312c6","resolution":{"observed_at":"2026-08-04T12:45:26.750295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2510.04265","last_updated":"2026-05-12T01:55:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-10-05T16:14:03Z","title":"Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-18T10:04:39.223895Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2510.04265"},"observation_digest":"sha256:60004898670a239637d85cf40cb846019b8f9af86ac646f65757a6001f6b4c31","observation_id":"80be55b5-0748-45e0-a2ec-247eaa29da5c","resolution":{"observed_at":"2026-05-18T10:06:13.954720Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-04T10:40:58.226873Z","title":"Cited as a general reference for HHH-style evaluation context","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.09330","last_updated":"2026-05-31T10:03:39Z","snapshot_observed_at":"2026-08-04T10:40:55.499553Z","submitted_at":"2025-10-10T12:32:43Z","title":"Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T10:40:58.226873Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2510.09330"},"observation_digest":"sha256:ca9a6f9b55961ff54034ed39a9035b19449bfb46e8d03b4b4f9cb9b0add1f7fa","observation_id":"319e9b58-67a0-441e-9d78-f2a7366e8fd7","resolution":{"observed_at":"2026-08-04T10:40:58.226873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2510.13786","last_updated":"2025-10-15T17:43:03Z","snapshot_observed_at":"2026-07-06T22:32:47.087967Z","submitted_at":"2025-10-15T17:43:03Z","title":"The Art of Scaling Reinforcement Learning Compute for LLMs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-16T16:29:13.954029Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2510.13786"},"observation_digest":"sha256:6951e4b0539229af1f71430d2935ce79403001862c60f84dd9c3022844cb37c5","observation_id":"a3e4bc57-bbd7-42e9-a1b9-7b1ca3204f87","resolution":{"observed_at":"2026-05-16T16:29:14.034600Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2510.26083","last_updated":"2026-04-08T13:55:00Z","snapshot_observed_at":"2026-07-06T22:34:28.484520Z","submitted_at":"2025-10-30T02:41:54Z","title":"Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-18T03:05:06.069642Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2510.26083"},"observation_digest":"sha256:6a3fc87a21803a7de7e5e5d078041b5e67ce85b0f5fb1335e5a1de0cd14c6213","observation_id":"854d13bd-fdbf-443a-a3c1-f9df365e5b8a","resolution":{"observed_at":"2026-05-18T03:05:48.081120Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2511.02627","last_updated":"2026-06-11T15:36:40Z","snapshot_observed_at":"2026-08-04T00:11:48.936857Z","submitted_at":"2025-11-04T14:57:11Z","title":"DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-18T01:18:44.523602Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2511.02627"},"observation_digest":"sha256:eac8f7527ba970f6d0e65584cb2f68545aa3fae2a271a264fb8b792631a1f8b9","observation_id":"3b88ff94-1e23-46d1-a5ca-4b9005d66098","resolution":{"observed_at":"2026-05-18T01:20:34.413999Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-04T00:11:52.162655Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.02627","last_updated":"2026-06-11T15:36:40Z","snapshot_observed_at":"2026-08-04T00:11:48.936857Z","submitted_at":"2025-11-04T14:57:11Z","title":"DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T00:11:52.162655Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2511.02627"},"observation_digest":"sha256:b6102f73040c3e285c0ad12470312d00f2135ce24bc6a0c9d181816ff9f24a53","observation_id":"0c49015a-43ae-444c-bd7e-88131d4a7d83","resolution":{"observed_at":"2026-08-04T00:11:52.162655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2511.05501","last_updated":"2026-04-28T16:06:15Z","snapshot_observed_at":"2026-07-06T22:35:13.699594Z","submitted_at":"2025-09-30T21:36:23Z","title":"Towards Real-World Validity in Generative AI Benchmarks: Understanding and Designing Domain-Centered Evaluations for Journalism Practitioners","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-18T10:59:16.139525Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2511.05501"},"observation_digest":"sha256:ea69739d10ecfd8387bec10880d8a639527a1f2f550a73d578f06aa015a096e2","observation_id":"783aef56-55e9-4758-a1c9-d04e478c10a4","resolution":{"observed_at":"2026-05-18T11:01:17.135129Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-03T21:09:38.915404Z","title":"Norbert Vanek and Haoruo Zhang","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.16527","last_updated":"2026-06-29T08:31:48Z","snapshot_observed_at":"2026-08-03T21:09:37.395196Z","submitted_at":"2025-11-20T16:41:36Z","title":"Contrastive vision-language learning with paraphrasing and negation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T21:09:38.915404Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2511.16527"},"observation_digest":"sha256:5e5e066e8af48aad77c2b86f4348d75f1033df9e624cfd5d32c169a5987daeca","observation_id":"d7849b73-2840-4e4a-a39d-98d78d63ae77","resolution":{"observed_at":"2026-08-03T21:09:38.915404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2512.13564","last_updated":"2026-01-13T09:33:57Z","snapshot_observed_at":"2026-07-30T04:57:05.391864Z","submitted_at":"2025-12-15T17:22:34Z","title":"Memory in the Age of AI Agents","version":2},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-05-11T18:18:19.911342Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2512.13564"},"observation_digest":"sha256:1f6d4244c65352f86167679bbe333517d1cf7e9478e941dba17e0371114c2edc","observation_id":"9910e596-a17e-4a09-8ee8-bdde9bcf70d5","resolution":{"observed_at":"2026-05-11T18:18:20.401592Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2512.21110","last_updated":"2026-04-24T20:27:34Z","snapshot_observed_at":"2026-07-06T22:39:58.137482Z","submitted_at":"2025-12-24T11:15:57Z","title":"Beyond Context: Large Language Models' Failure to Grasp Users' Intent","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-16T20:09:25.827452Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2512.21110"},"observation_digest":"sha256:2db0afc557f56c43dbf3f060eb9f1457000b918f3641b2f55d28dc28636082ba","observation_id":"8cbe9bf7-32e8-43ca-aa7a-22c6c3e1a805","resolution":{"observed_at":"2026-05-16T20:11:13.634496Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2601.14053","last_updated":"2026-04-16T15:26:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-01-20T15:06:19Z","title":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","version":2},"reference_index":145,"source":"pdf_text","source_observed_at":"2026-05-16T12:47:28.248540Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2601.14053"},"observation_digest":"sha256:5752ca43f5cf5d96eac3e05543a70f396a75d2f4f4f40ad483a75fb5d3baf5ab","observation_id":"d1f6dc17-0cf5-437c-a7b8-d7322cc96c0c","resolution":{"observed_at":"2026-05-16T12:47:53.638767Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-03T06:46:26.348309Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models.arXiv preprint arXiv:2206.04615, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2601.22025","last_updated":"2026-06-09T23:57:32Z","snapshot_observed_at":"2026-08-05T13:58:45.670760Z","submitted_at":"2026-01-29T17:32:34Z","title":"When Generic Prompt Improvements Hurt: Evaluation-Driven Iteration for LLM Applications","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T06:46:26.348309Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2601.22025"},"observation_digest":"sha256:57805e166a97ca76711089b55d10deba345fdcdc5f746b07fd1e5991cb0ad173","observation_id":"52b1f8f9-cd37-4b3d-9806-07d0c9eaf17f","resolution":{"observed_at":"2026-08-03T06:46:26.348309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-03T04:23:24.116611Z","title":"Beyond the Imitation Game: Quantifying and simulating the capabilities of large language models.arXiv preprint arXiv:2206.04615,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.11201","last_updated":"2026-06-05T15:01:24Z","snapshot_observed_at":"2026-08-04T06:01:52.357308Z","submitted_at":"2026-02-04T21:55:57Z","title":"Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning","version":2},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-03T04:23:24.116611Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2602.11201"},"observation_digest":"sha256:de5dce03e246662b894a2283ab003fea77b4a92c839edf5a57543c66a159c7ea","observation_id":"1f21422c-1069-42a7-88db-dca543e86cba","resolution":{"observed_at":"2026-08-03T04:23:24.116611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-02T23:56:43.635300Z","title":"Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.12424","last_updated":"2026-06-09T01:12:23Z","snapshot_observed_at":"2026-08-04T02:54:50.405793Z","submitted_at":"2026-02-12T21:28:46Z","title":"RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T23:56:43.635300Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2602.12424"},"observation_digest":"sha256:d1e95434fff6d5fd9ee907968dfb84c68f64524b4ee04ae90bd77e76ee0a415a","observation_id":"272130d4-2c34-4bf2-8dde-3596f4889729","resolution":{"observed_at":"2026-08-02T23:56:43.635300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-02T22:08:42.809515Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.17993","last_updated":"2026-07-12T00:58:22Z","snapshot_observed_at":"2026-08-04T01:08:51.761680Z","submitted_at":"2026-02-20T05:01:32Z","title":"Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T22:08:42.809515Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2602.17993"},"observation_digest":"sha256:dff280af34e2c607500c77cad429312714644458bfa28c6b03f1ea5458ea5ff2","observation_id":"c140785b-4a83-416f-b3cd-a0029e39f001","resolution":{"observed_at":"2026-08-02T22:08:42.809515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-02T21:28:31.091238Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2602.20094","last_updated":"2026-06-25T19:27:55Z","snapshot_observed_at":"2026-08-05T06:19:04.359386Z","submitted_at":"2026-02-23T18:06:15Z","title":"CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T21:28:31.091238Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2602.20094"},"observation_digest":"sha256:8f1a33ce2979e82c3bcb50db2cdfe90c7b70820875c90bf632930b92d15d77ff","observation_id":"4c0aaf51-26a8-4fba-95cd-e6e0708aa674","resolution":{"observed_at":"2026-08-02T21:28:31.091238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2603.06635","last_updated":"2026-04-28T19:02:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-02-24T13:46:35Z","title":"Graph Property Inference in Small Language Models: Effects of Representation and Reasoning Strategy","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-15T20:07:07.522017Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2603.06635"},"observation_digest":"sha256:b39ff2354c25ae8a17c93c7a536c5693481e8e4e397335c1b5d35112d9fd574f","observation_id":"04320c7b-90d2-45b4-a803-b26a1c80f824","resolution":{"observed_at":"2026-05-15T20:10:18.559695Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2604.03877","last_updated":"2026-04-04T22:00:22Z","snapshot_observed_at":"2026-08-02T19:57:28.366042Z","submitted_at":"2026-04-04T22:00:22Z","title":"When Models Know More Than They Say: Probing Analogical Reasoning in LLMs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2604.03877"},"observation_digest":"sha256:da26066e2cfdcb66757ca3214b3f5dd5ad0b71859dd9745103c5c39b6c0b9dfd","observation_id":"301c55de-fbe7-4ca3-b28f-d157955d06e9","resolution":{"observed_at":"2026-05-13T16:52:59.652395Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2604.05912","last_updated":"2026-04-07T14:15:45Z","snapshot_observed_at":"2026-07-06T22:54:30.567988Z","submitted_at":"2026-04-07T14:15:45Z","title":"FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-05-10T19:49:32.983778Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2604.05912"},"observation_digest":"sha256:cbd88b8aad6e338199523f61d5f543b1fed28e2c3698ae26a42af6884ec21373","observation_id":"0c175797-94bc-4917-bc83-75eac0c795d4","resolution":{"observed_at":"2026-05-10T23:26:25.883762Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2604.12049","last_updated":"2026-04-13T20:41:36Z","snapshot_observed_at":"2026-08-03T03:51:16.996563Z","submitted_at":"2026-04-13T20:41:36Z","title":"Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T15:11:35.346010Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2604.12049"},"observation_digest":"sha256:42527ef49ae1bc3b0a0ec8d21846c2b4741a70c1192fae5149ba393a135dd04c","observation_id":"54d18fb5-ad1e-498f-b34e-6e2e2af628a4","resolution":{"observed_at":"2026-05-10T23:26:25.883762Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":"2206.04615","doi":"10.1162/tacl_a_00688","metadata_source":"pith","pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","venue":"cs.CL","work_id":"bb63abb3-0d50-4362-b97c-b5e725b03b39","year":2022},"citing_paper":{"arxiv_id":"2604.12116","last_updated":"2026-05-24T06:41:18Z","snapshot_observed_at":"2026-08-02T05:40:32.176239Z","submitted_at":"2026-04-13T22:50:21Z","title":"The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T15:23:26.128263Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2604.12116"},"observation_digest":"sha256:03a80d564d0636326beabe91e0cd110acbe70e3e998dae6972e0871bfd175ff3","observation_id":"addbe7bf-e89d-4757-9468-bbcfaa47bc1f","resolution":{"observed_at":"2026-05-11T10:41:02.922816Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-07-12T21:35:10.173253Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.12116","last_updated":"2026-05-24T06:41:18Z","snapshot_observed_at":"2026-08-02T05:40:32.176239Z","submitted_at":"2026-04-13T22:50:21Z","title":"The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T21:35:10.173253Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2604.12116"},"observation_digest":"sha256:b6f7759d085829d1edff68d3f261846f343721acf02a48db73ee85bf5bb3c5dc","observation_id":"cd5c6406-627a-4879-a478-656a49e76187","resolution":{"observed_at":"2026-07-12T21:35:10.173253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2206.04615/citation-record","integrity":"/paper/2206.04615/integrity","json":"/paper/2206.04615/citation-record.json","paper":"/paper/2206.04615"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/n19-1245","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"MathQA: Towards interpretable math word problem solving with operation-based formalisms","venue":null,"work_id":"b73d762e-5f33-41a0-a44d-b2e613bffd36","year":2019},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:a956a5848955da82afea80f7bfaee2990209c8e3ccf3ea482cc09167f1c68418","observation_id":"499806ea-bbf2-4490-bbe7-dd3bcd80cd63","resolution":{"observed_at":"2026-05-10T23:26:25.778350Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-13T22:22:22.182129+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T22:22:22.182129+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1126/science.177.4047.393","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":"Science","work_id":"d27e9bf2-171d-4cc9-bada-506cc2da0e28","year":1972},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:d28629621778bb6fa05d0dfd254f7cf70be0e79eca4610a7b8163636835241cc","observation_id":"b3f33b82-cb8f-4a1c-8b27-ffb40ba3e906","resolution":{"observed_at":"2026-05-10T23:26:25.505769Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2020.8782","doi":"10.15390/eb.2020.8782","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":"TED EĞİTİM VE BİLİM","work_id":"18b15dc2-febe-42c2-8549-4a785bbd2dfa","year":2001},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:8951263576b0807b8c1df086abb77082fb82a3692e426b0b26d7c40cf64d6fc0","observation_id":"5b4d2b85-d7ba-4ca5-b9b0-fe4bed041872","resolution":{"observed_at":"2026-05-10T23:26:25.518933Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":"2108.07258","doi":"10.1016/j.specom.2008.12.003","metadata_source":"pith","pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"On the Opportunities and Risks of Foundation Models","venue":"cs.LG","work_id":"a18039e9-928d-47c9-a836-32656a71bf71","year":2021},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-11T11:50:26.030339Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:0d3eae9d5b8b44f01796c164ce47f5a2aa7ca8dd806d784fb0d0ba9c34e2d5bf","observation_id":"fccc22d1-56e2-4d45-a925-29e86d794ee7","resolution":{"observed_at":"2026-05-10T23:26:25.529016Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-05-24T09:22:59.787075+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T09:22:59.787075+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/w18-6433","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/W18-6433","venue":null,"work_id":"f4b97612-127d-4e16-95de-ebe9267b3d55","year":1964},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:f0331d93e6c7ce8988fba65f7a7084ae54b819e26d7bcc30a73babfa7a1ba8f6","observation_id":"a1c6ef8b-9b33-45a4-9277-21817768be6d","resolution":{"observed_at":"2026-05-10T23:26:25.543638Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/s1364-6613(02)00005-0","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Simplicity: a unifying principle in cognitive science? , volume =","venue":"Trends in Cognitive Sciences","work_id":"43cafb9d-3ad9-4b80-8d38-c36ba6c7d7c6","year":2020},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:19614cf2fdef4848b1d288fa29643e3daa651186af7411d20966674b41146a0b","observation_id":"4146ebab-a66e-4011-adfe-a37e05701b55","resolution":{"observed_at":"2026-05-10T23:26:25.550296Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/w19-3824","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/W19-3824","venue":null,"work_id":"0966adf1-c9ba-4d18-8096-741c1bd8c883","year":2019},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:354af0e3a116353965553ec60519e8feadc17294f905e8a94988ec7c83ad196f","observation_id":"39fd2b3e-a7a1-45e4-835f-59cb7b62045b","resolution":{"observed_at":"2026-05-10T23:26:25.558222Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-319-40566-7_4","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.1007/978-3-319-40566-7_4","venue":"Lecture notes in computer science","work_id":"12cbd958-e3ba-44f6-91b7-13279605ee2b","year":null},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:95f2f950e5a33a2a53529be4f26ffb909ff6a69864ea6028595eeb731c2caaf8","observation_id":"8a79cc0b-eea7-4202-8267-ea89daf77dd8","resolution":{"observed_at":"2026-05-10T23:26:25.562410Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s10994-019-05862-7","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"overinformative","venue":"Machine Learning","work_id":"8b338a4f-ef26-43dd-a387-d44f38ef523f","year":2015},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:ecce8f61fb05a26571b68a364ba22a4ecb601c4fc56d21caeca521c950f33ba0","observation_id":"97543141-53c3-408b-a2a8-81373b042ea0","resolution":{"observed_at":"2026-05-10T23:26:25.566922Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/j.jtbi.2014.01.028","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":"Journal of Theoretical Biology","work_id":"b2f8e529-2490-4b9d-a5cd-897492f733e7","year":2014},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:f79ccb88bce9e49055216d76345e9f58cdbbaf326b03ef16d127355824a3a967","observation_id":"d0676663-d3ef-47e7-8d71-97e29573918f","resolution":{"observed_at":"2026-05-10T23:26:25.574294Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.02227","last_updated":"2020-07-14T03:16:30Z","snapshot_observed_at":"2026-08-05T11:02:05.463113Z","submitted_at":"2019-10-05T07:48:55Z","title":"Making sense of sensory input","version":2},"cited_work":{"arxiv_id":"1910.02227","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1910.02227","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"(cited on p","venue":null,"work_id":"ee363ee4-aa44-4760-a7a4-0aa1191c7a07","year":1910},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"cited_paper":"/paper/1910.02227","citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:e62bc26513cf1cb836677566f88e98dfde139ff65bcd8adc7452ab263bfc6672","observation_id":"bb376dd7-54e5-4a40-be04-f253ea6b370e","resolution":{"observed_at":"2026-05-10T23:26:25.843131Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/n19-1395","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/N19-1395","venue":null,"work_id":"4c15d428-ae08-48bb-8ca1-f1d28a02749c","year":null},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:31b949352a4fbce58887b3155b9b30658e6c8bd7ca188fd5d875991c4ab95d03","observation_id":"2cf03759-18fd-43ff-8cae-3ad10a984262","resolution":{"observed_at":"2026-05-10T23:26:25.618260Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/p18-1082","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/P18-1082","venue":null,"work_id":"c375569a-4c17-4018-9dce-9e14337bd47a","year":2018},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:1782c4fb3e3e4b86cce9736ee3a2f5aa72240a1332c61de2659a1e5492a6143c","observation_id":"7ca183db-c8a3-481f-af4f-623814213246","resolution":{"observed_at":"2026-05-10T23:26:25.622610Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-17T21:20:54.696683+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-17T21:20:54.696683+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/0010-0277(88)90031-5","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Fodor and Zenon W","venue":"Cognition","work_id":"e749561b-4945-4b97-8e27-445cd1aa97d2","year":2025},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:8a2525f70adf9c66b65164fede8b50c7435e2629717cd01c229df90a78c4921e","observation_id":"f6546cd8-dd12-4765-a18e-80c45a3645e1","resolution":{"observed_at":"2026-05-10T23:26:25.630445Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-05-22T10:52:48.927348+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-22T10:52:48.927348+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"5275.162553","doi":"10.5555/1625275.1625535","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"doi: 10.5555/1625275.1625535","venue":null,"work_id":"7c95216f-9c4b-4d7a-8c10-794eb6ed2ae8","year":2022},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:17e7ff792b36ca7692d09421acc19703246b62ebdc6fc3eaf79eb67fc651ade5","observation_id":"524977f3-62e1-4c1f-be93-0d118172103f","resolution":{"observed_at":"2026-05-10T23:26:25.636170Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1073/pnas.1619666114","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":"Proceedings of the National Academy of Sciences","work_id":"552a8c74-c94c-4876-874e-f4d8c5153425","year":2017},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:02f68f22c99dae4d0bc919e17384347a13084efb7a4fdc894255e22ba6a01026","observation_id":"b2f4698a-62f4-4395-ae66-d47c8c61a3f7","resolution":{"observed_at":"2026-05-10T23:26:25.642596Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/n19-1061","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/N19-1061","venue":null,"work_id":"61915a52-d968-4a7e-ab83-1e2be0bd5936","year":2019},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:a9dce501a7d15e92e400e501d1fb80a853e9823083200958de42aced735fb638","observation_id":"903fb3e9-d637-4c24-bcfe-a7d15167bd7c","resolution":{"observed_at":"2026-05-10T23:26:25.648277Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-13T00:49:23.944509+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T00:49:23.944509+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.35111/0z6y-q265","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URL https://doi.org/10.35111/0z6y-q265","venue":"Americanae (AECID Library)","work_id":"0d2e59bf-7af0-4259-ab9b-9b9d1128999f","year":2003},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:8ba1b53035a8a9e28342d4b6203774d65334d027538c58a789a3e8e23f8186c9","observation_id":"5b1d8f6c-a77e-45e7-99c8-776eda943dbe","resolution":{"observed_at":"2026-05-10T23:26:25.658135Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"5844.192642","doi":"10.1145/1925844.1926423","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URL https://doi.org/10.1145/1925844.1926423","venue":"ACM SIGPLAN Notices","work_id":"c4e12e5f-44fa-4459-91d6-9b3d2a95e367","year":2011},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:6bff41a57bc12725f1cf0d44b99138eb8018ba2f21476479cb889743b3c6e55a","observation_id":"761b008f-20c5-4bed-98d1-2e7d43ebf516","resolution":{"observed_at":"2026-05-10T23:26:25.663352Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-05-30T14:55:20.684546+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-30T14:55:20.684546+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/bf02172093","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":"Journal of Autism and Developmental Disorders","work_id":"9a18c267-65a0-42d4-94ca-3cc7fe78bd47","year":1994},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:87614fda50b215b21cfd4fb65a636f213b2eadf579ab8db7cb3daf72fd7c9863","observation_id":"b87c8db7-c871-425b-aa99-3f54658d6a31","resolution":{"observed_at":"2026-05-10T23:26:25.668517Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1017/s0140525x0999152x","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Henrich, S","venue":"Behavioral and Brain Sciences","work_id":"0dc6bcd3-06c9-44ba-951a-b7da18e364ad","year":2010},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:345803b76a8be864de4b793c472cf501fe7ae4fb6a0bb49f041c48d7a79dc7d8","observation_id":"7ce107d8-6f8b-4a64-bb32-ecb300aed9ad","resolution":{"observed_at":"2026-05-10T23:26:25.671917Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.2478/9783110410167/html","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"29) China Household Management Research Center, Ministry of Public Security","venue":null,"work_id":"b70f053a-7d33-47e3-9105-970b2ab786b1","year":2018},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:0835f00582b715a093ac77dded76bc2dd78f5b780156146923c99d80fc79bda9","observation_id":"e6a67e0f-d32d-4156-b59e-4aa5616ccb6f","resolution":{"observed_at":"2026-05-10T23:26:25.679268Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2020.acl-main.164","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/2020.acl-main.164","venue":null,"work_id":"c576254b-16e1-4664-a02a-a8d100b457f4","year":2020},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:2c0028252fdbe3c76d028afc04a0008734c08e4fc9351361f73a356cb0ee0836","observation_id":"f6f6bbaf-1890-4453-b1fb-fc4178b9beb9","resolution":{"observed_at":"2026-05-10T23:26:25.684446Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-12T14:49:33.446459+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T14:49:33.446459+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2020.acl-main.232","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":null,"work_id":"3dfda765-01bc-4ad9-bc0b-5a7839838d76","year":2007},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:d4f11a43e36745f6c90096feef079da2f5a5ec971aadc0e423672b05ec06cb17","observation_id":"a0c8357e-077c-456f-95f3-fa0a7f76b497","resolution":{"observed_at":"2026-05-10T23:26:25.694224Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.3115/v1/p15-2124","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":null,"work_id":"1a833ca8-78b8-4170-890e-aa0cc74144eb","year":2005},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:e354cf1b96534fcf173eaf9293dc2cc8ba49ac6c69210dda2c13caed48e94c7c","observation_id":"b6f0dd71-dd83-4cce-9fc7-83a3b29def67","resolution":{"observed_at":"2026-05-10T23:26:25.699993Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1162/tacl_a_00023","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The N arrative QA reading comprehension challenge","venue":"Transactions of the Association for Computational Linguistics","work_id":"82006945-c336-4164-9c68-f07125cc331d","year":2018},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:550a55a2dae3652803174184d92552c25a9e10fcf2ba86f8c5ff9cb0ea5d31c5","observation_id":"ca22ed36-c860-4d89-9fec-1bb709f5652c","resolution":{"observed_at":"2026-05-10T23:26:25.703976Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-13T13:50:26.926336+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T13:50:26.926336+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s10992-020-09581-6","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URL https://doi.org/10.1007/s10992-020-09581-6","venue":"Journal of Philosophical Logic","work_id":"4979342b-42fb-4907-bd1b-af9a1201fcd3","year":2020},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:fad63f81bec3b68c39c87351a2ed01efae7a7a86e7a11acb896f7adda24b17b2","observation_id":"38a947b5-7079-4c93-88ac-6a87896fabc0","resolution":{"observed_at":"2026-05-10T23:26:25.707647Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2020.acl-main.653","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":null,"work_id":"cbab1242-0292-4249-90dd-2da563e8e359","year":2020},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:2bf4db1606c841a32da5c54590b012ba15c4d16a90aef6f5faf874a13da7eae7","observation_id":"b6e2d620-b30b-4b4c-99d1-bb0b9819d509","resolution":{"observed_at":"2026-05-10T23:26:25.717113Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/w19-3005","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/W19-3005","venue":null,"work_id":"a25240cb-d15c-4bd9-9271-0cee370a60f4","year":2019},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:28f8154b4b42548869732c8ad179cb4e0de55362f127b26743c8a09a7429c4da","observation_id":"67137944-82f1-4b14-ae6a-fbc76ee12077","resolution":{"observed_at":"2026-05-10T23:26:25.723283Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/n19-1063","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"and Rudinger, Rachel","venue":null,"work_id":"88f8dce9-17cc-41c1-a26a-e9b502ca0742","year":2019},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:edb497c46336a36bd8e77020b6b120ca1c1357e21de25d701b1250ce138560db","observation_id":"107b8f27-6805-4849-bd17-bf3c36680518","resolution":{"observed_at":"2026-05-10T23:26:25.726946Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-11T12:48:58.740552+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T12:48:58.740552+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/0306-4573(91)90066-u","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Andere zeiten, andere lehren","venue":"Information Processing & Management","work_id":"12164bb3-9cb2-443b-81e5-f3aabaaf9073","year":2005},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:e79fcb7107be231ff82284b6b90cf0cab3c6c22409421f35b392d85e4f906189","observation_id":"df711b25-1885-4ae8-aba9-904d944a6714","resolution":{"observed_at":"2026-05-10T23:26:25.733673Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"31) David Milne and Ian H","venue":null,"work_id":"0c63e084-5bed-4b41-8716-edf1d474b691","year":null},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:12015021cc9055d1656d75fa607ccadf2a074efc02723b138d2cab1a322aa097","observation_id":"dfcc865a-7bcf-40cd-a00a-7ada0c416117","resolution":{"observed_at":"2026-05-10T23:26:25.865742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/w19-3004","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URLhttps://www.aaai.org/Papers/Workshops/2008/WS- 08-15/WS08-15-005.pdf","venue":null,"work_id":"82348546-159e-4be7-a64a-bde7fd7f63e0","year":2008},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:eb327aed5030b084173ae5b0564473057fa792c60e693fed1561d88ce1c4f8e1","observation_id":"49d99f63-600b-47de-9374-a6d684d8fef2","resolution":{"observed_at":"2026-05-10T23:26:25.753871Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.08127","last_updated":"2021-02-19T03:24:24Z","snapshot_observed_at":"2026-08-03T04:24:28.195669Z","submitted_at":"2020-10-16T03:07:49Z","title":"The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers","version":2},"cited_work":{"arxiv_id":"2010.08127","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.08127","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The deep boot- strap framework: Good online learners are good offline generalizers.arXiv preprint arXiv:2010.08127","venue":null,"work_id":"b3aa582e-c46c-4145-85bc-1eba40c4ce5c","year":2010},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"cited_paper":"/paper/2010.08127","citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:f3b77d94ece03f4d57dae59f8bdb2e1acfb787582766b4cb0126c4142b34860e","observation_id":"9d40431e-0780-4aa4-993e-42d853c25105","resolution":{"observed_at":"2026-05-10T23:26:25.855730Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/d18-1206","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Cohen, and Mirella Lapata","venue":null,"work_id":"81c65d3c-3f2d-4368-8d20-570c7afcc196","year":2018},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:37fade70dca5d32c2547821cf004fcbb9df9ec3805224e2beaabec4a4c39fcda","observation_id":"20abb63c-278d-4e6e-8a6d-ed8e96ba45d8","resolution":{"observed_at":"2026-05-10T23:26:25.758060Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-17T21:20:56.751435+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-17T21:20:56.751435+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/p19-1442","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi: 10.18653/v1/P19-1442","venue":null,"work_id":"9accf31e-8854-4edf-b20f-5886a1abb332","year":2014},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:8280131c4e0867f398a72cee45026e1d1ff5b674b8a59ea3f0c74ff6b536f60e","observation_id":"980c77ab-506c-44b2-a1d0-7ee1e55d1df4","resolution":{"observed_at":"2026-05-10T23:26:25.770353Z","resolver_source":"doi","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1080/02724980443000566","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URL https://doi.org/10.1080/02724980443000566","venue":"The Quarterly Journal of Experimental Psychology Section A","work_id":"78cdc968-ef44-4d2a-b94f-0174b7ac9d42","year":2015},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:cb150705d8950cd1d546e73058b5e720b1e9d9c1c4fa0b73d77d26a829ca7b5e","observation_id":"596f7243-5571-4f85-b020-89e74078c9ef","resolution":{"observed_at":"2026-05-10T23:26:25.474346Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2020.coling-main.518","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"32) Judea Pearl.Causality: Models, Reasoning, and Inference","venue":null,"work_id":"5756350e-6f6e-4b36-8539-a344d5c0f78f","year":2000},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:d33fb8f775ba92090874f7c3c8946be11115461ef7e11579f6fa76736bf8dd34","observation_id":"bf6af985-ea02-48ec-849b-ecfbb3a2c1f5","resolution":{"observed_at":"2026-05-10T23:26:25.785346Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"29) Tony A","venue":null,"work_id":"a05ebf30-d3c4-4d94-8619-d85d3a2b2c00","year":null},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:5b3a4ed4a6d6a503c73bf43fdec3510edb3c4f0004c846c4a3d8062d09b9b623","observation_id":"41bf6c56-66ad-4d39-af61-31d4c40ffc41","resolution":{"observed_at":"2026-05-10T23:26:25.881584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1016/b978-0-12-558701-3.50007-7","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"29) Robert Plutchik","venue":"Elsevier eBooks","work_id":"6b8e0e35-7311-493f-8b7f-ad7b0cc091b8","year":1980},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:fc5913860a937c12bee4eb2fdc921ffa84fb99dab4c80822b3ad78ab0ad69bde","observation_id":"51ff55af-49cb-4d4d-9d6e-1e4318f94bfa","resolution":{"observed_at":"2026-05-10T23:26:25.792521Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-030-99739-7_26","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"URLhttps://aclanthology.org/2020.lrec-1.125","venue":"Lecture notes in computer science","work_id":"01b5433b-bddd-4870-82cb-98788210491a","year":2020},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:28e986c0ecdcb40e85867f9766a26544403deaba17d587af697b8e9e2af8281c","observation_id":"245e1109-2da1-45d4-a2f6-03e8a52d39b9","resolution":{"observed_at":"2026-05-10T23:26:25.805094Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"7348.159741","doi":"10.5555/1597348.1597414","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"(cited on p","venue":null,"work_id":"326edddc-84c1-4059-ace6-36f40c1491fe","year":2010},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:4505655ae8333a2d8dba443bc7b6df18b6a992f037980f743bec6f99368386b6","observation_id":"39592300-ccce-438b-a875-15853f495b46","resolution":{"observed_at":"2026-05-10T23:26:25.814589Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"38) Zijian Wang and David Jurgens","venue":null,"work_id":"89c8403a-c0bc-442b-bd33-c0f5c46cd8ff","year":2018},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:b8e6de122143eac185bec74064570d441ea64d408a5990defdc3ab94a7ba1e6c","observation_id":"e4e5305e-3980-4d06-84c8-40c1e1b746b4","resolution":{"observed_at":"2026-05-10T23:26:25.872973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/d18-1004","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"assessing BERT’s syntactic abilities","venue":null,"work_id":"139725cf-aa26-4063-bbcd-7a225b560c83","year":2019},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:d064486c7727f692e692fce6f6ac90d27fa6a32f5a5c1b906f744cdc9cb085e4","observation_id":"3302fd33-ab6b-4d8c-993a-441d920dcd70","resolution":{"observed_at":"2026-05-10T23:26:25.825599Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2841.344198","doi":"10.1145/3412841.3441982","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":null,"work_id":"fb4783ad-7fb4-4d9a-b1fb-893160ddfa01","year":2019},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:e7147689c4399103128ce7425e6be73a3dedeafb0dec409983a134dd44742f4b","observation_id":"a492a40f-8a0a-4550-b874-08fb972b1b5a","resolution":{"observed_at":"2026-05-10T23:26:25.582688Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/d15-1284","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on p","venue":null,"work_id":"6dda3e98-842d-412a-ad5e-5c549c6fca51","year":2015},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:45998d809d655a1a0c975c859e30c339067bf65a494de49b54a4d54edda77415","observation_id":"bfec096c-fe87-4344-b1ab-ee0c9365a972","resolution":{"observed_at":"2026-05-10T23:26:25.587000Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/w19-4815","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"(cited on pp","venue":null,"work_id":"ef176a65-c769-42c9-aa8f-8b77e62a5453","year":2002},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:33cbeb83e4c9c114797c35597467b998661fefa5d4875ed1a7313e7a775cfca1","observation_id":"2993704c-b483-4fe5-83e6-579323448f3b","resolution":{"observed_at":"2026-05-10T23:26:25.597303Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2019.291405","doi":"10.1109/tpami.2019.2914054","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"31) Zhou Yu, Dejing Xu, Jun Yu, Ting Yu, Zhou Zhao, Yueting Zhuang, and Dacheng Tao","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","work_id":"1b45d7c3-c700-43e9-bef1-ec24fca554a6","year":1906},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:7f83ec8c57bd47a275f8a25af528881464b3a3e7120c9c9f21f6dab7a093fe5d","observation_id":"09903080-9f60-479b-ac94-9d2368280315","resolution":{"observed_at":"2026-05-10T23:26:25.604187Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/n18-2003","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","venue":null,"work_id":"debd34b6-f412-41f5-8776-18ca1afb906a","year":2018},"citing_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-10T23:26:25.323988Z"},"links":{"citing_paper":"/paper/2206.04615"},"observation_digest":"sha256:db5516d255f5ef936add737664b69b734f286dd14f28347591ef0660bf8f63b1","observation_id":"fbb6d9ce-4ec6-4ee7-830c-64a5eebb8847","resolution":{"observed_at":"2026-05-10T23:26:25.608574Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":11,"parse_uncertain":0,"unresolved":0,"verified_exact":35,"verified_fuzzy":3},"total_outbound_references":49},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 100 inbound Pith citation observations for arXiv:2206.04615."}