{"as_of":"2026-08-09T01:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:12718d6c76978cf63c49909550a3be1070cbf4aef230da6f4cc14756db4f6f62","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T18:32:14.852483Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T07:21:36.652240Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.10390","snapshot_observed_at":"2026-08-04T07:21:36.652240Z","title":"(how) can transformers predict pseudo-random numbers?, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.26792","last_updated":"2026-02-16T23:41:23Z","snapshot_observed_at":"2026-08-08T03:13:50.232248Z","submitted_at":"2025-10-30T17:59:09Z","title":"Learning Pseudorandom Numbers with Transformers: Permuted Congruential Generators, Curricula, and Interpretability","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T07:21:36.652240Z"},"links":{"cited_paper":"/paper/2502.10390","citing_paper":"/paper/2510.26792"},"observation_digest":"sha256:d6b9aec48cce04fadbc7dca208c38188451cc6b5ec3e1d1bef3f28b32668e684","observation_id":"62567c29-b328-4e11-a615-8c4e5c6987ed","resolution":{"observed_at":"2026-08-04T07:21:36.652240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.10390","snapshot_observed_at":"2026-07-12T00:51:41.905788Z","title":"Eric Todd, Jannik Brinkmann, Rohit Gandikota, and David Bau","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03660","last_updated":"2026-07-04T01:47:29Z","snapshot_observed_at":"2026-08-07T05:34:25.091820Z","submitted_at":"2026-07-04T01:47:29Z","title":"Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-12T00:51:41.905788Z"},"links":{"cited_paper":"/paper/2502.10390","citing_paper":"/paper/2607.03660"},"observation_digest":"sha256:1ef5665caeb3fe27989c8fa8bc192eb9ea91296a1671d0dce1fcfb17fb9bd36e","observation_id":"dbfce7a2-8d98-408f-a855-a15e256dff8f","resolution":{"observed_at":"2026-07-12T00:51:41.905788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.10390","snapshot_observed_at":"2026-08-04T04:32:10.439762Z","title":"(How) can Transformers predict pseudo-random numbers?","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02575","last_updated":"2026-08-03T17:50:54Z","snapshot_observed_at":"2026-08-08T18:51:08.529667Z","submitted_at":"2026-08-03T17:50:54Z","title":"Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T04:32:10.439762Z"},"links":{"cited_paper":"/paper/2502.10390","citing_paper":"/paper/2608.02575"},"observation_digest":"sha256:764c3d4dbcffa86a4387881a3551f34f16e493d85e88c460ce9354e39a8c6caf","observation_id":"6e592903-89c8-4ab0-b674-d613d732d2a3","resolution":{"observed_at":"2026-08-04T04:32:10.439762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.10390/citation-record","integrity":"/paper/2502.10390/integrity","json":"/paper/2502.10390/citation-record.json","paper":"/paper/2502.10390"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:16.290786Z","title":"Transformers learn to implement preconditioned gradient descent for in-context learning","venue":null,"work_id":"73d91402-945d-4e1a-83cb-edbf5da79ea2","year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.380312Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:2732bb9ec9cdd80de29bd000fb43b5a3454d9c803141a5ba857bd744c9e1ddb4","observation_id":"8fa7b530-c065-4ca0-a264-6e7dfc08dc1e","resolution":{"observed_at":"2026-08-07T18:32:16.296565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T18:32:16.259758Z","title":"What learning algorithm is in-context learning? investigations with linearmodels, 2023","venue":null,"work_id":"ef188401-5ee0-4b3c-b219-7a9ac95079b8","year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.403106Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:d84effe80cecc53916b714ec67dd710629aa14f2b4af2cceff5d7c721219177b","observation_id":"b08aa4bb-c2a6-4d75-9d4d-cb1962d76b72","resolution":{"observed_at":"2026-08-07T18:32:16.266724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13673","last_updated":"2025-05-19T11:12:27Z","snapshot_observed_at":"2026-08-08T23:24:12.994765Z","submitted_at":"2023-05-23T04:28:16Z","title":"Physics of Language Models: Part 1, Learning Hierarchical Language Structures","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13673","snapshot_observed_at":"2026-08-07T18:32:14.414281Z","title":"and Li, Y","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.414281Z"},"links":{"cited_paper":"/paper/2305.13673","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:f9520d8bcf5072c78a2089dcc990a286f0e68f16073f0e0fc232f69f1f832025","observation_id":"0c0f718b-a69d-49e4-98b5-eeb8c8ed6d15","resolution":{"observed_at":"2026-08-07T18:32:14.414281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:15.685031Z","title":null,"venue":null,"work_id":"478fc658-226f-40b8-8c04-58d2513a12cd","year":2021},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.472895Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:1ea979091d87991e2309d48ad8ef1986661935e9db8a05d3c5b572bfc6f0f8b3","observation_id":"31faa282-0468-441f-b64f-28570381dc55","resolution":{"observed_at":"2026-08-07T18:32:15.695347Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.00048","last_updated":"2024-10-29T16:35:25Z","snapshot_observed_at":"2026-08-06T01:50:45.829638Z","submitted_at":"2024-05-28T17:01:22Z","title":"Towards a theory of how the structure of language is acquired by deep neural networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.00048","snapshot_observed_at":"2026-08-07T18:32:14.480461Z","title":"and Wyart, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.480461Z"},"links":{"cited_paper":"/paper/2406.00048","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:6acd185e8371065e267897123ee75cd772051b24f7e26e3477ee0db585df3f80","observation_id":"6ccf4f19-16bc-483b-a777-17cc33e5f30a","resolution":{"observed_at":"2026-08-07T18:32:14.480461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:16.235802Z","title":"M., Favero, A., and Wyart, M","venue":null,"work_id":"6182d416-f152-47a6-888e-6eedab90b9d6","year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.518354Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:1e321943ca17d5320a0b21d70dae63df811c30322202a98a391d60279461b1c6","observation_id":"dd89f2d7-2e8e-4821-898c-ef7aee3b80bd","resolution":{"observed_at":"2026-08-07T18:32:16.242377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T18:32:16.214842Z","title":"and Zou, D","venue":null,"work_id":"d9cae8ae-2c0a-479f-9491-2294340d99c8","year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.526101Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:510ccff4f7308adcfc85a11dcbf4a0629c915380ef520f0f1192d7e03ad1d0ad","observation_id":"ab083dbe-98c7-4090-92e9-b823f962068e","resolution":{"observed_at":"2026-08-07T18:32:16.221968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.535338Z","title":"Three models for the description of language","venue":null,"work_id":null,"year":1956},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.535338Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:cbc590c6779f503f584a32bbd80f6bdd76edbb9a54eaf8595bf547fc6c1a73fe","observation_id":"10da8810-b13e-4943-b9af-a0dad811fc45","resolution":{"observed_at":"2026-08-07T18:32:14.535338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.02098","last_updated":"2023-02-28T13:22:17Z","snapshot_observed_at":"2026-08-08T23:24:14.529963Z","submitted_at":"2022-07-05T15:06:11Z","title":"Neural Networks and the Chomsky Hierarchy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.02098","snapshot_observed_at":"2026-08-07T18:32:14.589213Z","title":"K., Catt, E., Cundy, C., Hutter, M., Legg, S., Veness, J., and Ortega, P","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.589213Z"},"links":{"cited_paper":"/paper/2207.02098","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:7d2ee8376160af74f82b3cab73ec9f9284fdb96b052eb53e2d919f3895a70418","observation_id":"9a754838-2723-4bb3-ba5a-0c787cd333e3","resolution":{"observed_at":"2026-08-07T18:32:14.589213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:16.163541Z","title":"To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets","venue":null,"work_id":"68fbf449-c885-45bf-a631-3fd0646429c2","year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.596481Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:9881e2fced54d18568229ffc2fcadd2abe0c5a203226dd9b2a89206e4e923e0e","observation_id":"00b1d5fe-c5ac-4cf2-ad64-6a3785f6b19e","resolution":{"observed_at":"2026-08-07T18:32:16.174417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.03495","last_updated":"2024-06-05T17:59:35Z","snapshot_observed_at":"2026-08-08T20:54:05.936045Z","submitted_at":"2024-06-05T17:59:35Z","title":"Grokking Modular Polynomials","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.03495","snapshot_observed_at":"2026-08-07T18:32:14.645620Z","title":"Grokking modular polynomials, 2024 b","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.645620Z"},"links":{"cited_paper":"/paper/2406.03495","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:952d23fddb8f6944951691a275e071bb5f94dec0442e4f484f67a0730db0a05a","observation_id":"bfb1fbbb-74cd-44c4-82c7-91221e920893","resolution":{"observed_at":"2026-08-07T18:32:14.645620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.654526Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.654526Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:d4502db47846aea0fe754d08f2b8aa23b9a371bc4931305b8b6a263e96cbdebf","observation_id":"a93dfc9d-b0f1-422e-9dc1-ec46d1284383","resolution":{"observed_at":"2026-08-07T18:32:14.654526Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:15.394183Z","title":null,"venue":null,"work_id":"53be8dc9-8798-401f-b3c9-4420729c3833","year":1959},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.661220Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:a11c5f65fc8cdfeb3e747470952b83cd467d723a4d553710026982e795eb0a3f","observation_id":"f72934fd-d4d4-452c-8c36-58fdcba7f4e4","resolution":{"observed_at":"2026-08-07T18:32:15.400757Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.02679","last_updated":"2023-01-06T19:00:01Z","snapshot_observed_at":"2026-08-06T08:20:11.326697Z","submitted_at":"2023-01-06T19:00:01Z","title":"Grokking modular arithmetic","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.02679","snapshot_observed_at":"2026-08-07T18:32:14.671833Z","title":"Grokking modular arithmetic, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.671833Z"},"links":{"cited_paper":"/paper/2301.02679","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:02238e97b111b82ecb9482b1b08c7d2d531005f43d92f429de8c4dd901be4abe","observation_id":"48b5c80c-52dd-406b-8180-b9a55177fff7","resolution":{"observed_at":"2026-08-07T18:32:14.671833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.681010Z","title":"Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.681010Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:257696c920d3badbdd586994441db793c13c3c315ac4519261652669a2ce2938","observation_id":"1822ff14-55bc-41b8-a397-ffbe84e6c0f9","resolution":{"observed_at":"2026-08-07T18:32:14.681010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:16.093043Z","title":"In-context learning creates task vectors, 2023","venue":null,"work_id":"e8bd6533-eeed-43cc-abf5-29134afd1863","year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.689457Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:c787c86f3ec6744e20f1ed6751ddce90073d318805482f0f63f54e01b47ff6ec","observation_id":"e8d0d95e-bbcd-49c1-8a79-081a3da51867","resolution":{"observed_at":"2026-08-07T18:32:16.111394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.696177Z","title":null,"venue":null,"work_id":null,"year":1962},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.696177Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:a2db9d97951b6d5772dceea486f7dfedc3f1ac7073633c88232c79ee2b1d84c0","observation_id":"9ab6c1be-48f5-492a-b06f-db520107ef7b","resolution":{"observed_at":"2026-08-07T18:32:14.696177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:16.058339Z","title":null,"venue":null,"work_id":"7a46f098-850b-4f96-bb35-7ee9a7ded1e0","year":1997},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.705384Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:cefa7b2ab6282283735f5c898766acc03aa337a786b7ef035e59e3a09a53fd7a","observation_id":"7486adb9-2044-42d1-94cc-d9e7e2914307","resolution":{"observed_at":"2026-08-07T18:32:16.068709Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T18:32:16.033975Z","title":"Learning skillful medium-range global weather forecasting","venue":null,"work_id":"89c8ec8e-47a9-4bc1-be97-51bc1d637d22","year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.714631Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:c2cbd315c1f67158e4f177da0be7d769df02b3e2e24e1198f036a27e9c33638c","observation_id":"bd64d9d6-4b0a-4a44-9997-b1701959cb1b","resolution":{"observed_at":"2026-08-07T18:32:16.043493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T18:32:15.996965Z","title":"In-context vectors: Making in context learning more effective and controllable through latent space steering, 2024","venue":null,"work_id":"3e5b1c54-8b70-4edd-88f8-9208773d3a33","year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.721439Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:44aa17ed39611048b02a74d5a6e0987da5dfb0d0f7afaeec728a6f6329a061d6","observation_id":"d01014ae-51c7-42dd-89aa-9df057680e2f","resolution":{"observed_at":"2026-08-07T18:32:16.004468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.728002Z","title":"and Hutter, F","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.728002Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:efa1965c55705a3a7c146a3d6c809f7ecc2acac6c2d73d738077c69245ded2d2","observation_id":"523fc187-9b37-47f4-8d21-1d6e41c6999c","resolution":{"observed_at":"2026-08-07T18:32:14.728002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18266","last_updated":"2025-05-23T18:02:46Z","snapshot_observed_at":"2026-08-09T00:29:07.939367Z","submitted_at":"2025-05-23T18:02:46Z","title":"Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.18266","snapshot_observed_at":"2026-08-07T18:32:14.733852Z","title":"Uncovering a universal abstract algorithm for modular addition in neural networks, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.733852Z"},"links":{"cited_paper":"/paper/2505.18266","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:f9023c9e6980138562a12482a1fe12c62918ed3cf4da9877b464993f538ac8bf","observation_id":"f3e92fce-8555-4c51-b983-84e7284a6016","resolution":{"observed_at":"2026-08-07T18:32:14.733852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17399","last_updated":"2024-12-23T12:46:06Z","snapshot_observed_at":"2026-08-08T23:24:13.516450Z","submitted_at":"2024-05-27T17:49:18Z","title":"Transformers Can Do Arithmetic with the Right Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17399","snapshot_observed_at":"2026-08-07T18:32:14.746603Z","title":"R., Kailkhura, B., Bhatele, A., Geiping, J., Schwarzschild, A., and Goldstein, T","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.746603Z"},"links":{"cited_paper":"/paper/2405.17399","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:6ccedf897af28b6cc5dd86a52c0eea7aa392230e4b531594ea66aec9534cc87a","observation_id":"4e8c3e48-40d4-4698-9263-e8f5be05db7e","resolution":{"observed_at":"2026-08-07T18:32:14.746603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:15.943158Z","title":"Progress measures for grokking via mechanistic interpretability","venue":null,"work_id":"4e404256-021b-488b-abef-82ea6e7629ec","year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.755728Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:3a4434bad5e4ae930d4ae5f0b220b322a087e8b47853e4972f9bec65df5d2485","observation_id":"19047ed8-f375-424a-b3e6-7c20c929f15d","resolution":{"observed_at":"2026-08-07T18:32:15.960403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.11895","last_updated":"2022-09-24T00:43:19Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-09-24T00:43:19Z","title":"In-context Learning and Induction Heads","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.11895","snapshot_observed_at":"2026-08-07T18:32:14.762136Z","title":"In-context learning and induction heads","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.762136Z"},"links":{"cited_paper":"/paper/2209.11895","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:9431f99dec6ba3cde323fb95c2e98632a1da3a7cf38d106551fb869ca9a1bc02","observation_id":"adac80fb-2b1b-46a6-914e-4501f0693095","resolution":{"observed_at":"2026-08-07T18:32:14.762136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:15.925115Z","title":null,"venue":null,"work_id":"fcce1d46-0bdd-49d2-b49b-27d454b1f9cb","year":2014},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.771407Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:b02f525d1c024caab172ad2ac5a5eb063d9c1d352f26c81fec99f482dbfbf9b4","observation_id":"3bdfabd4-2eb9-45a4-af80-d908929da84a","resolution":{"observed_at":"2026-08-07T18:32:15.930370Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.02177","last_updated":"2022-01-06T18:43:37Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-01-06T18:43:37Z","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.02177","snapshot_observed_at":"2026-08-07T18:32:14.779920Z","title":"Grokking: Generalization beyond overfitting on small algorithmic datasets","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.779920Z"},"links":{"cited_paper":"/paper/2201.02177","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:6f8f7d8b03786862dd9ec2e69331d570d0a07e1c2236f70842b461f4612ea5bf","observation_id":"7c146c5c-bc2b-4634-87f1-96971df1eec3","resolution":{"observed_at":"2026-08-07T18:32:14.779920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:15.901917Z","title":"and Wolf, L","venue":null,"work_id":"376586fb-bca6-415b-ac1a-45bad9d5ea77","year":2017},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.787263Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:09658c9fea51b80acaafd4844ca8ce19a8542cba2a924768d9eeac99c547105a","observation_id":"ba629857-f26f-43fa-a198-e9d821d8a3b6","resolution":{"observed_at":"2026-08-07T18:32:15.909485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.793627Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.793627Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:6058ac934f9d92fcb58692799c35703dd55f312c47675c2c5b92fca1ac31022a","observation_id":"a51114b4-2131-428f-9ea0-1a2a066d491e","resolution":{"observed_at":"2026-08-07T18:32:14.793627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:15.858290Z","title":null,"venue":null,"work_id":"500c647c-f1dc-48c6-ac42-b5e807708194","year":1991},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.800319Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:812e1eeb6e8ae89db667c95e77c211f637c49ba41a78c3f4189da6f85d776fa7","observation_id":"4162ba25-dc60-44e5-bf91-dee5b7ab7307","resolution":{"observed_at":"2026-08-07T18:32:15.865259Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16496","last_updated":"2025-01-27T20:57:18Z","snapshot_observed_at":"2026-07-06T20:27:04.664873Z","submitted_at":"2025-01-27T20:57:18Z","title":"Open Problems in Mechanistic Interpretability","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16496","snapshot_observed_at":"2026-08-07T18:32:14.806991Z","title":"J., Casper, S., Tegmark, M., Saunders, W., Bau, D., Todd, E., Geiger, A., Geva, M., Hoogland, J., Murfet, D., and McGrath, T","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.806991Z"},"links":{"cited_paper":"/paper/2501.16496","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:a87fca3c4279b95a0c85e78521cbec334881b124a6e69d79d91cc7e7a3b56c19","observation_id":"c5ab5823-34e2-4239-b5eb-d2abb76398a7","resolution":{"observed_at":"2026-08-07T18:32:14.806991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.05304","last_updated":"2021-09-24T20:00:58Z","snapshot_observed_at":"2026-08-08T14:00:13.706840Z","submitted_at":"2020-01-15T13:23:36Z","title":"Computationally easy, spectrally good multipliers for congruential pseudorandom number generators","version":3},"cited_work":{"arxiv_id":"2001.05304","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.05304","snapshot_observed_at":"2026-08-07T18:32:14.941274Z","title":"Computationally easy, spectrally good multipliers for congruential pseudorandom number generators","venue":"cs.DS","work_id":"afa3dd04-0aab-4287-b889-40b776c64a44","year":2020},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.813500Z"},"links":{"cited_paper":"/paper/2001.05304","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:f761b74c31988ba29327cd56c7bd2000d5dea35c643b40419d07d2a117513e33","observation_id":"8eb4a528-746b-40d6-8ee4-37cd83f1de87","resolution":{"observed_at":"2026-08-07T18:32:14.954630Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.818842Z","title":"N., Kaiser, L., and Polosukhin, I","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.818842Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:eaf0338816358c50cd0f5265cecf10502d42e1754a512dda21b8bd630c6dafd2","observation_id":"592b534e-cd7e-4c50-96bb-a59575162518","resolution":{"observed_at":"2026-08-07T18:32:14.818842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:15.808607Z","title":"Transformers learn in-context by gradient descent, 2023","venue":null,"work_id":"75a638de-4d1a-48c2-bb48-7e10bcc913f5","year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.824465Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:ada33002010a889ade58ab5822e788d6bbe48a4c7999be1fc43e7f5a82da0992","observation_id":"7b2cf917-6ed1-43d0-9569-ae5991714c70","resolution":{"observed_at":"2026-08-07T18:32:15.815621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11903","last_updated":"2023-01-10T23:07:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11903","snapshot_observed_at":"2026-08-07T18:32:14.832037Z","title":"Chain-of-thought prompting elicits reasoning in large language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.832037Z"},"links":{"cited_paper":"/paper/2201.11903","citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:c42452f7feb1af90ee97a87f4f9268b082a2397f8a8c0c34d0510435f3ce3b15","observation_id":"113006aa-b3d3-4286-9e05-f794d5d8884e","resolution":{"observed_at":"2026-08-07T18:32:14.832037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:15.777487Z","title":"and Nanda, N","venue":null,"work_id":"0734e65a-7d6b-4add-9f0f-4b50fedbbc4f","year":2024},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.838828Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:9c3e5c0be62c67e2f1d5242531c209c8f34e9eaf778558cb65e52b6fb4e85141","observation_id":"1ee35d3a-eed5-4702-b084-e56ac422645c","resolution":{"observed_at":"2026-08-07T18:32:15.784181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T18:32:15.752400Z","title":"The clock and the pizza: Two stories in mechanistic explanation of neural networks","venue":null,"work_id":"7bbc7887-f6ce-4a8e-be4c-ecb4cb06c148","year":2023},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.845238Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:c3a2e7930d05c4e0dd13c56fb5fbb07c0e058c7acb6623a8b33b9309e6b39bae","observation_id":"0d31b312-807d-451c-b72b-94a34c2cf7eb","resolution":{"observed_at":"2026-08-07T18:32:15.758861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:32:14.852483Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T18:32:14.852483Z"},"links":{"citing_paper":"/paper/2502.10390"},"observation_digest":"sha256:853d573586d6a6d8b96b5a536f253d4dfe4be116ca02314370c12433c1ed80f5","observation_id":"6839b307-0cce-4770-ac25-614aceff560e","resolution":{"observed_at":"2026-08-07T18:32:14.852483Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.10390","last_updated":"2025-07-08T18:20:16Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T23:23:47.910559Z","submitted_at":"2025-02-14T18:59:40Z","title":"(How) Can Transformers Predict Pseudo-Random Numbers?"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":3,"verified_fuzzy":13},"total_outbound_references":38},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 3 inbound Pith citation observations for arXiv:2502.10390."}