{"as_of":"2026-08-09T03:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3e5548a3479e6f7d6ccb325160c4e61d064f597385f369c6e6d55beac8e32a4d","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":28,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T22:21:52.626878Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":35,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2405.15793","last_updated":"2024-11-11T20:01:15Z","snapshot_observed_at":"2026-07-06T18:19:29.996982Z","submitted_at":"2024-05-06T17:41:33Z","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-11T12:45:34.286368Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2405.15793"},"observation_digest":"sha256:31dcf6d1f0e27c55f25ae67f9f0e5b7991302908106f7679da05fe993911ff6c","observation_id":"6c2a71e8-a51f-4e81-bf34-285360f87fe4","resolution":{"observed_at":"2026-05-11T12:45:35.367808Z","resolver_source":"arxiv_id","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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2410.05229","last_updated":"2025-08-27T16:24:39Z","snapshot_observed_at":"2026-07-06T19:29:09.714725Z","submitted_at":"2024-10-07T17:36:37Z","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","version":2},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-05-15T00:42:11.891829Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2410.05229"},"observation_digest":"sha256:32d28263d6f227db3565b30dfb22095674860a9e672b108e2c8f7632e7a7014c","observation_id":"c0d3b194-9b40-42cf-8b55-2a109a09bf9e","resolution":{"observed_at":"2026-05-15T00:42:12.042691Z","resolver_source":"arxiv_id","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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-07T22:21:52.626878Z","title":"T., Yao, S., Friedman, D., Hardy, M., and Griffiths, T","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.09192","last_updated":"2025-05-27T17:24:38Z","snapshot_observed_at":"2026-08-08T23:01:32.478617Z","submitted_at":"2025-02-13T11:32:09Z","title":"Thinking beyond the anthropomorphic paradigm benefits LLM research","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T22:21:52.626878Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2502.09192"},"observation_digest":"sha256:bdcfbfaaee585b1335338cc8d6eb75a81e4776cd2e4f505697077c928f4f5d08","observation_id":"82a7728d-c64b-4e0f-b73e-d18dfa7cce69","resolution":{"observed_at":"2026-08-07T22:21:52.626878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-07T14:31:46.768635Z","title":"Embers of autoregression: Understanding large language models through the problem they are trained to solve,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18690","last_updated":"2025-05-24T13:32:03Z","snapshot_observed_at":"2026-08-07T14:25:30.423247Z","submitted_at":"2025-05-24T13:32:03Z","title":"Benchmarking and Rethinking Knowledge Editing for Large Language Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T14:31:46.768635Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2505.18690"},"observation_digest":"sha256:e2d053804c01b5083484c75b9a6654cf4a4769e3d38132709608f69edd616024","observation_id":"b9a8ba7a-7a57-4d54-89b2-c2bb637460d9","resolution":{"observed_at":"2026-08-07T14:31:46.768635Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-06T22:36:23.410934Z","title":"Thomas McCoy, Shunyu Yao, Dan Friedman, Matthew Hardy, and Thomas L","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21215","last_updated":"2025-06-26T13:11:01Z","snapshot_observed_at":"2026-08-08T20:05:02.707562Z","submitted_at":"2025-06-26T13:11:01Z","title":"Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T22:36:23.410934Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2506.21215"},"observation_digest":"sha256:f734e32f59509f0926f67869741da2c9ad218ab7b5460a7271d4a999f10cc840","observation_id":"82410dd6-9c7d-4113-bfaa-bd89f85eacd2","resolution":{"observed_at":"2026-08-06T22:36:23.410934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2507.03933","last_updated":"2026-04-23T08:40:57Z","snapshot_observed_at":"2026-08-02T13:23:23.079353Z","submitted_at":"2025-07-05T07:36:49Z","title":"Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMs","version":3},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-19T06:43:13.780123Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2507.03933"},"observation_digest":"sha256:a490a9b6b43e6c370063c3e29d7c4a0c293a21ed8a9e1136ba232e80849b35c5","observation_id":"31a102b7-4e87-4c4c-9295-f303e1f2bcf8","resolution":{"observed_at":"2026-05-19T06:47:07.237936Z","resolver_source":"arxiv_id","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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-06T18:03:14.956649Z","title":"Embers of autoregression: Understanding large language models through the problem they are trained to solve","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09440","last_updated":"2025-07-13T01:09:26Z","snapshot_observed_at":"2026-08-07T14:37:18.792328Z","submitted_at":"2025-07-13T01:09:26Z","title":"Transformers Don't In-Context Learn Least Squares Regression","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T18:03:14.956649Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2507.09440"},"observation_digest":"sha256:328c8c3e41ffabcf0671e43ae55f0cbb5fbd2c4ab3a3eb21cb33e0bb22aba78c","observation_id":"51c9e342-52d9-4a2a-8e7d-48d5f35d2ecc","resolution":{"observed_at":"2026-08-06T18:03:14.956649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-06T17:12:11.347497Z","title":"Thomas McCoy, Shunyu Yao, Dan Friedman, Matthew Hardy, and Thomas L","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.11423","last_updated":"2025-07-16T13:02:26Z","snapshot_observed_at":"2026-08-06T17:05:50.479233Z","submitted_at":"2025-07-15T15:47:47Z","title":"Reasoning Strategies in Large Language Models: Can They Follow, Prefer, and Optimize?","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T17:12:11.347497Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2507.11423"},"observation_digest":"sha256:9dda54193ce695f7f7816a652196c37780380a4db1e301725a560e489f967f71","observation_id":"3b356d2d-d71a-4936-b246-4607be5c5755","resolution":{"observed_at":"2026-08-06T17:12:11.347497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-06T16:50:49.265422Z","title":", Yao, S","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.12547","last_updated":"2025-07-18T06:48:39Z","snapshot_observed_at":"2026-08-06T20:03:59.194878Z","submitted_at":"2025-07-16T18:01:03Z","title":"Modeling Open-World Cognition as On-Demand Synthesis of Probabilistic Models","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-06T16:50:49.265422Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2507.12547"},"observation_digest":"sha256:246f57b551eadce1fa72ea47b1de0f91dccb3ee26356cfd0c78ef829c56ef97c","observation_id":"4d509bba-f692-4382-bef0-2b9effbbfdb1","resolution":{"observed_at":"2026-08-06T16:50:49.265422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"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":45,"source":"pdf_text","source_observed_at":"2026-05-19T02:12:48.586913Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2507.23009"},"observation_digest":"sha256:a8533a7d73fd0105281b644f387d612d8428c032bfceebda14d815e1c03694e8","observation_id":"258441ab-7d9b-49af-8e50-a1c207a64b6f","resolution":{"observed_at":"2026-05-19T02:12:55.698013Z","resolver_source":"arxiv_id","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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T17:28:41.999957Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16705","last_updated":"2025-08-22T11:14:36Z","snapshot_observed_at":"2026-08-05T17:28:34.961580Z","submitted_at":"2025-08-22T11:14:36Z","title":"Assessing Consciousness-Related Behaviors in Large Language Models Using the Maze Test","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T17:28:41.999957Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2508.16705"},"observation_digest":"sha256:1bf94502812ff990425da5c74645022cfedc071f92925ba0c282077faff00f92","observation_id":"b29fc0df-0378-4ed7-9310-c33a7ef201f9","resolution":{"observed_at":"2026-08-05T17:28:41.999957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T10:50:28.986221Z","title":"Embers of autoregression: Understanding large language models through the problem they are trained to solve","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":18,"source":"arxiv_source","source_observed_at":"2026-08-05T10:50:28.986221Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2509.03644"},"observation_digest":"sha256:3fd0cdad7a3f60b427d71f2663caea45ffa3efb58419ab47a5604384f13d8c76","observation_id":"ac61b992-31eb-42cb-8f07-9b25bab39f80","resolution":{"observed_at":"2026-08-05T10:50:28.986221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2510.01685","last_updated":"2026-05-08T16:56:36Z","snapshot_observed_at":"2026-07-06T22:31:30.171287Z","submitted_at":"2025-10-02T05:21:34Z","title":"How Do Language Models Compose Functions?","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-18T11:04:09.179536Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2510.01685"},"observation_digest":"sha256:1b880aa43b1e8cc66692ad8f6e471d31dcd740e5a8323e1d4998c39bfe9b8c7f","observation_id":"b3fe2c25-97f7-4ad1-85dd-c30545ef9abb","resolution":{"observed_at":"2026-05-18T11:06:17.651651Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2604.10990","last_updated":"2026-04-13T04:48:20Z","snapshot_observed_at":"2026-07-06T22:59:27.499664Z","submitted_at":"2026-04-13T04:48:20Z","title":"When Verification Fails: How Compositionally Infeasible Claims Escape Rejection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T16:35:20.040822Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2604.10990"},"observation_digest":"sha256:1349e5c19c5f788d1f363f4b1ebcc8e355fb89231032fff0fadd7a0d932ecfad","observation_id":"de87f7ae-b17f-4c8e-b5c7-f46700c0d710","resolution":{"observed_at":"2026-05-11T08:30:58.770152Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2604.17650","last_updated":"2026-04-19T22:45:10Z","snapshot_observed_at":"2026-07-06T23:04:41.564912Z","submitted_at":"2026-04-19T22:45:10Z","title":"Measuring Distribution Shift in User Prompts and Its Effects on LLM Performance","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-05-10T05:27:50.049798Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2604.17650"},"observation_digest":"sha256:745efa28eec5852e41ab4372c7335ff1f7b14723706c74fe76783b95344d87c0","observation_id":"947c7cc0-196f-4708-a8f1-8387d027c792","resolution":{"observed_at":"2026-05-10T06:56:47.943215Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2604.18907","last_updated":"2026-04-20T23:14:48Z","snapshot_observed_at":"2026-08-02T07:41:12.503888Z","submitted_at":"2026-04-20T23:14:48Z","title":"Gradient-Based Program Synthesis with Neurally Interpreted Languages","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-05-10T04:29:33.858344Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2604.18907"},"observation_digest":"sha256:bf6f01c5a95909086280a9199357b4d4a5810d4928d49e14df9c331986b27cd3","observation_id":"dc976031-228b-4769-96a8-b29cf482fbba","resolution":{"observed_at":"2026-05-11T11:56:09.255758Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2605.06882","last_updated":"2026-05-07T19:31:43Z","snapshot_observed_at":"2026-07-06T23:19:15.382283Z","submitted_at":"2026-05-07T19:31:43Z","title":"How Well Do LLMs Perform on the Simplest Long-Chain Reasoning Tasks: An Empirical Study on the Equivalence Class Problem","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-11T01:29:33.453354Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2605.06882"},"observation_digest":"sha256:c7c6301e78355e325d56977ae81c7bd1c608dfb9721a5ec065ac73267f28e215","observation_id":"e70fcc8a-dbd2-4f05-b2ca-e38f1f1a54a4","resolution":{"observed_at":"2026-05-11T01:45:51.993772Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2605.07622","last_updated":"2026-05-08T11:48:22Z","snapshot_observed_at":"2026-08-02T05:48:50.765177Z","submitted_at":"2026-05-08T11:48:22Z","title":"Is She Even Relevant? When BERT Ignores Explicit Gender Cues","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-05-11T02:13:26.019184Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2605.07622"},"observation_digest":"sha256:dc31269ab0b2a50a39660ab79ab5e770fa92ee9217b196a0085f88828184810d","observation_id":"2acf4377-0d7f-42fc-931e-74d32a2ecbd3","resolution":{"observed_at":"2026-05-11T03:50:55.449012Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2605.11388","last_updated":"2026-05-12T01:21:37Z","snapshot_observed_at":"2026-07-06T23:23:16.461539Z","submitted_at":"2026-05-12T01:21:37Z","title":"Deep Reasoning in General Purpose Agents via Structured Meta-Cognition","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-05-13T02:47:10.398564Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2605.11388"},"observation_digest":"sha256:5be18ce44b041e7cb8b3ce8c2a2a674df2b481ef8b00d1878a2ecbca40b8ba8a","observation_id":"6c5f7b40-fa2d-4e16-9b66-0e7e849cee6b","resolution":{"observed_at":"2026-05-13T02:52:08.678449Z","resolver_source":"arxiv_id","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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2605.21683","last_updated":"2026-05-20T19:41:35Z","snapshot_observed_at":"2026-08-02T18:04:57.194626Z","submitted_at":"2026-05-20T19:41:35Z","title":"Investigating Concept Alignment Using Implausible Category Members","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-22T09:11:40.345156Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2605.21683"},"observation_digest":"sha256:2c92934e02d97793cf27a54eeef4016f1d9fa776319ed0db6bfca762402e0242","observation_id":"785d8acd-f290-4b37-babb-04535f49d2b4","resolution":{"observed_at":"2026-05-22T09:14:45.623827Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2605.23032","last_updated":"2026-05-21T20:56:51Z","snapshot_observed_at":"2026-08-01T19:43:25.185364Z","submitted_at":"2026-05-21T20:56:51Z","title":"Brain-LLM Alignment Tracks Training Data, Not Typology","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-05-25T05:40:32.571841Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2605.23032"},"observation_digest":"sha256:a41e199479dedf3994bb15dcd27aca8e6b29b64dfabfff4ffcab16efef8a35de","observation_id":"a3cabf13-e2b2-4265-a4c8-6bcfdcc13468","resolution":{"observed_at":"2026-05-25T05:45:23.017738Z","resolver_source":"arxiv_id","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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2605.29655","last_updated":"2026-07-07T02:54:21Z","snapshot_observed_at":"2026-07-12T15:43:46.526865Z","submitted_at":"2026-05-28T09:17:11Z","title":"SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-29T08:52:09.461853Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2605.29655"},"observation_digest":"sha256:91dadfe14640973c24c8628fadca30879d3e4210fa93bc456c93e42fc156f00c","observation_id":"580e03a0-ccf0-4e8f-934b-9be3c200f5d0","resolution":{"observed_at":"2026-06-29T08:53:15.649920Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2606.00570","last_updated":"2026-05-30T06:44:40Z","snapshot_observed_at":"2026-08-03T04:12:33.083328Z","submitted_at":"2026-05-30T06:44:40Z","title":"Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-06-28T19:03:00.055800Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2606.00570"},"observation_digest":"sha256:af94f4e78f56970f151b1e79a660e96464e265cfb5c953ac090a73ac12335252","observation_id":"f27f6629-3f00-4d02-83fa-6fdff3123352","resolution":{"observed_at":"2026-06-28T19:32:35.403391Z","resolver_source":"arxiv_id","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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2606.02211","last_updated":"2026-06-01T13:10:49Z","snapshot_observed_at":"2026-08-02T18:41:16.377453Z","submitted_at":"2026-06-01T13:10:49Z","title":"Consistency Training while Mitigating Obfuscation via Rate Matching","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-06-28T14:25:43.147442Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2606.02211"},"observation_digest":"sha256:5d40c042964faa1f70fc1570a9662859f98f7d54ade03fd6206a02eb390a12a0","observation_id":"579d769b-c004-4936-938a-cf55ac190bf6","resolution":{"observed_at":"2026-06-28T14:32:18.142375Z","resolver_source":"arxiv_id","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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2606.09395","last_updated":"2026-06-08T12:13:58Z","snapshot_observed_at":"2026-08-08T01:24:45.858849Z","submitted_at":"2026-06-08T12:13:58Z","title":"Empirical Study for Structured Output Control in LLMs for Software Engineering","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-27T15:42:28.064820Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2606.09395"},"observation_digest":"sha256:ea924707963c7fee362fe36018ab4bdda6f2a2b790a5e5f0161f5b09228b1332","observation_id":"87def45e-f137-4ad6-826a-da0afb83e0f7","resolution":{"observed_at":"2026-07-03T02:47:37.524525Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2606.09856","last_updated":"2026-05-26T15:40:02Z","snapshot_observed_at":"2026-08-07T23:31:21.950731Z","submitted_at":"2026-05-26T15:40:02Z","title":"Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-29T18:43:53.771836Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2606.09856"},"observation_digest":"sha256:a896a3877813881f399b293e07b0300ae6f58e4f69dfd33d1ce5c0de1a6f4d81","observation_id":"0059e049-6af2-4e99-a592-67c177993321","resolution":{"observed_at":"2026-06-29T18:53:51.912792Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":"2309.13638","doi":"10.48550/arxiv.2309.13638","metadata_source":"arxiv_reference","pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Thomas McCoy and Shunyu Yao and Dan Friedman and Matthew Hardy and Thomas L","venue":"arXiv (Cornell University)","work_id":"49d85091-4f72-41bd-a6be-3d6c4f46e861","year":2023},"citing_paper":{"arxiv_id":"2606.13607","last_updated":"2026-06-11T17:23:10Z","snapshot_observed_at":"2026-08-08T15:21:19.738713Z","submitted_at":"2026-06-11T17:23:10Z","title":"Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T06:44:31.919126Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2606.13607"},"observation_digest":"sha256:6d8a029d0c4c9599bee78ec2102c17cad05a3710ad74bf1a8b26a934ae73a1d3","observation_id":"762acea0-c741-4cdb-9c08-67514e58de16","resolution":{"observed_at":"2026-07-03T15:08:32.713343Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":"2026-05-25T16:25:56.819294+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T16:25:56.819294+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13638","snapshot_observed_at":"2026-08-01T15:26:58.293344Z","title":"arXiv preprint arXiv:2309.13638 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18443","last_updated":"2026-07-20T18:51:46Z","snapshot_observed_at":"2026-08-07T21:48:17.505747Z","submitted_at":"2026-07-20T18:51:46Z","title":"Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-01T15:26:58.293344Z"},"links":{"cited_paper":"/paper/2309.13638","citing_paper":"/paper/2607.18443"},"observation_digest":"sha256:e9e37ff779cbd3fefe6399a49e5ce6182f39043e9e5158d9ff5fafa5a4b68c9c","observation_id":"725cebcd-b851-4ec2-9c94-9cdd7fd0ec2c","resolution":{"observed_at":"2026-08-01T15:26:58.293344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.13638/citation-record","integrity":"/paper/2309.13638/integrity","json":"/paper/2309.13638/citation-record.json","paper":"/paper/2309.13638"},"outbound":[],"paper":{"arxiv_id":"2309.13638","last_updated":"2023-09-24T13:35:28Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T16:22:58.752949Z","submitted_at":"2023-09-24T13:35:28Z","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 28 inbound Pith citation observations for arXiv:2309.13638."}