{"as_of":"2026-08-12T09:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c34120952ca071c78e9ce7ce8407aa1de34b5facd35956b6e194a6af9823d7cc","coverage":[{"denominator":71,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":71,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:33:43.583162Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:37:03.120800Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T18:16:08.441338Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.05200","snapshot_observed_at":"2026-08-06T16:37:03.120800Z","title":"Transformers meet in-context learning: A universal approximation theory","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.13540","last_updated":"2025-07-30T01:51:41Z","snapshot_observed_at":"2026-08-09T06:21:45.685935Z","submitted_at":"2025-07-17T21:19:32Z","title":"Provable Low-Frequency Bias of In-Context Learning of Representations","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.120800Z"},"links":{"cited_paper":"/paper/2506.05200","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:14c4b4c755cd18319b665f8fdfd3f166e3a264300fb17bfee0737bf86591439a","observation_id":"60e3553d-05d9-4500-b701-c28612b2ca6c","resolution":{"observed_at":"2026-08-06T16:37:03.120800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.05200","snapshot_observed_at":"2026-08-04T13:15:25.792645Z","title":"Transformers meet in-context learning: A universal approximation theory.arXiv preprint arXiv: 2506.05200, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.01163","last_updated":"2026-06-24T11:54:33Z","snapshot_observed_at":"2026-08-10T04:34:00.898338Z","submitted_at":"2025-10-01T17:52:29Z","title":"How Does the Pretraining Distribution Shape In-Context Learning? A Fundamental Trade-Off","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-04T13:15:25.792645Z"},"links":{"cited_paper":"/paper/2506.05200","citing_paper":"/paper/2510.01163"},"observation_digest":"sha256:cfc4a1da217359ab73214f8a1bdc8baa7492a918103ccd94ab54e0a3ba13df49","observation_id":"4dc62d54-8731-4f56-9dc1-fb9f73ec4ef6","resolution":{"observed_at":"2026-08-04T13:15:25.792645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"cited_work":{"arxiv_id":"2506.05200","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.05200","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Transformers meet in- context learning: A universal approximation theory","venue":null,"work_id":"e83fcf55-70df-4dd0-88f8-e7c30f8621f8","year":2025},"citing_paper":{"arxiv_id":"2605.04995","last_updated":"2026-05-06T14:53:55Z","snapshot_observed_at":"2026-08-11T13:31:05.753478Z","submitted_at":"2026-05-06T14:53:55Z","title":"Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-08T17:00:37.250246Z"},"links":{"cited_paper":"/paper/2506.05200","citing_paper":"/paper/2605.04995"},"observation_digest":"sha256:b0a824f79d3c75b7bc80891e75ae9b90e23e946491e8b5234b28b68e1d7167a4","observation_id":"677bea9f-f6cd-4ea4-a160-4711237c95a3","resolution":{"observed_at":"2026-05-11T17:51:09.317230Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"cited_work":{"arxiv_id":"2506.05200","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.05200","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Transformers meet in- context learning: A universal approximation theory","venue":null,"work_id":"e83fcf55-70df-4dd0-88f8-e7c30f8621f8","year":2025},"citing_paper":{"arxiv_id":"2605.05176","last_updated":"2026-05-06T17:42:07Z","snapshot_observed_at":"2026-07-06T23:17:48.161262Z","submitted_at":"2026-05-06T17:42:07Z","title":"Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-08T16:26:09.066390Z"},"links":{"cited_paper":"/paper/2506.05200","citing_paper":"/paper/2605.05176"},"observation_digest":"sha256:2c028bd913789fc4ee3be5519180d5b6b1970342d85908595c1ff32d0e8616a9","observation_id":"5c8533d3-a68a-4ac5-ab57-f636746f132f","resolution":{"observed_at":"2026-05-11T18:16:08.453627Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.05200/citation-record","integrity":"/paper/2506.05200/integrity","json":"/paper/2506.05200/citation-record.json","paper":"/paper/2506.05200"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:33:55.756657Z","title":null,"venue":null,"work_id":"d542b2d3-2c58-4a0f-8172-2bb46da7077c","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:34.180087Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:9cc79664c3893ddb2a5fcb002f08716fa5c18b73b8469fd940aa3a5c832764ef","observation_id":"d5756bde-b5fa-41e3-923b-f958f71adb11","resolution":{"observed_at":"2026-08-07T10:33:55.944380Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04891","last_updated":"2024-04-14T05:12:52Z","snapshot_observed_at":"2026-08-07T21:36:08.711693Z","submitted_at":"2023-06-08T02:38:23Z","title":"In-Context Learning through the Bayesian Prism","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.04891","snapshot_observed_at":"2026-08-07T10:33:34.302322Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:34.302322Z"},"links":{"cited_paper":"/paper/2306.04891","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:51093209812990808f0675cb18e4511cc702d0ade71d99b25afb5713b82d7153","observation_id":"c4791222-49d1-4918-ad9a-c40cd690b27e","resolution":{"observed_at":"2026-08-07T10:33:34.302322Z","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":"2026-08-07T10:33:55.388397Z","title":null,"venue":null,"work_id":"c4e5e57c-6f49-4f79-a8ea-562088a9824d","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:34.447216Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:d091265b164473f3b00dc5f3da695aa0ee12a449ed49635710d8c6b6d1bc8ef6","observation_id":"ebfa6d0d-c284-4f6f-86ad-0ac0999ddef6","resolution":{"observed_at":"2026-08-07T10:33:55.567359Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:55.028621Z","title":null,"venue":null,"work_id":"b6b3638a-cd98-44ba-85ac-870c8b7b01ff","year":2017},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:34.595051Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:37b332ef7adc933eba51ec87673a4d2aebcb4261a8318e63f2c8a8848963279c","observation_id":"af3cad9a-9c2d-40aa-b2bc-4a6ca7a155d5","resolution":{"observed_at":"2026-08-07T10:33:55.220218Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:54.737620Z","title":null,"venue":null,"work_id":"9a24bcbf-38e3-486f-b379-85ebdf792fc1","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:34.707482Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:d56f31baaf0faefba87a54e2e07bea183178240e600fd377a016b851296b55e7","observation_id":"12df6de3-32cb-4a94-9ee2-47bda072fa46","resolution":{"observed_at":"2026-08-07T10:33:54.851744Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:54.450911Z","title":null,"venue":null,"work_id":"520419dd-11fd-4c36-b42a-aad4032dab83","year":1993},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:34.837620Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:ca748a7e64743be22e2b079569bbdcafa4a084cde411ec9a24a5327b632e1e46","observation_id":"0bb54b47-709b-4200-869a-aea5a84c1e58","resolution":{"observed_at":"2026-08-07T10:33:54.622669Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:54.136401Z","title":null,"venue":null,"work_id":"43554d5b-0a63-4928-aaf2-a7559dca6027","year":2017},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:34.955168Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:2051d6fd6402c2aed8131325fa1a4499e34bdcc88670b2fb8a9dbe76e5700c81","observation_id":"b92b35dc-2b55-4b64-9e9e-bc291d271082","resolution":{"observed_at":"2026-08-07T10:33:54.280877Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-07T10:33:35.074730Z","title":"A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:35.074730Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:b271df7cfa7fec924dc0ba7edc6bb167004733a609b0debe703232804d104c7a","observation_id":"c0315443-97c5-488d-aa61-9eb901f822c2","resolution":{"observed_at":"2026-08-07T10:33:35.074730Z","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":"2026-08-07T10:33:35.152774Z","title":"D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:35.152774Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:d18b750820edd2460ca3619c643d5059ee35ab04b5104c9ab11f8b0e36d88845","observation_id":"810f3f2f-3b94-44a1-9b0f-e49281788331","resolution":{"observed_at":"2026-08-07T10:33:35.152774Z","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":"2026-08-07T10:33:53.786439Z","title":null,"venue":null,"work_id":"bdaf2bfc-275f-4a62-bd8f-f4c02e59823c","year":2006},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:35.304273Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:01cabb0b6794e482dfc6cd2355b3e23d9872e0b75fa97a39a083b6fe51aaabb0","observation_id":"388e0509-e66b-4298-9249-2133d8f3c0a7","resolution":{"observed_at":"2026-08-07T10:33:53.949454Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.02975","last_updated":"2024-12-04T02:37:31Z","snapshot_observed_at":"2026-08-12T01:18:31.774514Z","submitted_at":"2024-12-04T02:37:31Z","title":"Theoretical limitations of multi-layer Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.02975","snapshot_observed_at":"2026-08-07T10:33:35.409540Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:35.409540Z"},"links":{"cited_paper":"/paper/2412.02975","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:018ea8324cdb1f1edb23da8a22d369f6e3009e96b4925b4d3e3b3b077c75a858","observation_id":"0892a673-8ad9-4bb9-8ba8-6a3aa63cfb42","resolution":{"observed_at":"2026-08-07T10:33:35.409540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04084","last_updated":"2024-02-06T15:39:09Z","snapshot_observed_at":"2026-07-06T17:26:19.028623Z","submitted_at":"2024-02-06T15:39:09Z","title":"Provably learning a multi-head attention layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04084","snapshot_observed_at":"2026-08-07T10:33:35.509713Z","title":"and Li, Y","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:35.509713Z"},"links":{"cited_paper":"/paper/2402.04084","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:f8deeb7920d16483879b0e660d7c66812c0e59e2e67c8e5e217b95d8f4dd627d","observation_id":"f5fee61a-8b01-4b22-9bcd-6d619cbfed03","resolution":{"observed_at":"2026-08-07T10:33:35.509713Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19442","last_updated":"2024-06-10T17:18:07Z","snapshot_observed_at":"2026-08-10T19:14:52.602904Z","submitted_at":"2024-02-29T18:43:52Z","title":"Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19442","snapshot_observed_at":"2026-08-07T10:33:35.674370Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:35.674370Z"},"links":{"cited_paper":"/paper/2402.19442","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:3190e8301c5ea6fe4ec7786891cb255a5c5ef5f5209c3a534818deb2107feeef","observation_id":"b0a96b15-0d08-4d63-bc77-d4a28a323726","resolution":{"observed_at":"2026-08-07T10:33:35.674370Z","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":"2026-08-07T10:33:53.516217Z","title":null,"venue":null,"work_id":"dc808336-af64-4fd3-81fb-0413e94678b2","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:35.789564Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:5485ea933235be81a4084829c2ac439529bbafb4d98a77bc015f0299aa2b1992","observation_id":"86675c9d-18a2-4f7f-9195-e5c0ca1478c3","resolution":{"observed_at":"2026-08-07T10:33:53.644940Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12293","last_updated":"2025-05-23T23:35:35Z","snapshot_observed_at":"2026-08-12T01:22:51.208515Z","submitted_at":"2024-09-18T19:59:50Z","title":"In-Context Learning of Linear Systems: Generalization Theory and Applications to Operator Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12293","snapshot_observed_at":"2026-08-07T10:33:35.954386Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:35.954386Z"},"links":{"cited_paper":"/paper/2409.12293","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:afbc51e04224cb13f639e175c1b92747c6c88f55a4ff7e0b982e80b47365e11d","observation_id":"79c13986-8394-4593-9150-bf46538b97e0","resolution":{"observed_at":"2026-08-07T10:33:35.954386Z","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":"2502.08136","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:33:44.675198Z","title":null,"venue":null,"work_id":"3b56dfaa-cb6c-4f25-8d44-8caa41c1ddb2","year":2025},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:36.094742Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:d684d9d57f5d289316c76ed7a949aed1856a39ae5fc3c38a8d7332c195c051d4","observation_id":"b3a12ade-1d1c-4bba-88ea-c2f473cbaf23","resolution":{"observed_at":"2026-08-07T10:33:44.797083Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10559","last_updated":"2023-05-15T11:45:12Z","snapshot_observed_at":"2026-08-09T08:03:27.441735Z","submitted_at":"2022-12-20T18:58:48Z","title":"Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.10559","snapshot_observed_at":"2026-08-07T10:33:36.244991Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:36.244991Z"},"links":{"cited_paper":"/paper/2212.10559","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:adb5cb804edcfe2daea11c18bf70d14d9a5c4f8032a6b324cf052ad6084345c0","observation_id":"f530a241-cb5d-45f9-98f0-db8dbcbee486","resolution":{"observed_at":"2026-08-07T10:33:36.244991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00234","last_updated":"2024-10-05T11:47:02Z","snapshot_observed_at":"2026-07-06T14:36:25.690733Z","submitted_at":"2022-12-31T15:57:09Z","title":"A Survey on In-context Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00234","snapshot_observed_at":"2026-08-07T10:33:36.403271Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:36.403271Z"},"links":{"cited_paper":"/paper/2301.00234","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:8086644e7a9d8052d60d1060371ab964897523087541a7f21809e635a988812f","observation_id":"163f0a49-dd20-418e-8ed8-3f02dcd64ef9","resolution":{"observed_at":"2026-08-07T10:33:36.403271Z","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":"2026-08-07T10:33:53.286719Z","title":null,"venue":null,"work_id":"8cd2f426-8210-4af3-afc4-1e11204abaea","year":2022},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:36.562978Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:6c76cabfd95920f0b48e215c0905bcdbbe4820851333ead4bf45773fa864b12b","observation_id":"0b99c245-123c-410f-8583-561c978693a2","resolution":{"observed_at":"2026-08-07T10:33:53.386425Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:36.704294Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:36.704294Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:dab0b07349a4abc790abdd10e63b259ea5f126185d3e459c66ddda0cdede7b1f","observation_id":"cd031c9f-c9f9-4cef-9652-b76ba5e6d44d","resolution":{"observed_at":"2026-08-07T10:33:36.704294Z","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":"2026-08-07T10:33:53.013617Z","title":null,"venue":null,"work_id":"8a5d4590-7e13-41b6-ae11-ac3c8d8ec482","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:36.821897Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:051159c6b0cfd66e9a3a4e8c01cca9eafb695684804e9ab67e624f4de0334d63","observation_id":"ad76bd12-c546-4046-97a8-e7596f8435bb","resolution":{"observed_at":"2026-08-07T10:33:53.151577Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:52.741936Z","title":null,"venue":null,"work_id":"d7d3c487-b126-46e1-aa27-bf79dc16ca0c","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:36.947267Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:faac8e15d50531ceb5ee8b8d1c471950fa7ddadcde1a84aad58de699bfe4c6d5","observation_id":"ea8b35f6-b77f-4c72-b656-4e69559601b0","resolution":{"observed_at":"2026-08-07T10:33:52.867772Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.01367","last_updated":"2024-10-03T02:43:59Z","snapshot_observed_at":"2026-08-12T07:03:39.761856Z","submitted_at":"2024-08-02T16:21:48Z","title":"Transformers are Universal In-context Learners","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.01367","snapshot_observed_at":"2026-08-07T10:33:37.065976Z","title":"V., and Peyr \\'e , G","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:37.065976Z"},"links":{"cited_paper":"/paper/2408.01367","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:69e8e13a1f2e4d33307094463cf6882b0d1133bc5a4e115f76e8be7d996804c5","observation_id":"a86f70b7-d493-4a70-b8e7-08bfe6638851","resolution":{"observed_at":"2026-08-07T10:33:37.065976Z","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":"2026-08-07T10:33:52.449897Z","title":"S., and Valiant, G","venue":null,"work_id":"64588e84-7d37-44c6-a932-a531dbd33ba5","year":2022},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:37.238907Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:6c53f9ca8d619fabb3a5381a0a100eefcb334bf7002817fbbe9b6401b6790adc","observation_id":"e1778cd7-776d-44a2-b4f6-d6ce20544564","resolution":{"observed_at":"2026-08-07T10:33:52.606815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:52.172045Z","title":"D., and Papailiopoulos, D","venue":null,"work_id":"e892ca86-3367-4751-a9ce-134898242cd1","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:37.351733Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:0e037745a4bdfb927f561791654a9917c992e2f38ba36b7640412b5092a3ea17","observation_id":"d2b57ba7-1169-4bde-b63c-29214f0db64b","resolution":{"observed_at":"2026-08-07T10:33:52.296118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03183","last_updated":"2024-03-05T18:20:10Z","snapshot_observed_at":"2026-08-10T11:23:02.731910Z","submitted_at":"2024-03-05T18:20:10Z","title":"How Well Can Transformers Emulate In-context Newton's Method?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03183","snapshot_observed_at":"2026-08-07T10:33:37.489293Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:37.489293Z"},"links":{"cited_paper":"/paper/2403.03183","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:c11b1cf0ab9f3d62fa19c1390b8a4c5d3fd2759df708a59526c5db809da18f01","observation_id":"d9332bc3-54f7-44cc-b35e-e8692ef160ff","resolution":{"observed_at":"2026-08-07T10:33:37.489293Z","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":"2026-08-07T10:33:51.890514Z","title":null,"venue":null,"work_id":"e175e5d4-cacb-4cad-86d4-d3bedce2a60b","year":2020},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:37.599655Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:3ce344392f25e52adc8a2d4f6d3cc5a8eb42294a3ab47ca1c16c374016c52dad","observation_id":"4665ec28-6813-49e7-b963-e872f47c8b53","resolution":{"observed_at":"2026-08-07T10:33:52.062255Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:51.593486Z","title":null,"venue":null,"work_id":"99c3bc96-8b0f-4faa-855b-390fac455802","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:37.726321Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:af8684e6dd779c7c21db566f033d4e0c676bfd7aae57660f0e3c602e2ad01258","observation_id":"338501c5-07b0-4f2c-bb91-6733092aa031","resolution":{"observed_at":"2026-08-07T10:33:51.745107Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:51.283170Z","title":null,"venue":null,"work_id":"511ee13c-d3a9-49e7-a34c-ff7d433b422b","year":2020},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:37.870076Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:9748dbaab9b196ea9f2556a19c8a9c005b0fab209e2d409d87309907c62d4a4c","observation_id":"e22aa380-d783-4701-a7f7-717470198891","resolution":{"observed_at":"2026-08-07T10:33:51.413886Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.07971","last_updated":"2023-03-14T15:24:05Z","snapshot_observed_at":"2026-08-11T15:58:14.964764Z","submitted_at":"2023-03-14T15:24:05Z","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.07971","snapshot_observed_at":"2026-08-07T10:33:37.994781Z","title":"and Goyal, N","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:37.994781Z"},"links":{"cited_paper":"/paper/2303.07971","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:b591cd5f6a70f406a6adab934031f083255e863a1f54e0f78c2da14c70380861","observation_id":"9f785aa8-d926-4dc7-9d86-a4c56edf096d","resolution":{"observed_at":"2026-08-07T10:33:37.994781Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16819","last_updated":"2024-05-27T04:33:53Z","snapshot_observed_at":"2026-08-09T01:59:39.479624Z","submitted_at":"2024-05-27T04:33:53Z","title":"Automatic Domain Adaptation by Transformers in In-Context Learning","version":1},"cited_work":{"arxiv_id":"2405.16819","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.16819","snapshot_observed_at":"2026-08-07T10:33:44.286039Z","title":"Automatic Domain Adaptation by Transformers in In-Context Learning","venue":"cs.LG","work_id":"973993c0-f009-4945-aad9-4e63f632048a","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:38.128253Z"},"links":{"cited_paper":"/paper/2405.16819","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:d99a5b4986595f8a97ef780f32933be5d0705561d07de61e97a5f9466af494d1","observation_id":"08161a87-f218-409a-a649-f563e632a8d6","resolution":{"observed_at":"2026-08-07T10:33:44.435927Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:50.982397Z","title":null,"venue":null,"work_id":"7c4fb31e-37d5-4ef7-ba42-d0b4f4159f60","year":1994},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:38.252636Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:889e31d87629ac49188766503018ec050fb0fdbdbf807079d425c17d891e4a28","observation_id":"aa480a26-5864-4d8e-abc9-50a299814699","resolution":{"observed_at":"2026-08-07T10:33:51.138803Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:50.724742Z","title":null,"venue":null,"work_id":"cc92ec63-addd-413a-a041-e025c1f33d7d","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:38.431130Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:f3743ded60188c3c2641b3bf7b26c4ed608086311423a875941caca840f5cdb1","observation_id":"ebcf0c52-8b4a-4d04-add6-475b4b27a292","resolution":{"observed_at":"2026-08-07T10:33:50.836283Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:50.464087Z","title":null,"venue":null,"work_id":"125f7205-bf1f-4872-b060-a18a52a50c2b","year":2025},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:38.578076Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:a158ccb9f39eb921596dc3ff275b8883e0a2652fed106a1740a6e30c6bb25163","observation_id":"afc9ab70-f704-4574-893f-1d734d7f1da5","resolution":{"observed_at":"2026-08-07T10:33:50.597738Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01032","last_updated":"2024-06-03T22:22:15Z","snapshot_observed_at":"2026-08-09T22:32:41.851014Z","submitted_at":"2024-02-01T21:44:11Z","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01032","snapshot_observed_at":"2026-08-07T10:33:38.690738Z","title":"M., and Malach, E","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:38.690738Z"},"links":{"cited_paper":"/paper/2402.01032","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:2b5112267fe9aff59772bf8c5b312bb89aa64d22b0985291d9c7092a4e7afad9","observation_id":"ac4be71b-5e71-480c-9044-2122935aa254","resolution":{"observed_at":"2026-08-07T10:33:38.690738Z","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":"2026-08-07T10:33:50.167215Z","title":null,"venue":null,"work_id":"1ed1f6a5-3d87-4e01-becb-92bbe5c0dbe2","year":2020},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:38.858579Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:68dd7dfea9800976f40deb4962db80f10461a10bbb0c8216eea08adfa7d047d0","observation_id":"915a7441-5b09-4ff3-a674-0db4f5005793","resolution":{"observed_at":"2026-08-07T10:33:50.288635Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:49.878175Z","title":"and Nemirovski, A","venue":null,"work_id":"82816e94-f125-4953-ae34-646143c8d2c4","year":2000},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:38.997352Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:6d4872d43db85595399adf7f6f48cabb0dc2a0f306d88a20f43c813048a4251a","observation_id":"1aebd610-238e-463b-84a4-83249de8afed","resolution":{"observed_at":"2026-08-07T10:33:50.033459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:49.623433Z","title":"W., Khan, F","venue":null,"work_id":"bd7a0e23-f682-4b2a-ad59-7b66ffdada97","year":2022},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:39.158834Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:4fbc965ff8e13b12bea7c858175c3ea69c4dae8401c266aa43d01599920f7d0c","observation_id":"bfa7db19-7f14-458d-a440-12bd2fe5b961","resolution":{"observed_at":"2026-08-07T10:33:49.735475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:49.332581Z","title":"and Suzuki, T","venue":null,"work_id":"7b300a78-8f39-4e93-8c8b-e905c39a2cb9","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:39.302813Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:3137f5371cae354c6beb66d55aa90f9f0a0278d12c17d85ec7e2ceab210507f1","observation_id":"c752dad0-f22f-42b4-98f1-970cc2d3954b","resolution":{"observed_at":"2026-08-07T10:33:49.451421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:49.056036Z","title":"and Sanguineti, M","venue":null,"work_id":"2e610af8-f8d2-4d57-b1de-4e14dcc700bc","year":2002},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:39.418073Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:ec07c2a3579748a7ea794b75af522242bec5202e3a587fbdd83844827a0cad27","observation_id":"89ea7339-dbf9-46af-bc11-722083408b57","resolution":{"observed_at":"2026-08-07T10:33:49.176267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.14808","last_updated":"2026-04-29T13:47:53Z","snapshot_observed_at":"2026-07-06T21:27:22.757206Z","submitted_at":"2025-05-20T18:15:49Z","title":"Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective","version":2},"cited_work":{"arxiv_id":"2505.14808","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.14808","snapshot_observed_at":"2026-08-07T10:33:44.010674Z","title":"Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective","venue":"stat.ML","work_id":"03f1dbb0-0395-449f-958f-755b6e0fe502","year":2025},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:39.563472Z"},"links":{"cited_paper":"/paper/2505.14808","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:9826f9bcdd048a2b0a5eb7a873b443e4dc139dbad5c0d65c282b50f76c691c5f","observation_id":"c4835d13-b760-4fd5-acd4-ac23b81024eb","resolution":{"observed_at":"2026-08-07T10:33:44.111884Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:48.732473Z","title":null,"venue":null,"work_id":"575c3828-1984-4bfb-9b51-e158cf9d74c9","year":2017},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:39.674292Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:ef910eb0c836baffba0e1d16343ff6e5ec9e7314c1a6c3192e5026a8898fb6ad","observation_id":"cb4e955d-2b26-49d8-b1fd-66571b9508f4","resolution":{"observed_at":"2026-08-07T10:33:48.888457Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15607","last_updated":"2024-06-16T04:02:28Z","snapshot_observed_at":"2026-08-10T20:24:59.828653Z","submitted_at":"2024-02-23T21:07:20Z","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15607","snapshot_observed_at":"2026-08-07T10:33:39.817646Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:39.817646Z"},"links":{"cited_paper":"/paper/2402.15607","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:d98c9ad004314c27325835a47f731375f31805fe96d54bdda513e1edcaf28b96","observation_id":"769b032a-cfef-4f3b-a127-20b83ec0a2c7","resolution":{"observed_at":"2026-08-07T10:33:39.817646Z","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":"2026-08-07T10:33:48.449713Z","title":"E., Papailiopoulos, D., and Oymak, S","venue":null,"work_id":"dc85a7a0-8679-485d-8c04-bc60d15fa588","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:39.964430Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:5aa41a7644f819979f7c013c6bfac730fde40160fb5359e90a50e124193d256b","observation_id":"79616905-60ae-4386-8b35-68d37499ae55","resolution":{"observed_at":"2026-08-07T10:33:48.561985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12875","last_updated":"2024-09-21T06:48:45Z","snapshot_observed_at":"2026-08-07T02:31:13.044154Z","submitted_at":"2024-02-20T10:11:03Z","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12875","snapshot_observed_at":"2026-08-07T10:33:40.095232Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:40.095232Z"},"links":{"cited_paper":"/paper/2402.12875","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:e7658cabbcf34412f943efb2c2b359b446c0b9b3c5cfe58f2f2c4b28a7cc8e6b","observation_id":"252fc36b-cfc5-49c8-b26e-c7905db6cbc6","resolution":{"observed_at":"2026-08-07T10:33:40.095232Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03764","last_updated":"2021-06-08T10:02:26Z","snapshot_observed_at":"2026-08-10T14:40:11.318545Z","submitted_at":"2021-06-07T16:30:28Z","title":"On the Expressive Power of Self-Attention Matrices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03764","snapshot_observed_at":"2026-08-07T10:33:40.270823Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:40.270823Z"},"links":{"cited_paper":"/paper/2106.03764","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:fe6ba51f3bc4c7a4a060caa1f73d4d5f72c59e0c954ad159dbbd4e43a4630661","observation_id":"41d3ef9c-2de4-41fd-9c7d-7c548ac28b21","resolution":{"observed_at":"2026-08-07T10:33:40.270823Z","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":"2026-08-07T10:33:48.212450Z","title":null,"venue":null,"work_id":"3dd96843-6640-490d-99e7-eed45daa57df","year":2022},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:40.382251Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:8f1ffe7288217aaf1cffd1417dfae8cc3ecfc81d94cd6e54bba762cbc9e53941","observation_id":"af70dc40-f129-4b0b-a0c7-7397286ea440","resolution":{"observed_at":"2026-08-07T10:33:48.333252Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.10749","last_updated":"2023-05-02T14:16:15Z","snapshot_observed_at":"2026-08-10T14:40:09.922399Z","submitted_at":"2022-10-19T17:45:48Z","title":"Transformers Learn Shortcuts to Automata","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.10749","snapshot_observed_at":"2026-08-07T10:33:40.540930Z","title":"T., Goel, S., Krishnamurthy, A., and Zhang, C","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:40.540930Z"},"links":{"cited_paper":"/paper/2210.10749","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:e74ad26f1edc404a07810bb2ccbb07a68ffefe8e4fd4bf97f943c0c754f7818b","observation_id":"5dcb5bf9-8a9d-41b7-b476-5a3842da069c","resolution":{"observed_at":"2026-08-07T10:33:40.540930Z","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":"2026-08-07T10:33:47.934515Z","title":"V., Hashimoto, T., and Ma, T","venue":null,"work_id":"8407fd7c-eda4-46d4-ba44-709ae9f50bae","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:40.681219Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:186d04bc5923ac2693875f84d15a3e5fc51de45d0a4019cde3041201a4f1d524","observation_id":"1daecc26-197a-4ca2-b537-28ab6fd8074c","resolution":{"observed_at":"2026-08-07T10:33:48.100356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:47.689106Z","title":"and Sabharwal, A","venue":null,"work_id":"9521a77e-a0de-49d8-84dd-b696b23dc69a","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:40.807897Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:a794ae3799603c49ee5abec89224d4f6c17a7b4496520fb5453367f1e77d8d89","observation_id":"d51488a1-14bc-4584-af63-2231e31a1371","resolution":{"observed_at":"2026-08-07T10:33:47.810104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:47.409336Z","title":null,"venue":null,"work_id":"0edab235-92f3-4658-9153-9c94ed731345","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:40.922071Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:0d863dfac5a984af40a436fe946ac916e2feed32bbb7d2077a1bbbfc29fe3dd9","observation_id":"b1d28389-1062-44a3-a420-23a8c71dc702","resolution":{"observed_at":"2026-08-07T10:33:47.553893Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:47.103665Z","title":null,"venue":null,"work_id":"d52a6dc4-359e-41ec-921a-f63e20b7c7b7","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:41.026421Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:701ef123f0a7d1a6f8f646e4a046800f02cec2d75f53505fad5b8a4596603fa8","observation_id":"53aa29ae-0560-4d55-8149-b1ba7873f3df","resolution":{"observed_at":"2026-08-07T10:33:47.274346Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.03429","last_updated":"2019-01-10T23:21:35Z","snapshot_observed_at":"2026-08-05T09:57:13.598004Z","submitted_at":"2019-01-10T23:21:35Z","title":"On the Turing Completeness of Modern Neural Network Architectures","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.03429","snapshot_observed_at":"2026-08-07T10:33:41.145585Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:41.145585Z"},"links":{"cited_paper":"/paper/1901.03429","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:513ca9a33ac8062718a6bd02b7988e76efde3e08c90a1d273862d54debca5962","observation_id":"128c3e7c-3215-4e32-89a8-0250edc712fc","resolution":{"observed_at":"2026-08-07T10:33:41.145585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09268","last_updated":"2024-02-14T15:54:55Z","snapshot_observed_at":"2026-08-10T12:40:38.754076Z","submitted_at":"2024-02-14T15:54:55Z","title":"Transformers, parallel computation, and logarithmic depth","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09268","snapshot_observed_at":"2026-08-07T10:33:41.255646Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:41.255646Z"},"links":{"cited_paper":"/paper/2402.09268","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:fa1f55e517914a0de3a4c80cf0a7798df241dfe7150f46035aac70c5d3d08db7","observation_id":"bee2c974-0540-4f90-96b0-6b4539e200dd","resolution":{"observed_at":"2026-08-07T10:33:41.255646Z","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":"2026-08-07T10:33:46.832814Z","title":"J., and Telgarsky, M","venue":null,"work_id":"5f9e6ad3-c081-4581-b4d1-53a7e5f2b4f5","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:41.412340Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:630ec8f00063bd437021f62f1694a5af9b5d0bc7c2df5373de2bec2b23b7f239","observation_id":"4dd2153d-149f-4753-a89d-08e60392fa59","resolution":{"observed_at":"2026-08-07T10:33:46.949332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:46.606025Z","title":"W., Khan, M","venue":null,"work_id":"f5e8876b-e5c7-4513-85ee-83a3dc9b7ada","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:41.523722Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:38781796b6cf1d37175f37bd36c39be37a40eb5986724a79967b6b41f917d41b","observation_id":"8d5e45e7-3fd9-45e1-86b8-697fac049349","resolution":{"observed_at":"2026-08-07T10:33:46.679478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08540","last_updated":"2024-06-03T04:18:11Z","snapshot_observed_at":"2026-08-10T11:49:53.800203Z","submitted_at":"2023-10-12T17:32:09Z","title":"Do pretrained Transformers Learn In-Context by Gradient Descent?","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08540","snapshot_observed_at":"2026-08-07T10:33:41.646967Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:41.646967Z"},"links":{"cited_paper":"/paper/2310.08540","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:ae2eabc771cc49e3ddf38e68e569bf62513899985cb7203d071cd0559b5f0d1f","observation_id":"43f50103-e083-430a-b5da-18b7258417fa","resolution":{"observed_at":"2026-08-07T10:33:41.646967Z","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":"2026-08-07T10:33:41.773023Z","title":null,"venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:41.773023Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:03cf3d0ae2b7827c34e0a9886df09cf01595fd24169fa95ed8e52a9ac8fbdc23","observation_id":"5a6a06b2-9bd4-4ea3-8be9-5b5debc33486","resolution":{"observed_at":"2026-08-07T10:33:41.773023Z","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":"2026-08-07T10:33:41.922851Z","title":"N., Kaiser, ., and Polosukhin, I","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:41.922851Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:a4890e064da441d8610ef97c93cd9e39cf4001fae339cbacf35b0561016c6704","observation_id":"f01d2e7d-0339-434a-ae09-56d344751939","resolution":{"observed_at":"2026-08-07T10:33:41.922851Z","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":"2026-08-07T10:33:42.065495Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:42.065495Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:41370f21f754f0319c974c4c35416b887614589cc21e3d545bb52037a2b96495","observation_id":"0cd119e6-a82c-48ba-87d3-c2ebe9bd4584","resolution":{"observed_at":"2026-08-07T10:33:42.065495Z","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":"2026-08-07T10:33:46.353321Z","title":null,"venue":null,"work_id":"4b7ac26d-8eae-4752-aa26-84635a9c19c6","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:42.194477Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:235959f1f1fafe1fc61044d24f8ba30426ef8b615bb88a0193c905c108ff465b","observation_id":"02397db7-2e18-49df-8a67-b3e02784cefb","resolution":{"observed_at":"2026-08-07T10:33:46.463374Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:46.055603Z","title":null,"venue":null,"work_id":"3094447f-bb04-490d-99c2-d386f833f0c1","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:42.314366Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:6b85dcd8eb1f69813594026e121fd435829132b0038f69e96b831a29e27ac365","observation_id":"9be8aa75-a760-4b53-82bb-997f94b33d6b","resolution":{"observed_at":"2026-08-07T10:33:46.185324Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.05858","last_updated":"2024-10-15T13:43:50Z","snapshot_observed_at":"2026-08-10T11:11:24.311555Z","submitted_at":"2023-09-11T22:42:50Z","title":"Uncovering mesa-optimization algorithms in Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.05858","snapshot_observed_at":"2026-08-07T10:33:42.468990Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:42.468990Z"},"links":{"cited_paper":"/paper/2309.05858","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:4f05ee748f576b1640eb9efbb0363286ec467c71e010eb0aa7ede10328116a2d","observation_id":"6fdb14e6-8e63-428b-9224-93dcb347cd95","resolution":{"observed_at":"2026-08-07T10:33:42.468990Z","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":"2026-08-07T10:33:45.776002Z","title":null,"venue":null,"work_id":"735c5b23-ee0f-4d75-aab9-9b0079d3c716","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:42.570319Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:6c7bbba0c6a11600e3a5281b2f8114bba1631e8f07d77818cddb7a5b85997f58","observation_id":"996fc921-c1c9-48c2-8199-f361dd4ae60e","resolution":{"observed_at":"2026-08-07T10:33:45.943052Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18510","last_updated":"2024-12-06T19:50:34Z","snapshot_observed_at":"2026-08-12T01:17:57.623430Z","submitted_at":"2024-02-28T17:38:06Z","title":"RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18510","snapshot_observed_at":"2026-08-07T10:33:42.715105Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:42.715105Z"},"links":{"cited_paper":"/paper/2402.18510","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:71b783e8117ac2522fcdb6f2df44af489419fc2a2df91932c383e2ff1a2df0f2","observation_id":"ff6f128c-990d-4ac4-9183-51cb3ae78c2d","resolution":{"observed_at":"2026-08-07T10:33:42.715105Z","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":"2026-08-07T10:33:45.515842Z","title":null,"venue":null,"work_id":"ad2fab58-401a-4c4a-b195-c310c1f31ebc","year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:42.842571Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:a86bdd18d7a9630e120085ff6a5f009b71e7c40c842b4b974805c7f4cd8d6561","observation_id":"a1cef037-afae-4350-9869-5b6cbdec1bf4","resolution":{"observed_at":"2026-08-07T10:33:45.662006Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-07T10:33:45.245667Z","title":"M., Raghunathan, A., Liang, P., and Ma, T","venue":null,"work_id":"fcafac6c-5ba9-4df9-be7a-3f6ca4a76006","year":2022},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:42.960399Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:3f96227cf340659af60a5da722885601f5f45d33a6e2cb670f70b5d233e80a72","observation_id":"0ac95955-07f6-4701-a342-6a3d393197d1","resolution":{"observed_at":"2026-08-07T10:33:45.377198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10147","last_updated":"2024-09-25T19:16:16Z","snapshot_observed_at":"2026-07-06T19:02:56.021845Z","submitted_at":"2024-08-19T16:47:46Z","title":"In-Context Learning with Representations: Contextual Generalization of Trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10147","snapshot_observed_at":"2026-08-07T10:33:43.118598Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:43.118598Z"},"links":{"cited_paper":"/paper/2408.10147","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:853687bb0d57bd740e017fb19f26cf36bd3be5aa1a77c1db60c49e0895c33b6c","observation_id":"ef54cc4a-1763-4073-b8af-7f62ff900332","resolution":{"observed_at":"2026-08-07T10:33:43.118598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.11115","last_updated":"2023-03-13T01:47:55Z","snapshot_observed_at":"2026-07-06T11:12:04.788175Z","submitted_at":"2021-05-24T06:42:58Z","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.11115","snapshot_observed_at":"2026-08-07T10:33:43.256501Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:43.256501Z"},"links":{"cited_paper":"/paper/2105.11115","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:ff1a6a733b15e067f7e078a6d31cd57eb0b372c20fe25491afac40b544869d4b","observation_id":"5b8e69a8-c1d0-4b5b-b9fc-c81eebd1b422","resolution":{"observed_at":"2026-08-07T10:33:43.256501Z","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":"2026-08-07T10:33:44.994432Z","title":null,"venue":null,"work_id":"cff7a9c7-6752-43a0-81e9-d320c9d274eb","year":2024},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:43.421587Z"},"links":{"citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:5a0e376ca4e5ee83bd1432c009b80b6986d93d6b3140206478554f87337619cd","observation_id":"155cb17c-69ec-4d14-8c34-527df3a9dd8e","resolution":{"observed_at":"2026-08-07T10:33:45.098506Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19420","last_updated":"2023-10-10T04:47:47Z","snapshot_observed_at":"2026-08-10T11:50:40.040020Z","submitted_at":"2023-05-30T21:23:47Z","title":"What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19420","snapshot_observed_at":"2026-08-07T10:33:43.583162Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:43.583162Z"},"links":{"cited_paper":"/paper/2305.19420","citing_paper":"/paper/2506.05200"},"observation_digest":"sha256:3dc6a9a3faef345a8a6df505dc4c6c7a6eed452524287653d3215a257e66b318","observation_id":"c08623d9-6cd5-4f39-bbdc-f2d3c585938f","resolution":{"observed_at":"2026-08-07T10:33:43.583162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.05200","last_updated":"2025-08-28T16:07:16Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T04:21:50.390154Z","submitted_at":"2025-06-05T16:12:51Z","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory"},"reference_resolution":{"displayed":71,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":56,"verified_exact":3,"verified_fuzzy":12},"total_outbound_references":71},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 4 inbound Pith citation observations for arXiv:2506.05200."}