{"as_of":"2026-08-19T00:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b09a3e6b80c2ea8f521b0e40f0b2230ab1ca244d210e80f771dd594d6c4ebdad","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T22:19:54.467641Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.15819/citation-record","integrity":"/paper/2607.15819/integrity","json":"/paper/2607.15819/citation-record.json","paper":"/paper/2607.15819"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.15661","last_updated":"2023-05-17T21:08:32Z","snapshot_observed_at":"2026-08-15T11:54:11.033052Z","submitted_at":"2022-11-28T18:59:51Z","title":"What learning algorithm is in-context learning? Investigations with linear models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.15661","snapshot_observed_at":"2026-08-01T22:19:53.336641Z","title":"What learn- ing algorithm is in-context learning? investigations with linear models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:53.336641Z"},"links":{"cited_paper":"/paper/2211.15661","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:a9d212ecabe3dd311db2f07b61bd631ce7c9f8c32fe9e3084c4e2112de96d7dd","observation_id":"6d947ce2-2b87-4fbe-8d24-3f6fddc3fa14","resolution":{"observed_at":"2026-08-01T22:19:53.336641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.04637","last_updated":"2023-07-06T16:55:36Z","snapshot_observed_at":"2026-08-16T15:25:44.387232Z","submitted_at":"2023-06-07T17:59:31Z","title":"Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.04637","snapshot_observed_at":"2026-08-01T22:19:53.480915Z","title":"Transformers as Statisticians: Prov- able in-context learning with in-context algorithm selection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:53.480915Z"},"links":{"cited_paper":"/paper/2306.04637","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:bad119500824411faec8bd0878630dca5c19bec59aad8df8f03929b639c0dfa1","observation_id":"80533f9c-b332-4a17-ac86-896c63ddd866","resolution":{"observed_at":"2026-08-01T22:19:53.480915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-01T22:19:53.635773Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:53.635773Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:20df9ca84f1b37d1fdc2042faff6e8e18131a70512bc986b1f7d9189d4a62092","observation_id":"cdc6ee46-e2eb-475c-9129-19ee3ee1bd19","resolution":{"observed_at":"2026-08-01T22:19:53.635773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10559","last_updated":"2023-05-15T11:45:12Z","snapshot_observed_at":"2026-08-16T16:47:10.413798Z","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":"2026-08-01T22:19:53.717359Z","title":"Why can gpt learn in- context? language models secretly perform gradient descent as meta-optimizers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:53.717359Z"},"links":{"cited_paper":"/paper/2212.10559","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:589771672de5471ded751c112cb4dc5148aeb7abd7d18212b29f599ad4d0fb70","observation_id":"9826500b-d439-411f-a5ba-babb80ea6390","resolution":{"observed_at":"2026-08-01T22:19:53.717359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01066","last_updated":"2023-08-11T19:27:58Z","snapshot_observed_at":"2026-08-16T16:41:53.982332Z","submitted_at":"2022-08-01T18:01:40Z","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01066","snapshot_observed_at":"2026-08-01T22:19:53.798648Z","title":"What can transformers learn in-context? a case study of simple function classes","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:53.798648Z"},"links":{"cited_paper":"/paper/2208.01066","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:e2b6d9bdea3b39f2377404c9707b4609a241953f506f85de9c572a1beb78871a","observation_id":"9237aa7a-a605-49ac-93e5-d11e4f3e1dac","resolution":{"observed_at":"2026-08-01T22:19:53.798648Z","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":"2026-08-01T22:19:53.878707Z","title":"Hagiwara, ‘Effect of bias matrix in linear self-attention for in-context learning”, IEICE Trans","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:53.878707Z"},"links":{"citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:f4168642136dcea6ad4069c1618d2dc89ccb81b0b0c4c67f60468a1b98ec8d01","observation_id":"ea8fdc47-2f64-4d75-9282-d2b96bfa7c9e","resolution":{"observed_at":"2026-08-01T22:19:53.878707Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-01T22:19:53.936375Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:53.936375Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:329688fc0c62b66ce75bd9960c67e0fce33121ec26c522390adbd7933fcb3da0","observation_id":"d7f69787-ae94-43f7-b508-827c05c03e51","resolution":{"observed_at":"2026-08-01T22:19:53.936375Z","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":"2026-08-01T22:19:53.995765Z","title":"Multilayer feedforward networks are universal approximators","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:53.995765Z"},"links":{"citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:c85dd709d65045ab92b69f9ad06e269085ef72f3043a59c46747475d50139919","observation_id":"39c4c4ee-0515-4a68-a996-215aa84d4945","resolution":{"observed_at":"2026-08-01T22:19:53.995765Z","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":"2026-08-01T22:19:54.064937Z","title":"ImageNet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:54.064937Z"},"links":{"citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:fce05a2a635aecb8ec6313cc781128e40911f33a82b26aa6cecee6d40ba0bdc2","observation_id":"739cf631-4c6d-4bce-a588-6b949ebfb345","resolution":{"observed_at":"2026-08-01T22:19:54.064937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03576","last_updated":"2023-07-07T13:09:18Z","snapshot_observed_at":"2026-08-16T15:17:57.789299Z","submitted_at":"2023-07-07T13:09:18Z","title":"One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03576","snapshot_observed_at":"2026-08-01T22:19:54.130585Z","title":"One step of gradient descent is provably the optimal in-context learner with one layer of linear self-attention","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:54.130585Z"},"links":{"cited_paper":"/paper/2307.03576","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:bf5a510fbeac0551bb9eb68f5f42b02cf7fcc7bddccfced479b891052bb01164","observation_id":"fba34b91-0d3c-4eba-890b-989f0ed7c938","resolution":{"observed_at":"2026-08-01T22:19:54.130585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.07677","last_updated":"2023-05-31T08:59:47Z","snapshot_observed_at":"2026-08-16T16:08:30.136973Z","submitted_at":"2022-12-15T09:21:21Z","title":"Transformers learn in-context by gradient descent","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.07677","snapshot_observed_at":"2026-08-01T22:19:54.206559Z","title":"Transformers learn in-context by gradient descent","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:54.206559Z"},"links":{"cited_paper":"/paper/2212.07677","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:b18899a4eb5faefe9698478ad75ea9514ce5d72831413f072b4d608b2af5f98a","observation_id":"937cce38-7c21-47f1-8935-1769e2e8f247","resolution":{"observed_at":"2026-08-01T22:19:54.206559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.03762","last_updated":"2023-08-02T00:41:18Z","snapshot_observed_at":"2026-08-17T01:19:18.409791Z","submitted_at":"2017-06-12T17:57:34Z","title":"Attention Is All You Need","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.03762","snapshot_observed_at":"2026-08-01T22:19:54.238369Z","title":"Attention is All you Need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:54.238369Z"},"links":{"cited_paper":"/paper/1706.03762","citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:f061f7a8a339929a44402ffa982b1e428a436c5239ff20c7b4b4d0646dfafbee","observation_id":"d32aa13d-cfde-43a9-ad2b-4ab39d557381","resolution":{"observed_at":"2026-08-01T22:19:54.238369Z","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":"2026-08-01T22:19:54.392217Z","title":"Trained transformers learn linear models in- context","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:54.392217Z"},"links":{"citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:29091e204c06a6649dd870a1c01f0ab5fd8d937a5f260df7e86236834b995f55","observation_id":"fbcd43ba-1ff3-4ad3-acc6-e10d7833b62d","resolution":{"observed_at":"2026-08-01T22:19:54.392217Z","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":"2026-08-01T22:19:54.467641Z","title":"A first course in linear model theory","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T22:19:54.467641Z"},"links":{"citing_paper":"/paper/2607.15819"},"observation_digest":"sha256:e219b3d7baedc81d7c51264a21bc34c09fd4588b950aca665ae24328d87ce687","observation_id":"c033295b-622d-45be-aa67-df9fb13fcb64","resolution":{"observed_at":"2026-08-01T22:19:54.467641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.15819","last_updated":"2026-07-17T10:28:27Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T02:43:41.371867Z","submitted_at":"2026-07-17T10:28:27Z","title":"In-context learning of closed form solution to simple linear regression task using transformer with linear self-attention"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":14},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2607.15819."}