{"as_of":"2026-08-10T10:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e97822fbd395d259462fdf553600c279d3c56784377cc380ae75e92a87804649","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:37:03.643683Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-08T17:00:37.250246Z","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":"2026-05-11T17:51:09.334284Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_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},"cited_work":{"arxiv_id":"2507.13540","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.13540","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"afc2f6ce-9a93-4009-93c5-e625ab797bab","year":2025},"citing_paper":{"arxiv_id":"2605.04995","last_updated":"2026-05-06T14:53:55Z","snapshot_observed_at":"2026-07-06T23:17:43.402046Z","submitted_at":"2026-05-06T14:53:55Z","title":"Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-08T17:00:37.250246Z"},"links":{"cited_paper":"/paper/2507.13540","citing_paper":"/paper/2605.04995"},"observation_digest":"sha256:d5692d2f569fe15ce59925a0511a9b06561c24ea5e438f32f08c1af843906280","observation_id":"7dec9c26-646a-4dcf-a1b1-03ab48c189ef","resolution":{"observed_at":"2026-05-11T17:51:09.336932Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.13540/citation-record","integrity":"/paper/2507.13540/integrity","json":"/paper/2507.13540/citation-record.json","paper":"/paper/2507.13540"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:37:04.423769Z","title":"A.1 E VENTS IN A RANDOM WALK SEQUENCE Theorem 3 (Theorem 1 in (Fan et al., 2021))","venue":null,"work_id":"f77089b4-4ea4-4d85-ad29-79b5ba7e8fc4","year":2021},"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":1,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.581055Z"},"links":{"citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:0cb491e189f220b5286b529905d1e7bbcbc1d61ce2a65dbfb36951547bc1e1e6","observation_id":"7e260cc1-35e0-42b0-8615-44b098b2e65d","resolution":{"observed_at":"2026-08-06T16:37:04.524602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T16:37:02.712441Z","title":"Why can gpt learn in-context? language models implicitly perform gradient descent as meta-optimizers","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":4,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:02.712441Z"},"links":{"cited_paper":"/paper/2212.10559","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:d2cf20dffe75342338191ad126a59867dc124672384ae2bfaa73e640f0c1b164","observation_id":"deca8069-da0c-437e-813b-8acbc46c6ab6","resolution":{"observed_at":"2026-08-06T16:37:02.712441Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.03874","last_updated":"2021-11-08T21:30:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-03-05T18:59:39Z","title":"Measuring Mathematical Problem Solving With the MATH Dataset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.03874","snapshot_observed_at":"2026-08-06T16:37:02.864036Z","title":"Measuring mathematical problem solving with the math dataset","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":6,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:02.864036Z"},"links":{"cited_paper":"/paper/2103.03874","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:2ac63f8541531aa4de80d1793c0de6102e1e9574a9b86ee3398cc55ae6817e0e","observation_id":"c881234e-b7ab-4a2f-b6d5-038eaa931e9e","resolution":{"observed_at":"2026-08-06T16:37:02.864036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05249","last_updated":"2023-10-08T17:55:33Z","snapshot_observed_at":"2026-07-06T16:29:32.059905Z","submitted_at":"2023-10-08T17:55:33Z","title":"In-Context Convergence of Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05249","snapshot_observed_at":"2026-08-06T16:37:02.984306Z","title":"In-context convergence of transformers","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":8,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:02.984306Z"},"links":{"cited_paper":"/paper/2310.05249","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:d2f81db85dd13d07b12715819000d8e80b6d9a77519a980f7175a737cfe8e6bf","observation_id":"b0af5446-026e-47f2-8d34-93a54cd36b13","resolution":{"observed_at":"2026-08-06T16:37:02.984306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-06T16:37:03.059773Z","title":"Semi-supervised classification with graph convolutional networks","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":9,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.059773Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:752933fe6a067bcca6a882dc2d932c4e3beff20042943ac8799518604441d182","observation_id":"7f1c8bea-505c-460e-bcb0-050be785130b","resolution":{"observed_at":"2026-08-06T16:37:03.059773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00070","last_updated":"2025-05-02T05:27:38Z","snapshot_observed_at":"2026-08-08T10:10:41.531442Z","submitted_at":"2024-12-29T18:58:09Z","title":"ICLR: In-Context Learning of Representations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00070","snapshot_observed_at":"2026-08-06T16:37:03.260977Z","title":"Core Francisco Park, Andrew Lee, Ekdeep Singh Lubana, Yongyi Yang, Maya Okawa, Kento Nishi, Martin Wattenberg, and Hidenori Tanaka","venue":null,"work_id":null,"year":2022},"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":13,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.260977Z"},"links":{"cited_paper":"/paper/2501.00070","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:ae282b9f857f51f88471e914b86c9ed5222287b12c1836db74da0e57711cab88","observation_id":"cbb59033-0b0e-47da-a17c-3453b7beacaf","resolution":{"observed_at":"2026-08-06T16:37:03.260977Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.02217","last_updated":"2021-04-28T07:24:49Z","snapshot_observed_at":"2026-08-05T15:08:02.538782Z","submitted_at":"2020-07-16T17:52:37Z","title":"Hopfield Networks is All You Need","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.02217","snapshot_observed_at":"2026-08-06T16:37:03.328081Z","title":"Hopfield networks is all you need","venue":null,"work_id":null,"year":2008},"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":14,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.328081Z"},"links":{"cited_paper":"/paper/2008.02217","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:7aed9d1f0ccd9550de7b47f666f2f806cdb214cf4d66c74cec255c85c4978d98","observation_id":"e9a24332-1d2f-4ed5-8a10-8797d88d55d0","resolution":{"observed_at":"2026-08-06T16:37:03.328081Z","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":"2026-08-06T16:37:04.704224Z","title":"Spectral and algebraic graph theory, incomplete draft, dated december 4, 2019,","venue":null,"work_id":"ad744baf-64f2-438e-8d75-b2d458e8ea71","year":2019},"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":15,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.390213Z"},"links":{"citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:7fb4a19f2d584030280ed225eae505e4472708c45eb9049d0ea84722fdfdde0a","observation_id":"af382494-60fd-4af5-bd66-f65b4a65f50c","resolution":{"observed_at":"2026-08-06T16:37:04.814915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.11474","last_updated":"2025-01-29T10:27:40Z","snapshot_observed_at":"2026-08-08T00:03:37.835337Z","submitted_at":"2024-10-15T10:22:27Z","title":"How Transformers Get Rich: Approximation and Dynamics Analysis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.11474","snapshot_observed_at":"2026-08-06T16:37:03.512234Z","title":"How transformers implement induction heads: Approximation and optimization analysis","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":17,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.512234Z"},"links":{"cited_paper":"/paper/2410.11474","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:aa8f832e7a93dec4f40e2b03bf7b3e15240c5e1562227bf1d55e058c79e3ab71","observation_id":"e86347a4-52b2-4b0b-b888-38fbdd3e9914","resolution":{"observed_at":"2026-08-06T16:37:03.512234Z","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":"2026-08-06T16:37:04.173008Z","title":"(γ1, γ2, Z , U ) and σ′ : Rd → Rd be a great mapping w.r.t.(γ′ 1, γ′ 2, Z , U ), then σ1 ◦ σ2 is a great mapping w.r.t.(γ1γ′ 1, γ2γ′ 2, Z , U )","venue":null,"work_id":"37ce4d5f-2de7-4f01-bf5f-d4c500688520","year":2024},"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":19,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.643683Z"},"links":{"citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:dc74949f4ad804346732a5fda74471d468947d295c5abb781b64697ad046b76a","observation_id":"e4f92c17-1f35-4b49-a87d-f33224c049d1","resolution":{"observed_at":"2026-08-06T16:37:04.308245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:37:03.175444Z","title":"Asymptotic theory of in-context learning by linear attention","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":2018,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.175444Z"},"links":{"citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:e380b03de279f2ad6289d593f4f4df032c33c7605b40171e34920de64ec9ea6f","observation_id":"485b4f5b-17a1-461a-9d15-5c3c0df911df","resolution":{"observed_at":"2026-08-06T16:37:03.175444Z","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":"2026-08-06T16:37:03.442170Z","title":"Recurrent self-attention dynamics: An energy-agnostic perspective from jacobians","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":2019,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.442170Z"},"links":{"citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:a6b04d7ae267e79338717180e8a6988ea3909293181170e2de865a153595f55b","observation_id":"37875f45-884d-404b-8888-193318e70b76","resolution":{"observed_at":"2026-08-06T16:37:03.442170Z","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":"2026-08-06T16:37:04.866817Z","title":"Exploring the robustness of in-context learning with noisy labels","venue":null,"work_id":"34fc176b-57fa-489e-9da5-a0a304bbf65a","year":2025},"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":2020,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:02.659663Z"},"links":{"citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:da11f621845a8ff997f48e3b9c5b79455fa171186b1ec043942b17f0db970dff","observation_id":"3d7268b3-ffa3-4de4-b18e-e101cd042960","resolution":{"observed_at":"2026-08-06T16:37:04.901804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11646","last_updated":"2025-05-30T09:02:07Z","snapshot_observed_at":"2026-08-07T18:13:03.036753Z","submitted_at":"2025-02-17T10:39:11Z","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","version":3},"cited_work":{"arxiv_id":"2502.11646","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.11646","snapshot_observed_at":"2026-08-06T16:37:03.982494Z","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","venue":"cs.LG","work_id":"b289bad9-0592-45f8-9f29-8a74bb8088bf","year":2025},"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":2021,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:02.929456Z"},"links":{"cited_paper":"/paper/2502.11646","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:7691429b7e85545337446b4ecb3a87e3c79a9382c8ea163b64d29553922ea934","observation_id":"0c25e03d-0d9a-4a2b-83a1-9c53fa21a201","resolution":{"observed_at":"2026-08-06T16:37:04.045002Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10794","last_updated":"2025-08-21T11:31:09Z","snapshot_observed_at":"2026-08-08T06:50:47.708998Z","submitted_at":"2023-12-17T19:06:29Z","title":"A mathematical perspective on Transformers","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10794","snapshot_observed_at":"2026-08-06T16:37:02.796390Z","title":"A mathematical perspec- tive on transformers","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":2022,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:02.796390Z"},"links":{"cited_paper":"/paper/2312.10794","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:6a34aa2af00fc19fd37bb9883a05c8bdb248c0caa44fabfff1a60d5f3b9916da","observation_id":"9c0ed3e4-7792-4070-80ae-b784f7715728","resolution":{"observed_at":"2026-08-06T16:37:02.796390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.15661","last_updated":"2023-05-17T21:08:32Z","snapshot_observed_at":"2026-08-07T19:33:04.292595Z","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":"2026-08-06T16:37:02.536151Z","title":"What learning algo- rithm is in-context learning? investigations with linear models","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":2023,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:02.536151Z"},"links":{"cited_paper":"/paper/2211.15661","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:98d9843c33fe8abccaffbe22c6ac1e68cdd5dda3805a4fda3674f705a1f2bbcd","observation_id":"fd57a1c7-9e2e-4e4f-8c4c-f6967efd72af","resolution":{"observed_at":"2026-08-06T16:37:02.536151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.12837","last_updated":"2022-10-20T14:04:10Z","snapshot_observed_at":"2026-08-01T15:23:39.998892Z","submitted_at":"2022-02-25T17:25:19Z","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.12837","snapshot_observed_at":"2026-08-06T16:37:03.216653Z","title":"Rethinking the role of demonstrations: What makes in-context learning work? arXiv preprint arXiv:2202.12837,","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":2024,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:03.216653Z"},"links":{"cited_paper":"/paper/2202.12837","citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:b3c8f3fecd3fb4fd50e7ff21045d199f238669c650466005a5d58e85caf5eb16","observation_id":"25d3e5df-f91d-472d-9a9d-bef5904c0dbd","resolution":{"observed_at":"2026-08-06T16:37:03.216653Z","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":"2026-08-06T16:37:02.587659Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"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":2025,"source":"pdf_text","source_observed_at":"2026-08-06T16:37:02.587659Z"},"links":{"citing_paper":"/paper/2507.13540"},"observation_digest":"sha256:917756aaf23ece25db625972f171daf00318b0fbb1c7f8991d30f8f5516b833b","observation_id":"200f9cda-2031-48cd-8e3e-5712925c66a9","resolution":{"observed_at":"2026-08-06T16:37:02.587659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.13540","last_updated":"2025-07-30T01:51:41Z","latest_version":2,"primary_category":"cs.LG","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"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":1,"verified_fuzzy":4},"total_outbound_references":19},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 1 inbound Pith citation observation for arXiv:2507.13540."}