{"as_of":"2026-08-10T00:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:51e82011117686e4911147d4e37706ed7df8fdc72ec6f0b2606a1edfa9c3ea63","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T05:16:20.035595Z","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":"2026-06-28T19:22:35.277252Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.14951","last_updated":"2024-02-22T20:26:08Z","snapshot_observed_at":"2026-07-06T17:34:16.065501Z","submitted_at":"2024-02-22T20:26:08Z","title":"In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14951","snapshot_observed_at":"2026-08-09T05:16:20.035595Z","title":"In-context learning of a linear transformer block: benefits of the mlp component and one-step gd initialization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03327","last_updated":"2025-02-05T16:22:46Z","snapshot_observed_at":"2026-08-09T11:14:21.353958Z","submitted_at":"2025-02-05T16:22:46Z","title":"Is In-Context Universality Enough? MLPs are Also Universal In-Context","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-09T05:16:20.035595Z"},"links":{"cited_paper":"/paper/2402.14951","citing_paper":"/paper/2502.03327"},"observation_digest":"sha256:dc1a0643e8de131735506efd0052a6dedf8fc6eeab87e53a66474564c0bcb434","observation_id":"70821f6a-6323-4e15-b203-24cd5a429a5c","resolution":{"observed_at":"2026-08-09T05:16:20.035595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14951","last_updated":"2024-02-22T20:26:08Z","snapshot_observed_at":"2026-07-06T17:34:16.065501Z","submitted_at":"2024-02-22T20:26:08Z","title":"In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization","version":1},"cited_work":{"arxiv_id":"2402.14951","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.14951","snapshot_observed_at":"2026-06-28T19:22:35.277252Z","title":"L.(2024c)","venue":null,"work_id":"fed2907d-574f-4da4-b883-d57ce2939b92","year":null},"citing_paper":{"arxiv_id":"2605.06609","last_updated":"2026-05-07T17:27:55Z","snapshot_observed_at":"2026-07-06T23:19:00.794334Z","submitted_at":"2026-05-07T17:27:55Z","title":"Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-08T12:22:27.265973Z"},"links":{"cited_paper":"/paper/2402.14951","citing_paper":"/paper/2605.06609"},"observation_digest":"sha256:1b10c878a453a327565530b64e37f7093e11298897e8aba6eebaa2a210d29e3b","observation_id":"c98b5466-2e58-4226-8525-634a1a1a3d1b","resolution":{"observed_at":"2026-05-11T19:16:09.569363Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14951","last_updated":"2024-02-22T20:26:08Z","snapshot_observed_at":"2026-07-06T17:34:16.065501Z","submitted_at":"2024-02-22T20:26:08Z","title":"In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization","version":1},"cited_work":{"arxiv_id":"2402.14951","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.14951","snapshot_observed_at":"2026-06-28T19:22:35.277252Z","title":"L.(2024c)","venue":null,"work_id":"fed2907d-574f-4da4-b883-d57ce2939b92","year":null},"citing_paper":{"arxiv_id":"2606.00605","last_updated":"2026-05-30T08:05:27Z","snapshot_observed_at":"2026-08-09T16:32:50.056879Z","submitted_at":"2026-05-30T08:05:27Z","title":"Looped Transformers with Layer Normalization Provably Learn the Power Method","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-06-28T19:03:51.212121Z"},"links":{"cited_paper":"/paper/2402.14951","citing_paper":"/paper/2606.00605"},"observation_digest":"sha256:132feca29e545b75a05d4937dec449ec1692fa01ec270288c0e8b71acfa56241","observation_id":"d75e15ca-415b-407d-8373-32861bdf2b94","resolution":{"observed_at":"2026-06-28T19:22:35.278749Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.14951/citation-record","integrity":"/paper/2402.14951/integrity","json":"/paper/2402.14951/citation-record.json","paper":"/paper/2402.14951"},"outbound":[],"paper":{"arxiv_id":"2402.14951","last_updated":"2024-02-22T20:26:08Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-07-06T17:34:16.065501Z","submitted_at":"2024-02-22T20:26:08Z","title":"In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.14951."}