{"as_of":"2026-08-08T09:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:faab3fb887f83cae828885df91f2ee0e77a09294f0860b4f0efaa6373a765f0c","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T10:33:35.509713Z","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":"2026-07-02T23:57:29.167982Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"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":"2026-08-08T06:17:18.850826Z","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":"sha256:53f142f52cdc14347095d26c0f2ab578a3967c3be43f2eda464f5a83f279d730","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":"2402.04084","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":"2026-08-07T06:10:16.973138Z","title":"and Li, Y","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06179","last_updated":"2025-06-06T15:44:10Z","snapshot_observed_at":"2026-08-07T08:23:24.866121Z","submitted_at":"2025-06-06T15:44:10Z","title":"A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T06:10:16.973138Z"},"links":{"cited_paper":"/paper/2402.04084","citing_paper":"/paper/2506.06179"},"observation_digest":"sha256:8396dbfcb610b811680f9a71015db38f94243c86d9aef1283e28a88b5af46f10","observation_id":"56b1e1c8-31ae-4eb2-a06f-9c493c7e724e","resolution":{"observed_at":"2026-08-07T06:10:16.973138Z","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":"2402.04084","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04084","snapshot_observed_at":"2026-07-02T23:57:29.167982Z","title":"arXiv preprint arXiv:2402.04084 , year=","venue":null,"work_id":"6dc195e3-afb6-4b89-8cb7-737e09e0cdf7","year":null},"citing_paper":{"arxiv_id":"2606.09731","last_updated":"2026-07-23T03:50:50Z","snapshot_observed_at":"2026-08-04T15:25:58.819590Z","submitted_at":"2026-06-08T16:56:24Z","title":"Tight Sample Complexity of Transformers","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-06-27T17:33:48.373948Z"},"links":{"cited_paper":"/paper/2402.04084","citing_paper":"/paper/2606.09731"},"observation_digest":"sha256:65931a8f10d9ac07999093856f3fc6ea5786b756ce075d1061f36d14ffb79176","observation_id":"e0a40042-207e-41fd-babe-981385d2535f","resolution":{"observed_at":"2026-07-02T23:57:29.169339Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.04084/citation-record","integrity":"/paper/2402.04084/integrity","json":"/paper/2402.04084/citation-record.json","paper":"/paper/2402.04084"},"outbound":[],"paper":{"arxiv_id":"2402.04084","last_updated":"2024-02-06T15:39:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:26:19.028623Z","submitted_at":"2024-02-06T15:39:09Z","title":"Provably learning a multi-head attention layer"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.04084."}