{"as_of":"2026-08-08T02:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ff493b51aad8d67fdfc76e57b443baf251851ca42c1552a99f0bac10a593ea9f","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T06:10:17.345237Z","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":"2026-07-04T13:29:50.964232Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.12680","last_updated":"2024-10-12T04:12:31Z","snapshot_observed_at":"2026-07-06T16:35:35.755643Z","submitted_at":"2023-10-19T12:18:24Z","title":"On the Optimization and Generalization of Multi-head Attention","version":2},"cited_work":{"arxiv_id":"2310.12680","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.12680","snapshot_observed_at":"2026-07-04T13:29:50.964232Z","title":"On the optimization and generalization of multi-head attention","venue":null,"work_id":"6d43a358-1f93-4286-9793-bb4dc08db41c","year":2023},"citing_paper":{"arxiv_id":"2306.14048","last_updated":"2023-12-18T19:10:00Z","snapshot_observed_at":"2026-08-06T19:19:02.165567Z","submitted_at":"2023-06-24T20:11:14Z","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","version":3},"reference_index":114,"source":"pdf_text","source_observed_at":"2026-05-17T18:00:50.053377Z"},"links":{"cited_paper":"/paper/2310.12680","citing_paper":"/paper/2306.14048"},"observation_digest":"sha256:2fb9371b3d6ea25f3d3dc53f6d7229b1895ea4044d1d2c800c0159ad47c96e2c","observation_id":"5fbf6793-d710-4691-817d-2cdfbdbe287b","resolution":{"observed_at":"2026-05-17T18:00:50.332170Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.12680","last_updated":"2024-10-12T04:12:31Z","snapshot_observed_at":"2026-07-06T16:35:35.755643Z","submitted_at":"2023-10-19T12:18:24Z","title":"On the Optimization and Generalization of Multi-head Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.12680","snapshot_observed_at":"2026-08-07T06:10:17.345237Z","title":"On the Optimization and Generalization of Multi -head Attention , October 2023","venue":null,"work_id":null,"year":2023},"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":15,"source":"arxiv_source","source_observed_at":"2026-08-07T06:10:17.345237Z"},"links":{"cited_paper":"/paper/2310.12680","citing_paper":"/paper/2506.06179"},"observation_digest":"sha256:dd48d0b40da1e10ea6a266b878887dbe0fa2711ef92e4bbef5354fab425ac641","observation_id":"cd45c953-249f-42de-9f57-f256a71e4bd0","resolution":{"observed_at":"2026-08-07T06:10:17.345237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.12680","last_updated":"2024-10-12T04:12:31Z","snapshot_observed_at":"2026-07-06T16:35:35.755643Z","submitted_at":"2023-10-19T12:18:24Z","title":"On the Optimization and Generalization of Multi-head Attention","version":2},"cited_work":{"arxiv_id":"2310.12680","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.12680","snapshot_observed_at":"2026-07-04T13:29:50.964232Z","title":"On the optimization and generalization of multi-head attention","venue":null,"work_id":"6d43a358-1f93-4286-9793-bb4dc08db41c","year":2023},"citing_paper":{"arxiv_id":"2606.26749","last_updated":"2026-06-25T08:33:34Z","snapshot_observed_at":"2026-08-01T16:00:20.311664Z","submitted_at":"2026-06-25T08:33:34Z","title":"Structure Before Collapse: Transient semantic geometry in next-token prediction","version":1},"reference_index":201,"source":"arxiv_source","source_observed_at":"2026-06-26T05:14:07.208255Z"},"links":{"cited_paper":"/paper/2310.12680","citing_paper":"/paper/2606.26749"},"observation_digest":"sha256:d843374d9402b143839485813119a2ae02cc4419c938fb972a214ce709516956","observation_id":"8270ac6b-bb71-4d17-acb4-c80c0289ccde","resolution":{"observed_at":"2026-07-04T13:29:50.966010Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.12680/citation-record","integrity":"/paper/2310.12680/integrity","json":"/paper/2310.12680/citation-record.json","paper":"/paper/2310.12680"},"outbound":[],"paper":{"arxiv_id":"2310.12680","last_updated":"2024-10-12T04:12:31Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T16:35:35.755643Z","submitted_at":"2023-10-19T12:18:24Z","title":"On the Optimization and Generalization of Multi-head Attention"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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:2310.12680."}