{"as_of":"2026-08-04T21:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3d619d36096257ad264dec10be9b56d5a227e7f59e6a0808faa600f4a6ee0709","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":"2026-08-04T06:34:03.388597+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":"2026-07-11T19:15:37.565998Z","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":"2026-07-03T09:07:47.393566Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.12919","last_updated":"2023-12-01T17:33:55Z","snapshot_observed_at":"2026-07-06T16:50:46.608196Z","submitted_at":"2023-11-21T18:43:07Z","title":"SPOT! Revisiting Video-Language Models for Event Understanding","version":2},"cited_work":{"arxiv_id":"2311.12919","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.12919","snapshot_observed_at":"2026-07-03T09:07:47.393566Z","title":null,"venue":null,"work_id":"db63cfe7-4972-4cba-a9b5-5421493e45a2","year":2023},"citing_paper":{"arxiv_id":"2606.08144","last_updated":"2026-06-06T12:46:19Z","snapshot_observed_at":"2026-07-06T23:47:43.942733Z","submitted_at":"2026-06-06T12:46:19Z","title":"IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-27T19:50:42.757895Z"},"links":{"cited_paper":"/paper/2311.12919","citing_paper":"/paper/2606.08144"},"observation_digest":"sha256:915dad877e0d6c50d1bcdb1a40ec10b364cdaeb2973ab2d4643f153411c95bcb","observation_id":"d83a06b4-8194-44f0-a851-3a5bb20597dc","resolution":{"observed_at":"2026-07-02T21:17:24.791125Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12919","last_updated":"2023-12-01T17:33:55Z","snapshot_observed_at":"2026-07-06T16:50:46.608196Z","submitted_at":"2023-11-21T18:43:07Z","title":"SPOT! Revisiting Video-Language Models for Event Understanding","version":2},"cited_work":{"arxiv_id":"2311.12919","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.12919","snapshot_observed_at":"2026-07-03T09:07:47.393566Z","title":null,"venue":null,"work_id":"db63cfe7-4972-4cba-a9b5-5421493e45a2","year":2023},"citing_paper":{"arxiv_id":"2606.11689","last_updated":"2026-06-10T06:06:34Z","snapshot_observed_at":"2026-07-06T23:50:44.713490Z","submitted_at":"2026-06-10T06:06:34Z","title":"RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-27T10:35:28.866038Z"},"links":{"cited_paper":"/paper/2311.12919","citing_paper":"/paper/2606.11689"},"observation_digest":"sha256:ef4136cd66bbc4a6d429423c759395545bb211c75ce01f0aca230ba61965cd4b","observation_id":"20e8c3cd-11f7-4922-86ee-2c77851398a3","resolution":{"observed_at":"2026-07-03T09:07:47.394884Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12919","last_updated":"2023-12-01T17:33:55Z","snapshot_observed_at":"2026-07-06T16:50:46.608196Z","submitted_at":"2023-11-21T18:43:07Z","title":"SPOT! Revisiting Video-Language Models for Event Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12919","snapshot_observed_at":"2026-07-11T19:15:37.565998Z","title":"arXiv preprint arXiv:2311.12919 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04430","last_updated":"2026-07-05T17:50:32Z","snapshot_observed_at":"2026-07-11T19:15:37.250480Z","submitted_at":"2026-07-05T17:50:32Z","title":"Uncertainty-Aware Abstention in Large Language Models with Provable Alignment Guarantees","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-11T19:15:37.565998Z"},"links":{"cited_paper":"/paper/2311.12919","citing_paper":"/paper/2607.04430"},"observation_digest":"sha256:76344153d9502b6f0656cac397d8526d913028edcd0252212f3ab5758f20364e","observation_id":"72b3b01f-9928-469f-b770-d65348ea2d74","resolution":{"observed_at":"2026-07-11T19:15:37.565998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2311.12919/citation-record","integrity":"/paper/2311.12919/integrity","json":"/paper/2311.12919/citation-record.json","paper":"/paper/2311.12919"},"outbound":[],"paper":{"arxiv_id":"2311.12919","last_updated":"2023-12-01T17:33:55Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:50:46.608196Z","submitted_at":"2023-11-21T18:43:07Z","title":"SPOT! Revisiting Video-Language Models for Event Understanding"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2311.12919."}