{"as_of":"2026-08-07T01:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b8c85a00dad0df2cc9fc078d3aae422caebd3d5be44acec39736126582fa7ba5","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":"2026-08-06T06:34:29.942622+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":"2026-08-06T17:55:45.430467Z","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":"2026-07-02T17:27:15.761589Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.15393","last_updated":"2025-03-01T02:06:59Z","snapshot_observed_at":"2026-07-06T20:40:25.692449Z","submitted_at":"2025-02-21T11:40:23Z","title":"LongCaptioning: Unlocking the Power of Long Video Caption Generation in Large Multimodal Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15393","snapshot_observed_at":"2026-08-06T17:55:45.430467Z","title":"CoRR abs/2502.15393 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09693","last_updated":"2025-07-13T16:09:58Z","snapshot_observed_at":"2026-08-06T19:46:33.050466Z","submitted_at":"2025-07-13T16:09:58Z","title":"ExpStar: Towards Automatic Commentary Generation for Multi-discipline Scientific Experiments","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T17:55:45.430467Z"},"links":{"cited_paper":"/paper/2502.15393","citing_paper":"/paper/2507.09693"},"observation_digest":"sha256:3a21c2691ccc9a8e118c1bfc37e9e5d42e62587399b4be4ff9ad23485ef7cda1","observation_id":"6191a76b-1841-4846-b350-55411b4aefc4","resolution":{"observed_at":"2026-08-06T17:55:45.430467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.15393","last_updated":"2025-03-01T02:06:59Z","snapshot_observed_at":"2026-07-06T20:40:25.692449Z","submitted_at":"2025-02-21T11:40:23Z","title":"LongCaptioning: Unlocking the Power of Long Video Caption Generation in Large Multimodal Models","version":2},"cited_work":{"arxiv_id":"2502.15393","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.15393","snapshot_observed_at":"2026-07-02T17:27:15.761589Z","title":"Longcaptioning: Unlocking the power of long video caption generation in large multimodal models,","venue":null,"work_id":"a9c81210-8e79-43ef-99b5-c0dae6e179ae","year":2025},"citing_paper":{"arxiv_id":"2606.07433","last_updated":"2026-06-05T16:29:13Z","snapshot_observed_at":"2026-08-01T21:05:06.439607Z","submitted_at":"2026-06-05T16:29:13Z","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-06-27T22:00:28.350003Z"},"links":{"cited_paper":"/paper/2502.15393","citing_paper":"/paper/2606.07433"},"observation_digest":"sha256:4418d1c64dc6c169b04c2ebdf020e23106bbedc9c1b4b9008a40d38a9b0b67fd","observation_id":"74bbc708-9bc2-4185-a15a-3c23914329cf","resolution":{"observed_at":"2026-07-02T17:27:15.763039Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.15393","last_updated":"2025-03-01T02:06:59Z","snapshot_observed_at":"2026-07-06T20:40:25.692449Z","submitted_at":"2025-02-21T11:40:23Z","title":"LongCaptioning: Unlocking the Power of Long Video Caption Generation in Large Multimodal Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15393","snapshot_observed_at":"2026-07-31T05:08:20.086437Z","title":"LongCaptioning: Unlocking the power of long video caption generation in large multimodal models.arXiv preprint arXiv:2502.15393, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.28509","last_updated":"2026-07-30T16:48:28Z","snapshot_observed_at":"2026-08-03T15:13:30.086781Z","submitted_at":"2026-07-30T16:48:28Z","title":"RefCaptioner: Multi-Reference Image-Grounded Video Captioning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-31T05:08:20.086437Z"},"links":{"cited_paper":"/paper/2502.15393","citing_paper":"/paper/2607.28509"},"observation_digest":"sha256:6098f8a6274a65dcba9eb22041a5245552d56274fa4a8ddb124b7c13c7c96e01","observation_id":"e5dae559-0b17-4e16-a728-7434a8665c0f","resolution":{"observed_at":"2026-07-31T05:08:20.086437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.15393/citation-record","integrity":"/paper/2502.15393/integrity","json":"/paper/2502.15393/citation-record.json","paper":"/paper/2502.15393"},"outbound":[],"paper":{"arxiv_id":"2502.15393","last_updated":"2025-03-01T02:06:59Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T20:40:25.692449Z","submitted_at":"2025-02-21T11:40:23Z","title":"LongCaptioning: Unlocking the Power of Long Video Caption Generation in Large Multimodal Models"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2502.15393."}