{"as_of":"2026-08-11T07:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bd87ec3136873fa14aa07885c8139fa0649011e7bf275cfcfe09fdc864b712d2","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T23:16:42.001361Z","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":"2026-06-29T00:12:50.456237Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.07076","last_updated":"2025-07-30T12:47:35Z","snapshot_observed_at":"2026-07-06T19:48:32.368124Z","submitted_at":"2024-11-11T15:51:48Z","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","version":3},"cited_work":{"arxiv_id":"2411.07076","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.07076","snapshot_observed_at":"2026-06-29T00:12:50.456237Z","title":"Storyteller: Improving long video description through global audio-visual character identification.arXiv preprint arXiv:2411.07076, 2024","venue":null,"work_id":"24c0eecc-fd77-42eb-a606-de94870fa0ba","year":2024},"citing_paper":{"arxiv_id":"2605.31069","last_updated":"2026-05-29T09:38:43Z","snapshot_observed_at":"2026-08-07T07:32:37.435310Z","submitted_at":"2026-05-29T09:38:43Z","title":"Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T23:16:42.001361Z"},"links":{"cited_paper":"/paper/2411.07076","citing_paper":"/paper/2605.31069"},"observation_digest":"sha256:fe7a1443c12593d05059899a1633d63be98e21c6a9f7b8bcb246e3081d3886cb","observation_id":"7e0dc3f9-f255-4a78-ae44-b912e4340fe4","resolution":{"observed_at":"2026-06-29T00:02:50.366251Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.07076","last_updated":"2025-07-30T12:47:35Z","snapshot_observed_at":"2026-07-06T19:48:32.368124Z","submitted_at":"2024-11-11T15:51:48Z","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","version":3},"cited_work":{"arxiv_id":"2411.07076","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.07076","snapshot_observed_at":"2026-06-29T00:12:50.456237Z","title":"Storyteller: Improving long video description through global audio-visual character identification.arXiv preprint arXiv:2411.07076, 2024","venue":null,"work_id":"24c0eecc-fd77-42eb-a606-de94870fa0ba","year":2024},"citing_paper":{"arxiv_id":"2605.31075","last_updated":"2026-05-29T09:43:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-29T09:43:35Z","title":"Task-Focused Memorization for Multimodal Agents","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T23:14:45.287255Z"},"links":{"cited_paper":"/paper/2411.07076","citing_paper":"/paper/2605.31075"},"observation_digest":"sha256:49318ae4e94bda1f9d363fca157e7506802514a75e79944e506cac4f7e5d5121","observation_id":"152e0ba2-86f2-4eb2-8dc9-f89dc9b0e23d","resolution":{"observed_at":"2026-06-29T00:12:50.457713Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.07076/citation-record","integrity":"/paper/2411.07076/integrity","json":"/paper/2411.07076/citation-record.json","paper":"/paper/2411.07076"},"outbound":[],"paper":{"arxiv_id":"2411.07076","last_updated":"2025-07-30T12:47:35Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:48:32.368124Z","submitted_at":"2024-11-11T15:51:48Z","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2411.07076."}