{"as_of":"2026-08-16T20:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4991f7684aaa9a213b7d0f37fd5cafc666b361afcd46ec71f03a89a2752cff6b","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":"2026-08-16T06:30:59.297886+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":"2026-08-15T18:13:42.208738Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-11T17:10:44.475912Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.06708","last_updated":"2023-04-13T17:57:01Z","snapshot_observed_at":"2026-08-16T15:40:37.699076Z","submitted_at":"2023-04-13T17:57:01Z","title":"Verbs in Action: Improving verb understanding in video-language models","version":1},"cited_work":{"arxiv_id":"2304.06708","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.06708","snapshot_observed_at":"2026-08-11T17:10:44.475912Z","title":"Verbs in Action: Improving verb understanding in video-language models","venue":"cs.CV","work_id":"924c47a6-a94b-41e3-8341-ab95e27ba1e6","year":2023},"citing_paper":{"arxiv_id":"2412.09353","last_updated":"2025-04-15T10:14:34Z","snapshot_observed_at":"2026-08-16T18:37:28.389117Z","submitted_at":"2024-12-12T15:22:03Z","title":"Causal Graphical Models for Vision-Language Compositional Understanding","version":2},"reference_index":1993,"source":"pdf_text","source_observed_at":"2026-08-11T17:10:44.347225Z"},"links":{"cited_paper":"/paper/2304.06708","citing_paper":"/paper/2412.09353"},"observation_digest":"sha256:d176bdb4fbb3697a68ef9018d715f690c702ca00be7176b96c9cd5c9c8f14e6e","observation_id":"84517f84-2ab7-41c3-87ec-ae41c01244ac","resolution":{"observed_at":"2026-08-11T17:10:44.480082Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06708","last_updated":"2023-04-13T17:57:01Z","snapshot_observed_at":"2026-08-16T15:40:37.699076Z","submitted_at":"2023-04-13T17:57:01Z","title":"Verbs in Action: Improving verb understanding in video-language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06708","snapshot_observed_at":"2026-08-15T18:13:42.208738Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18750","last_updated":"2025-07-24T19:01:05Z","snapshot_observed_at":"2026-08-15T18:47:44.892298Z","submitted_at":"2025-07-24T19:01:05Z","title":"CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:13:42.208738Z"},"links":{"cited_paper":"/paper/2304.06708","citing_paper":"/paper/2507.18750"},"observation_digest":"sha256:2762bb55e1b6f727354a31fb418e187840fb3ea5d8c66b75a2d68e4f45673905","observation_id":"47adc57a-a63e-4b88-8ab3-d99fe3fa6aca","resolution":{"observed_at":"2026-08-15T18:13:42.208738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2304.06708/citation-record","integrity":"/paper/2304.06708/integrity","json":"/paper/2304.06708/citation-record.json","paper":"/paper/2304.06708"},"outbound":[],"paper":{"arxiv_id":"2304.06708","last_updated":"2023-04-13T17:57:01Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T15:40:37.699076Z","submitted_at":"2023-04-13T17:57:01Z","title":"Verbs in Action: Improving verb understanding in video-language 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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2304.06708."}