{"as_of":"2026-08-22T14:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:62a07af97bbe0a9c0094b0528b45f299580ff8afbf0149404649988c44f72862","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":"2026-08-22T06:32:14.747728+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":"2026-08-16T00:01:14.776345Z","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":"2026-06-30T07:54:22.344177Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.08367","last_updated":"2024-10-01T10:11:14Z","snapshot_observed_at":"2026-08-20T12:18:45.552700Z","submitted_at":"2023-12-13T18:58:15Z","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08367","snapshot_observed_at":"2026-08-10T15:56:37.648819Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.13536","last_updated":"2025-01-23T10:35:22Z","snapshot_observed_at":"2026-08-15T21:59:17.503454Z","submitted_at":"2025-01-23T10:35:22Z","title":"ReasVQA: Advancing VideoQA with Imperfect Reasoning Process","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-10T15:56:37.648819Z"},"links":{"cited_paper":"/paper/2312.08367","citing_paper":"/paper/2501.13536"},"observation_digest":"sha256:9e25e0ad061fd06422b4116e738cd01c0ea29cb4cbb3708d894173a71a1dfa61","observation_id":"f4a0924f-dbad-4f48-a827-a192d9653db3","resolution":{"observed_at":"2026-08-10T15:56:37.648819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08367","last_updated":"2024-10-01T10:11:14Z","snapshot_observed_at":"2026-08-20T12:18:45.552700Z","submitted_at":"2023-12-13T18:58:15Z","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.08367","snapshot_observed_at":"2026-08-16T00:01:14.776345Z","title":"Lin, and Shan Yang","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.03173","last_updated":"2025-05-06T04:38:09Z","snapshot_observed_at":"2026-08-21T19:23:22.591388Z","submitted_at":"2025-05-06T04:38:09Z","title":"RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T00:01:14.776345Z"},"links":{"cited_paper":"/paper/2312.08367","citing_paper":"/paper/2505.03173"},"observation_digest":"sha256:535e3a37c5650e9e41d715acb01601a6a893031bb2244e5878732203779f7899","observation_id":"7488f1a5-dbe9-43d4-99f5-b28335ffd11a","resolution":{"observed_at":"2026-08-16T00:01:14.776345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.08367","last_updated":"2024-10-01T10:11:14Z","snapshot_observed_at":"2026-08-20T12:18:45.552700Z","submitted_at":"2023-12-13T18:58:15Z","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","version":4},"cited_work":{"arxiv_id":"2312.08367","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.08367","snapshot_observed_at":"2026-06-30T07:54:22.344177Z","title":null,"venue":null,"work_id":"ad412f36-7bfb-4a6f-9259-34c5b50b7c16","year":2024},"citing_paper":{"arxiv_id":"2606.29445","last_updated":"2026-06-28T15:11:19Z","snapshot_observed_at":"2026-08-14T09:35:12.467667Z","submitted_at":"2026-06-28T15:11:19Z","title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-30T07:48:01.719339Z"},"links":{"cited_paper":"/paper/2312.08367","citing_paper":"/paper/2606.29445"},"observation_digest":"sha256:2c74aeb90d52e7dd26af600252cfef0ac9a3f523ae1f0c2d17504497ed291525","observation_id":"6bdead58-81d0-44cc-92c6-28714474d1a4","resolution":{"observed_at":"2026-06-30T07:54:22.345583Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.08367/citation-record","integrity":"/paper/2312.08367/integrity","json":"/paper/2312.08367/citation-record.json","paper":"/paper/2312.08367"},"outbound":[],"paper":{"arxiv_id":"2312.08367","last_updated":"2024-10-01T10:11:14Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-20T12:18:45.552700Z","submitted_at":"2023-12-13T18:58:15Z","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2312.08367."}