{"as_of":"2026-08-12T19:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9267afead653024a26e5d6fdf2ebb45b75c25f63377650d6dc20cd6e1a6ac39d","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T16:57:35.780791Z","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":"2026-07-04T06:39:37.696968Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1904.11574","last_updated":"2020-05-11T19:43:42Z","snapshot_observed_at":"2026-08-12T17:43:07.893711Z","submitted_at":"2019-04-25T20:37:26Z","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.11574","snapshot_observed_at":"2026-08-11T16:57:35.780791Z","title":"Tvqa+: Spatio-temporal grounding for video question answering","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2412.09601","last_updated":"2025-03-05T07:06:15Z","snapshot_observed_at":"2026-08-12T09:02:21.582867Z","submitted_at":"2024-12-12T18:59:11Z","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T16:57:35.780791Z"},"links":{"cited_paper":"/paper/1904.11574","citing_paper":"/paper/2412.09601"},"observation_digest":"sha256:7fc42cd6771c3d9369168469db9f106189655194edec61b669d66b1435b327d7","observation_id":"7196a738-8449-467c-9ea5-e1a851bcd4ac","resolution":{"observed_at":"2026-08-11T16:57:35.780791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.11574","last_updated":"2020-05-11T19:43:42Z","snapshot_observed_at":"2026-08-12T17:43:07.893711Z","submitted_at":"2019-04-25T20:37:26Z","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.11574","snapshot_observed_at":"2026-08-07T04:40:43.256019Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.09953","last_updated":"2025-06-11T17:23:35Z","snapshot_observed_at":"2026-08-07T09:14:08.520195Z","submitted_at":"2025-06-11T17:23:35Z","title":"Outside Knowledge Conversational Video (OKCV) Dataset -- Dialoguing over Videos","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T04:40:43.256019Z"},"links":{"cited_paper":"/paper/1904.11574","citing_paper":"/paper/2506.09953"},"observation_digest":"sha256:65a20c376b9aa6dfa20b7a4f0f73a7392d97a9bdf304a1f98e9363aff78e4e8d","observation_id":"62cf8365-3fa5-4bd9-9ae0-7d3969c59f44","resolution":{"observed_at":"2026-08-07T04:40:43.256019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.11574","last_updated":"2020-05-11T19:43:42Z","snapshot_observed_at":"2026-08-12T17:43:07.893711Z","submitted_at":"2019-04-25T20:37:26Z","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","version":2},"cited_work":{"arxiv_id":"1904.11574","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1904.11574","snapshot_observed_at":"2026-07-04T06:39:37.696968Z","title":"Tvqa+: Spatio-temporal grounding for video question answering","venue":null,"work_id":"9355de67-cd6a-416e-ada4-f56434722675","year":1904},"citing_paper":{"arxiv_id":"2510.13016","last_updated":"2026-05-14T11:57:52Z","snapshot_observed_at":"2026-08-07T09:50:24.742675Z","submitted_at":"2025-10-14T22:10:49Z","title":"SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-18T07:06:06.322273Z"},"links":{"cited_paper":"/paper/1904.11574","citing_paper":"/paper/2510.13016"},"observation_digest":"sha256:a231fb3cd8a6e7481f3afe8a57796ccf65d4607807f228e48e5a3097d631cdcb","observation_id":"20a3a5ca-1af3-4158-a538-9d6f04df0234","resolution":{"observed_at":"2026-05-18T07:11:04.142028Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.11574","last_updated":"2020-05-11T19:43:42Z","snapshot_observed_at":"2026-08-12T17:43:07.893711Z","submitted_at":"2019-04-25T20:37:26Z","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","version":2},"cited_work":{"arxiv_id":"1904.11574","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1904.11574","snapshot_observed_at":"2026-07-04T06:39:37.696968Z","title":"Tvqa+: Spatio-temporal grounding for video question answering","venue":null,"work_id":"9355de67-cd6a-416e-ada4-f56434722675","year":1904},"citing_paper":{"arxiv_id":"2606.21734","last_updated":"2026-06-19T20:43:49Z","snapshot_observed_at":"2026-08-05T18:05:51.515234Z","submitted_at":"2026-06-19T20:43:49Z","title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","version":1},"reference_index":162,"source":"arxiv_source","source_observed_at":"2026-06-26T14:19:53.450263Z"},"links":{"cited_paper":"/paper/1904.11574","citing_paper":"/paper/2606.21734"},"observation_digest":"sha256:b7281fe11f614f9ce433a09c6fc03d673b3c65dee20b797be14f4654cf0243b1","observation_id":"46983744-c8eb-40f3-b790-10b195a4f8d2","resolution":{"observed_at":"2026-07-04T06:39:37.698319Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1904.11574/citation-record","integrity":"/paper/1904.11574/integrity","json":"/paper/1904.11574/citation-record.json","paper":"/paper/1904.11574"},"outbound":[],"paper":{"arxiv_id":"1904.11574","last_updated":"2020-05-11T19:43:42Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T17:43:07.893711Z","submitted_at":"2019-04-25T20:37:26Z","title":"TVQA+: Spatio-Temporal Grounding 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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1904.11574."}