{"as_of":"2026-08-09T09:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:27324c833a5047974e1b91d7ab2955a1484af62b7ac31094264d82478757e1b2","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T00:40:52.057242Z","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":"2026-08-05T23:59:13.903272Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.04632","last_updated":"2021-08-18T21:55:27Z","snapshot_observed_at":"2026-08-01T20:01:49.108442Z","submitted_at":"2021-06-08T18:34:21Z","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.04632","snapshot_observed_at":"2026-08-07T00:40:52.057242Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.13055","last_updated":"2025-06-16T02:52:44Z","snapshot_observed_at":"2026-08-07T21:24:42.876067Z","submitted_at":"2025-06-16T02:52:44Z","title":"CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T00:40:52.057242Z"},"links":{"cited_paper":"/paper/2106.04632","citing_paper":"/paper/2506.13055"},"observation_digest":"sha256:b102a8ecb1048094509b01fc5796a4480b39b17529dfc0fedfe0702fface3ee1","observation_id":"58490e69-5dbe-4499-bd3a-641d8bc41934","resolution":{"observed_at":"2026-08-07T00:40:52.057242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.04632","last_updated":"2021-08-18T21:55:27Z","snapshot_observed_at":"2026-08-01T20:01:49.108442Z","submitted_at":"2021-06-08T18:34:21Z","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.04632","snapshot_observed_at":"2026-08-06T19:43:42.892853Z","title":"arXiv preprint 22 Fig","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.04815","last_updated":"2025-07-07T09:33:19Z","snapshot_observed_at":"2026-08-09T08:45:09.436329Z","submitted_at":"2025-07-07T09:33:19Z","title":"From Vision To Language through Graph of Events in Space and Time: An Explainable Self-supervised Approach","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T19:43:42.892853Z"},"links":{"cited_paper":"/paper/2106.04632","citing_paper":"/paper/2507.04815"},"observation_digest":"sha256:04351d421d2742762f3ba1ecd09dd9ddbe775882ae5eb83d7de391f1d1d1c1fc","observation_id":"b7cd5ae3-72ce-4467-8188-336581dd4010","resolution":{"observed_at":"2026-08-06T19:43:42.892853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.04632","last_updated":"2021-08-18T21:55:27Z","snapshot_observed_at":"2026-08-01T20:01:49.108442Z","submitted_at":"2021-06-08T18:34:21Z","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.04632","snapshot_observed_at":"2026-08-06T12:31:26.059865Z","title":"Value: A multi-task benchmark for video-and-language understand- ing evaluation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21741","last_updated":"2025-07-29T12:17:46Z","snapshot_observed_at":"2026-08-06T12:31:24.449021Z","submitted_at":"2025-07-29T12:17:46Z","title":"MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T12:31:26.059865Z"},"links":{"cited_paper":"/paper/2106.04632","citing_paper":"/paper/2507.21741"},"observation_digest":"sha256:5e294e24427da805c5e0f4c7a36c8cbe8a409e110958f0a7ef476f1d284a75a0","observation_id":"7ba075e9-3b99-40b1-8010-230270d6c175","resolution":{"observed_at":"2026-08-06T12:31:26.059865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.04632","last_updated":"2021-08-18T21:55:27Z","snapshot_observed_at":"2026-08-01T20:01:49.108442Z","submitted_at":"2021-06-08T18:34:21Z","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","version":2},"cited_work":{"arxiv_id":"2106.04632","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.04632","snapshot_observed_at":"2026-08-05T23:59:13.903272Z","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","venue":"cs.CV","work_id":"b6ba9b25-4372-40bc-898b-b650c382c92a","year":2021},"citing_paper":{"arxiv_id":"2508.04549","last_updated":"2025-09-01T08:36:15Z","snapshot_observed_at":"2026-08-06T22:01:15.202286Z","submitted_at":"2025-08-06T15:34:24Z","title":"MSC: A Marine Wildlife Video Dataset with Grounded Segmentation and Clip-Level Captioning","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T23:59:10.065554Z"},"links":{"cited_paper":"/paper/2106.04632","citing_paper":"/paper/2508.04549"},"observation_digest":"sha256:363e930ba1627485f0fb9d74736d37a507ae7a6ad941266deeeed8ce55d4a02c","observation_id":"c3b64f8d-5b7b-4368-a21d-d868e28e907b","resolution":{"observed_at":"2026-08-05T23:59:14.075656Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.04632/citation-record","integrity":"/paper/2106.04632/integrity","json":"/paper/2106.04632/citation-record.json","paper":"/paper/2106.04632"},"outbound":[],"paper":{"arxiv_id":"2106.04632","last_updated":"2021-08-18T21:55:27Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-01T20:01:49.108442Z","submitted_at":"2021-06-08T18:34:21Z","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2106.04632."}