{"as_of":"2026-08-10T03:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cb58106e94fa435140f10528207683ed101705f901b008b90579e8da1aefa3b7","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":"2026-08-06T17:58:27.497281Z","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":"2026-05-17T02:46:16.724019Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.11865","last_updated":"2023-11-20T16:02:10Z","snapshot_observed_at":"2026-08-09T17:05:39.480445Z","submitted_at":"2023-11-20T16:02:10Z","title":"VLM-Eval: A General Evaluation on Video Large Language Models","version":1},"cited_work":{"arxiv_id":"2311.11865","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.11865","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"7a71024c-d83c-4f9b-bceb-40007ce5d941","year":2023},"citing_paper":{"arxiv_id":"2403.00476","last_updated":"2024-06-03T04:13:39Z","snapshot_observed_at":"2026-08-04T21:17:37.211833Z","submitted_at":"2024-03-01T12:02:19Z","title":"TempCompass: Do Video LLMs Really Understand Videos?","version":3},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-05-17T02:46:16.632743Z"},"links":{"cited_paper":"/paper/2311.11865","citing_paper":"/paper/2403.00476"},"observation_digest":"sha256:6427de029e3a39e289378b55705adf543ced2ce90c65d647dd614bc8c8f90eba","observation_id":"5d27f254-ae1b-4da7-acf1-08d58efeb77a","resolution":{"observed_at":"2026-05-17T02:46:16.726617Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11865","last_updated":"2023-11-20T16:02:10Z","snapshot_observed_at":"2026-08-09T17:05:39.480445Z","submitted_at":"2023-11-20T16:02:10Z","title":"VLM-Eval: A General Evaluation on Video Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11865","snapshot_observed_at":"2026-08-06T17:58:27.497281Z","title":"In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 22195–22206","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.09491","last_updated":"2025-07-13T04:44:57Z","snapshot_observed_at":"2026-08-07T08:24:47.947962Z","submitted_at":"2025-07-13T04:44:57Z","title":"GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T17:58:27.497281Z"},"links":{"cited_paper":"/paper/2311.11865","citing_paper":"/paper/2507.09491"},"observation_digest":"sha256:3b3bde87be829df59c29fc177ec9500d034d242faa7a3703308aef626759d5ed","observation_id":"2e9fe91c-3242-4a7e-84de-3a088856acb2","resolution":{"observed_at":"2026-08-06T17:58:27.497281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11865","last_updated":"2023-11-20T16:02:10Z","snapshot_observed_at":"2026-08-09T17:05:39.480445Z","submitted_at":"2023-11-20T16:02:10Z","title":"VLM-Eval: A General Evaluation on Video Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11865","snapshot_observed_at":"2026-08-04T13:54:18.667591Z","title":", Zhang , Y","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.24563","last_updated":"2026-07-15T12:54:15Z","snapshot_observed_at":"2026-08-08T23:25:33.156446Z","submitted_at":"2025-09-29T10:16:05Z","title":"NeMo: Needle in a Montage for Video-Language Understanding","version":3},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-04T13:54:18.667591Z"},"links":{"cited_paper":"/paper/2311.11865","citing_paper":"/paper/2509.24563"},"observation_digest":"sha256:756a257ef6b48166263cac7fe626827298c499c3157af17022c625198ac467e5","observation_id":"704f1686-453e-4a85-8545-8ef5ad8cd00c","resolution":{"observed_at":"2026-08-04T13:54:18.667591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11865","last_updated":"2023-11-20T16:02:10Z","snapshot_observed_at":"2026-08-09T17:05:39.480445Z","submitted_at":"2023-11-20T16:02:10Z","title":"VLM-Eval: A General Evaluation on Video Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11865","snapshot_observed_at":"2026-08-03T20:27:23.711376Z","title":"Vlm-eval: A general evaluation on video large language models.arXiv preprint arXiv:2311.11865, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.19995","last_updated":"2026-06-02T01:15:52Z","snapshot_observed_at":"2026-08-06T23:58:32.880799Z","submitted_at":"2025-11-25T07:00:42Z","title":"CREward: A Type-Specific Creativity Reward Model","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T20:27:23.711376Z"},"links":{"cited_paper":"/paper/2311.11865","citing_paper":"/paper/2511.19995"},"observation_digest":"sha256:aa98a245748590be1d3078743e94c5b752e48a14a9e2191de8e7adc06ba3af24","observation_id":"bb79e491-fe71-43e5-90c0-dee4fd2c2c01","resolution":{"observed_at":"2026-08-03T20:27:23.711376Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2311.11865/citation-record","integrity":"/paper/2311.11865/integrity","json":"/paper/2311.11865/citation-record.json","paper":"/paper/2311.11865"},"outbound":[],"paper":{"arxiv_id":"2311.11865","last_updated":"2023-11-20T16:02:10Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T17:05:39.480445Z","submitted_at":"2023-11-20T16:02:10Z","title":"VLM-Eval: A General Evaluation on Video Large 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2311.11865."}