{"as_of":"2026-08-08T19:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3767041f6acbc24dee6a30977f3aa78986eebdeedae5d9db4cf3d70e4e0f6a70","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T14:27:11.072412Z","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":"2026-08-05T23:59:14.564678Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.09754","last_updated":"2025-04-03T14:52:24Z","snapshot_observed_at":"2026-08-08T13:57:39.347745Z","submitted_at":"2024-12-12T23:10:54Z","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09754","snapshot_observed_at":"2026-08-07T14:27:11.072412Z","title":"Vicas: A dataset for combining holistic and pixel-level video understanding using captions with grounded segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18816","last_updated":"2025-05-24T18:23:14Z","snapshot_observed_at":"2026-08-07T21:26:48.765722Z","submitted_at":"2025-05-24T18:23:14Z","title":"Reasoning Segmentation for Images and Videos: A Survey","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T14:27:11.072412Z"},"links":{"cited_paper":"/paper/2412.09754","citing_paper":"/paper/2505.18816"},"observation_digest":"sha256:9789c167cf03a19736cd6f1cb2215196879a8e8fe750e54d4975b1b9ad74c0a1","observation_id":"5104d3b1-8a63-48c0-bd05-b019af82bf66","resolution":{"observed_at":"2026-08-07T14:27:11.072412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09754","last_updated":"2025-04-03T14:52:24Z","snapshot_observed_at":"2026-08-08T13:57:39.347745Z","submitted_at":"2024-12-12T23:10:54Z","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09754","snapshot_observed_at":"2026-08-07T13:09:52.818163Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22627","last_updated":"2025-06-01T02:55:39Z","snapshot_observed_at":"2026-08-08T13:58:01.163947Z","submitted_at":"2025-05-28T17:45:55Z","title":"Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T13:09:52.818163Z"},"links":{"cited_paper":"/paper/2412.09754","citing_paper":"/paper/2505.22627"},"observation_digest":"sha256:cb9b587aaf3179a55dc0d76ef16f2632514afcffbb848f49324c7ccea2720d58","observation_id":"97e4b629-3eb7-46e6-8365-936fd6bbc686","resolution":{"observed_at":"2026-08-07T13:09:52.818163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09754","last_updated":"2025-04-03T14:52:24Z","snapshot_observed_at":"2026-08-08T13:57:39.347745Z","submitted_at":"2024-12-12T23:10:54Z","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.09754","snapshot_observed_at":"2026-08-07T10:27:26.747875Z","title":"Vicas: A dataset for combining holistic and pixel-level video understanding using captions with grounded segmentation.arXiv preprint arXiv:2412.09754, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05336","last_updated":"2025-07-05T11:38:26Z","snapshot_observed_at":"2026-08-08T13:58:02.206064Z","submitted_at":"2025-06-05T17:59:29Z","title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:27:26.747875Z"},"links":{"cited_paper":"/paper/2412.09754","citing_paper":"/paper/2506.05336"},"observation_digest":"sha256:5513b2f679959a96b6a85bdb7ab87322be053f2469be9cf0ab8322e67c721b3e","observation_id":"28c1eb74-7799-4472-83fb-94c29f173286","resolution":{"observed_at":"2026-08-07T10:27:26.747875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.09754","last_updated":"2025-04-03T14:52:24Z","snapshot_observed_at":"2026-08-08T13:57:39.347745Z","submitted_at":"2024-12-12T23:10:54Z","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","version":3},"cited_work":{"arxiv_id":"2412.09754","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.09754","snapshot_observed_at":"2026-08-05T23:59:14.564678Z","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","venue":"cs.CV","work_id":"4645774c-a0e4-4943-af29-61f6a7d8dd37","year":2024},"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":6,"source":"pdf_text","source_observed_at":"2026-08-05T23:59:08.911675Z"},"links":{"cited_paper":"/paper/2412.09754","citing_paper":"/paper/2508.04549"},"observation_digest":"sha256:d190240d09cd60828fcb76e35719075816f2041301d42f8b1cd2904c6c631955","observation_id":"19af39be-5fed-4716-8f46-c09c679da4b2","resolution":{"observed_at":"2026-08-05T23:59:14.681879Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.09754/citation-record","integrity":"/paper/2412.09754/integrity","json":"/paper/2412.09754/citation-record.json","paper":"/paper/2412.09754"},"outbound":[],"paper":{"arxiv_id":"2412.09754","last_updated":"2025-04-03T14:52:24Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T13:57:39.347745Z","submitted_at":"2024-12-12T23:10:54Z","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2412.09754."}