{"as_of":"2026-08-04T18:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7f1bde97a93ebbd0adfeb1c318ae5b209300e1b6987184befa5d9fe9ecdd5fd4","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":"2026-08-04T06:34:03.388597+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":"2026-05-24T09:02:31.211260Z","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":"2026-05-24T09:04:15.054398Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2302.00402","last_updated":"2023-02-01T12:40:03Z","snapshot_observed_at":"2026-07-06T14:47:00.945435Z","submitted_at":"2023-02-01T12:40:03Z","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","version":1},"cited_work":{"arxiv_id":"2302.00402","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.00402","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"mplug-2: A modularized multi-modal foundation model across text, image and video","venue":null,"work_id":"e48f6577-0181-4115-9570-ca671541d2a8","year":2023},"citing_paper":{"arxiv_id":"2304.14178","last_updated":"2024-03-29T08:13:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-27T13:27:01Z","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-24T09:02:31.211260Z"},"links":{"cited_paper":"/paper/2302.00402","citing_paper":"/paper/2304.14178"},"observation_digest":"sha256:6207b502cc1cc05c9bc9722255523e7e5c9425825dd5242489bf1a0d7bc689ff","observation_id":"71a320d5-2ef4-4aa6-a654-0a2a5620c7ba","resolution":{"observed_at":"2026-05-24T09:04:15.057623Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.00402","last_updated":"2023-02-01T12:40:03Z","snapshot_observed_at":"2026-07-06T14:47:00.945435Z","submitted_at":"2023-02-01T12:40:03Z","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","version":1},"cited_work":{"arxiv_id":"2302.00402","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.00402","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"mplug-2: A modularized multi-modal foundation model across text, image and video","venue":null,"work_id":"e48f6577-0181-4115-9570-ca671541d2a8","year":2023},"citing_paper":{"arxiv_id":"2307.06942","last_updated":"2024-01-04T05:00:34Z","snapshot_observed_at":"2026-07-06T15:53:46.393481Z","submitted_at":"2023-07-13T17:58:32Z","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-15T06:30:22.431538Z"},"links":{"cited_paper":"/paper/2302.00402","citing_paper":"/paper/2307.06942"},"observation_digest":"sha256:e74b7480afbf0ffa54d281e6deefa7c1085ce1d972faaec18aade61e1470190a","observation_id":"e8ea9a48-177e-4db5-a889-4efe78cf0f9f","resolution":{"observed_at":"2026-05-15T06:30:22.637374Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.00402","last_updated":"2023-02-01T12:40:03Z","snapshot_observed_at":"2026-07-06T14:47:00.945435Z","submitted_at":"2023-02-01T12:40:03Z","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","version":1},"cited_work":{"arxiv_id":"2302.00402","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.00402","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"mplug-2: A modularized multi-modal foundation model across text, image and video","venue":null,"work_id":"e48f6577-0181-4115-9570-ca671541d2a8","year":2023},"citing_paper":{"arxiv_id":"2402.17177","last_updated":"2024-04-17T18:41:39Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-02-27T03:30:58Z","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-13T13:43:11.024069Z"},"links":{"cited_paper":"/paper/2302.00402","citing_paper":"/paper/2402.17177"},"observation_digest":"sha256:8bceb5ea00424e9d4462bbfe77897a5b62d9fbf9ee3b057295905ddfaee0dbaa","observation_id":"e7eeb6d8-0493-448f-94ac-be651bd71be9","resolution":{"observed_at":"2026-05-13T13:43:11.158538Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2302.00402/citation-record","integrity":"/paper/2302.00402/integrity","json":"/paper/2302.00402/citation-record.json","paper":"/paper/2302.00402"},"outbound":[],"paper":{"arxiv_id":"2302.00402","last_updated":"2023-02-01T12:40:03Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T14:47:00.945435Z","submitted_at":"2023-02-01T12:40:03Z","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2302.00402."}