{"as_of":"2026-08-07T19:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:444fe7fa0b61831113c925ffa8f039cc362dde3a506cfa526490f34be342b3a0","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T16:23:41.993429Z","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":"2026-05-13T13:43:11.290566Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.10226","last_updated":"2024-10-01T05:58:37Z","snapshot_observed_at":"2026-07-06T17:17:31.008185Z","submitted_at":"2024-01-18T18:59:13Z","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","version":2},"cited_work":{"arxiv_id":"2401.10226","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.10226","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"To- wards language-driven video inpainting via multimodal large language models","venue":null,"work_id":"d54551df-b87e-426b-9e5a-e6703f13320e","year":2024},"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":200,"source":"pdf_text","source_observed_at":"2026-05-13T13:43:11.024069Z"},"links":{"cited_paper":"/paper/2401.10226","citing_paper":"/paper/2402.17177"},"observation_digest":"sha256:5225e4ff1ccd6d05e01f478adab688c23ca112e8d4deb3b48fdbd76222b3eaa8","observation_id":"e365d2b1-2942-4066-baca-6498d079bb32","resolution":{"observed_at":"2026-05-13T13:43:11.292077Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.10226","last_updated":"2024-10-01T05:58:37Z","snapshot_observed_at":"2026-07-06T17:17:31.008185Z","submitted_at":"2024-01-18T18:59:13Z","title":"Towards Language-Driven Video Inpainting via Multimodal Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.10226","snapshot_observed_at":"2026-08-05T16:23:41.993429Z","title":"Towards language-driven video inpainting via multimodal large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.18633","last_updated":"2025-08-26T03:18:31Z","snapshot_observed_at":"2026-08-05T16:23:35.382635Z","submitted_at":"2025-08-26T03:18:31Z","title":"ROSE: Remove Objects with Side Effects in Videos","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T16:23:41.993429Z"},"links":{"cited_paper":"/paper/2401.10226","citing_paper":"/paper/2508.18633"},"observation_digest":"sha256:05aa3c31b8f8999f66468d5880b0be74aa4d7f6fb1ffaf1474572e444266db8a","observation_id":"9275bdbb-3657-4f5b-aaa7-354279306029","resolution":{"observed_at":"2026-08-05T16:23:41.993429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2401.10226/citation-record","integrity":"/paper/2401.10226/integrity","json":"/paper/2401.10226/citation-record.json","paper":"/paper/2401.10226"},"outbound":[],"paper":{"arxiv_id":"2401.10226","last_updated":"2024-10-01T05:58:37Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:17:31.008185Z","submitted_at":"2024-01-18T18:59:13Z","title":"Towards Language-Driven Video Inpainting via Multimodal 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2401.10226."}