{"as_of":"2026-08-19T09:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a75490cf69dba5af602b22f2827154e4be7dc8907f9afbf5cd35133015a9fdef","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":"2026-08-19T06:32:44.657259+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":"2026-08-16T10:51:00.644261Z","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":"2026-05-15T16:06:14.433448Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.10656","last_updated":"2023-12-19T13:54:15Z","snapshot_observed_at":"2026-08-18T09:44:11.389351Z","submitted_at":"2023-12-17T09:05:56Z","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10656","snapshot_observed_at":"2026-08-10T21:35:41.971739Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.04606","last_updated":"2025-06-11T04:23:47Z","snapshot_observed_at":"2026-08-16T00:28:07.895058Z","submitted_at":"2025-01-08T16:41:31Z","title":"Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:35:41.971739Z"},"links":{"cited_paper":"/paper/2312.10656","citing_paper":"/paper/2501.04606"},"observation_digest":"sha256:e37474ebc7e8b1d77fd88c98fe21ee742989a136ad0069b8753f76d6610922d7","observation_id":"70be48f4-3b51-4af8-8727-d8e0b7d0d921","resolution":{"observed_at":"2026-08-10T21:35:41.971739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10656","last_updated":"2023-12-19T13:54:15Z","snapshot_observed_at":"2026-08-18T09:44:11.389351Z","submitted_at":"2023-12-17T09:05:56Z","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10656","snapshot_observed_at":"2026-08-10T18:53:00.127384Z","title":"Vidtome: Video token merging for zero-shot video editing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.10928","last_updated":"2025-04-19T14:52:08Z","snapshot_observed_at":"2026-08-10T18:47:01.186615Z","submitted_at":"2025-01-19T03:19:47Z","title":"Generative Physical AI in Vision: A Survey","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T18:53:00.127384Z"},"links":{"cited_paper":"/paper/2312.10656","citing_paper":"/paper/2501.10928"},"observation_digest":"sha256:fa20d96f5b2a2086b743c9cc217b7f973a93c8aebe538042ee49b606a73baf0b","observation_id":"43492200-38ef-4a43-b753-506ecf566cf4","resolution":{"observed_at":"2026-08-10T18:53:00.127384Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10656","last_updated":"2023-12-19T13:54:15Z","snapshot_observed_at":"2026-08-18T09:44:11.389351Z","submitted_at":"2023-12-17T09:05:56Z","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10656","snapshot_observed_at":"2026-08-16T10:51:00.644261Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.17269","last_updated":"2025-07-01T14:10:46Z","snapshot_observed_at":"2026-08-17T12:09:08.463793Z","submitted_at":"2025-04-24T05:54:56Z","title":"Towards Generalized and Training-Free Text-Guided Semantic Manipulation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T10:51:00.644261Z"},"links":{"cited_paper":"/paper/2312.10656","citing_paper":"/paper/2504.17269"},"observation_digest":"sha256:e13fc4e7a0d9f4ade06baf8989d571c93a6913b9997681a685bc7b7b69a8e521","observation_id":"7b1e0f0b-5ecd-4426-8167-9869aeb63423","resolution":{"observed_at":"2026-08-16T10:51:00.644261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10656","last_updated":"2023-12-19T13:54:15Z","snapshot_observed_at":"2026-08-18T09:44:11.389351Z","submitted_at":"2023-12-17T09:05:56Z","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","version":2},"cited_work":{"arxiv_id":"2312.10656","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.10656","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arxiv:2312.10656 (2023)","venue":null,"work_id":"a3440663-577e-4e0b-a0a7-9814e0eb658f","year":2023},"citing_paper":{"arxiv_id":"2603.05811","last_updated":"2026-04-28T22:44:43Z","snapshot_observed_at":"2026-08-13T20:50:15.487718Z","submitted_at":"2026-03-06T01:49:47Z","title":"Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-15T16:05:36.307084Z"},"links":{"cited_paper":"/paper/2312.10656","citing_paper":"/paper/2603.05811"},"observation_digest":"sha256:64d8aa204fd81ca5e8c03c28cc06822740e1c7208d2f7d513924a163d75d1a47","observation_id":"d2a58e5d-3a1c-4a1c-995c-e1370b6ed4f2","resolution":{"observed_at":"2026-05-15T16:06:14.436548Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.10656/citation-record","integrity":"/paper/2312.10656/integrity","json":"/paper/2312.10656/citation-record.json","paper":"/paper/2312.10656"},"outbound":[],"paper":{"arxiv_id":"2312.10656","last_updated":"2023-12-19T13:54:15Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T09:44:11.389351Z","submitted_at":"2023-12-17T09:05:56Z","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2312.10656."}