{"as_of":"2026-08-12T16:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:84715933ade864175f3abd6776d1a872e1fbe5d272f4c2bfdb1b16a7b75b041f","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":"2026-08-12T06:34:41.77262+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":"2026-08-12T05:16:59.667873Z","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":"2026-08-06T21:12:06.327198Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.07356","last_updated":"2025-03-19T10:22:15Z","snapshot_observed_at":"2026-08-12T15:39:28.153284Z","submitted_at":"2024-07-10T04:27:06Z","title":"Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07356","snapshot_observed_at":"2026-08-12T05:16:59.667873Z","title":"Video in-context learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.00596","last_updated":"2025-04-01T09:33:55Z","snapshot_observed_at":"2026-08-12T11:08:40.105379Z","submitted_at":"2024-11-30T22:02:12Z","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T05:16:59.667873Z"},"links":{"cited_paper":"/paper/2407.07356","citing_paper":"/paper/2412.00596"},"observation_digest":"sha256:d3c5502079f0aabd82d3b2fcee3331919358f3100c3aaea9aecacf240ece5885","observation_id":"6632e14c-239c-49c3-9542-0c5c148cc6dd","resolution":{"observed_at":"2026-08-12T05:16:59.667873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07356","last_updated":"2025-03-19T10:22:15Z","snapshot_observed_at":"2026-08-12T15:39:28.153284Z","submitted_at":"2024-07-10T04:27:06Z","title":"Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07356","snapshot_observed_at":"2026-08-11T15:40:20.223009Z","title":"Video in-context learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.10783","last_updated":"2025-03-22T08:53:33Z","snapshot_observed_at":"2026-08-11T20:10:49.995786Z","submitted_at":"2024-12-14T10:39:55Z","title":"Video Diffusion Transformers are In-Context Learners","version":3},"reference_index":109,"source":"pdf_text","source_observed_at":"2026-08-11T15:40:20.223009Z"},"links":{"cited_paper":"/paper/2407.07356","citing_paper":"/paper/2412.10783"},"observation_digest":"sha256:b285319a6585dffc342b1c721668afe5d41795d17961361e2acf7b33bbba33e2","observation_id":"45693286-2936-4c0c-a737-5b6101cbd6d7","resolution":{"observed_at":"2026-08-11T15:40:20.223009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07356","last_updated":"2025-03-19T10:22:15Z","snapshot_observed_at":"2026-08-12T15:39:28.153284Z","submitted_at":"2024-07-10T04:27:06Z","title":"Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07356","snapshot_observed_at":"2026-08-11T13:30:23.560193Z","title":"Video in-context learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.13061","last_updated":"2024-12-17T16:27:11Z","snapshot_observed_at":"2026-08-12T11:08:41.222809Z","submitted_at":"2024-12-17T16:27:11Z","title":"VidTok: A Versatile and Open-Source Video Tokenizer","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-11T13:30:23.560193Z"},"links":{"cited_paper":"/paper/2407.07356","citing_paper":"/paper/2412.13061"},"observation_digest":"sha256:de905d906190ada73d4aab9d7b3b4660e0b97a2f0464dc7d2775e820ca002d58","observation_id":"26e6b10e-eba2-4e9f-b75a-467e885db8f3","resolution":{"observed_at":"2026-08-11T13:30:23.560193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07356","last_updated":"2025-03-19T10:22:15Z","snapshot_observed_at":"2026-08-12T15:39:28.153284Z","submitted_at":"2024-07-10T04:27:06Z","title":"Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators","version":2},"cited_work":{"arxiv_id":"2407.07356","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.07356","snapshot_observed_at":"2026-08-06T21:12:06.327198Z","title":"Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators","venue":"cs.CV","work_id":"18d42a9e-74d0-44ce-99d4-8519b92468fd","year":2024},"citing_paper":{"arxiv_id":"2507.00868","last_updated":"2025-07-02T09:16:31Z","snapshot_observed_at":"2026-08-12T15:53:05.644474Z","submitted_at":"2025-07-01T15:32:23Z","title":"Is Visual in-Context Learning for Compositional Medical Tasks within Reach?","version":2},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-06T21:12:06.151483Z"},"links":{"cited_paper":"/paper/2407.07356","citing_paper":"/paper/2507.00868"},"observation_digest":"sha256:5b01af1d1c4915e80c89702be43526e8b3950f21ae14cb7378aa8ff48445aa0c","observation_id":"5f6c9b9a-9a26-43a0-a67d-e1420e868bf5","resolution":{"observed_at":"2026-08-06T21:12:06.334449Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.07356/citation-record","integrity":"/paper/2407.07356/integrity","json":"/paper/2407.07356/citation-record.json","paper":"/paper/2407.07356"},"outbound":[],"paper":{"arxiv_id":"2407.07356","last_updated":"2025-03-19T10:22:15Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T15:39:28.153284Z","submitted_at":"2024-07-10T04:27:06Z","title":"Video In-context Learning: Autoregressive Transformers are Zero-Shot Video Imitators"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2407.07356."}