{"as_of":"2026-08-22T22:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:876041c1ad7e614e0b0eb658e5e10e992fdbb47f9ca0b1028e90c51d34272b01","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":"2026-08-22T06:32:14.747728+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":"2026-08-07T13:21:47.964071Z","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":"2026-07-01T07:55:31.527442Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.13133","last_updated":"2025-02-18T18:56:18Z","snapshot_observed_at":"2026-08-20T04:14:57.634507Z","submitted_at":"2025-02-18T18:56:18Z","title":"AV-Flow: Transforming Text to Audio-Visual Human-like Interactions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13133","snapshot_observed_at":"2026-08-07T13:21:47.964071Z","title":"Av-flow: Transforming text to audio-visual human-like interactions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22141","last_updated":"2025-08-27T16:33:34Z","snapshot_observed_at":"2026-08-10T20:19:26.392892Z","submitted_at":"2025-05-28T09:04:00Z","title":"FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:47.964071Z"},"links":{"cited_paper":"/paper/2502.13133","citing_paper":"/paper/2505.22141"},"observation_digest":"sha256:1f732382f203f535bcbb8cf69996c9ec1541b42cf2626dae693862bb7b4847f0","observation_id":"0d981bfc-00cc-4c23-862a-28705f7c20a0","resolution":{"observed_at":"2026-08-07T13:21:47.964071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13133","last_updated":"2025-02-18T18:56:18Z","snapshot_observed_at":"2026-08-20T04:14:57.634507Z","submitted_at":"2025-02-18T18:56:18Z","title":"AV-Flow: Transforming Text to Audio-Visual Human-like Interactions","version":1},"cited_work":{"arxiv_id":"2502.13133","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.13133","snapshot_observed_at":"2026-07-01T07:55:31.527442Z","title":"A V-Flow: Transforming text to audio-visual human-like interactions.arXiv preprint arXiv:2502.13133","venue":null,"work_id":"3bd55284-8be5-452f-b23a-03450f21be88","year":null},"citing_paper":{"arxiv_id":"2511.01233","last_updated":"2026-04-22T07:05:26Z","snapshot_observed_at":"2026-08-11T18:09:42.207312Z","submitted_at":"2025-11-03T05:17:28Z","title":"Towards Reliable Human Evaluations in Gesture Generation: Insights from a Community-Driven State-of-the-Art Benchmark","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-18T01:39:17.346513Z"},"links":{"cited_paper":"/paper/2502.13133","citing_paper":"/paper/2511.01233"},"observation_digest":"sha256:791451c5e34057df1aa2fe8c5577c113175c18c2efac62c8d567bac74da26d0a","observation_id":"255366d5-5c74-49cd-a2f4-fde625231cd6","resolution":{"observed_at":"2026-05-18T01:40:37.038974Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13133","last_updated":"2025-02-18T18:56:18Z","snapshot_observed_at":"2026-08-20T04:14:57.634507Z","submitted_at":"2025-02-18T18:56:18Z","title":"AV-Flow: Transforming Text to Audio-Visual Human-like Interactions","version":1},"cited_work":{"arxiv_id":"2502.13133","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.13133","snapshot_observed_at":"2026-07-01T07:55:31.527442Z","title":"A V-Flow: Transforming text to audio-visual human-like interactions.arXiv preprint arXiv:2502.13133","venue":null,"work_id":"3bd55284-8be5-452f-b23a-03450f21be88","year":null},"citing_paper":{"arxiv_id":"2606.30662","last_updated":"2026-06-17T07:01:20Z","snapshot_observed_at":"2026-08-14T13:01:26.831157Z","submitted_at":"2026-06-17T07:01:20Z","title":"ELEVATE: Designing Human-Centered GenAI Virtual Tutors for Scalable and Inclusive Education","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-07-01T07:45:22.445395Z"},"links":{"cited_paper":"/paper/2502.13133","citing_paper":"/paper/2606.30662"},"observation_digest":"sha256:dbfd5fbfb0a252ef8f71718c2615f43b46c42adb0f38728375fcdef8de61256d","observation_id":"ef434461-ae67-40e7-a931-daac2b31ba05","resolution":{"observed_at":"2026-07-01T07:55:31.529678Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.13133/citation-record","integrity":"/paper/2502.13133/integrity","json":"/paper/2502.13133/citation-record.json","paper":"/paper/2502.13133"},"outbound":[],"paper":{"arxiv_id":"2502.13133","last_updated":"2025-02-18T18:56:18Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-20T04:14:57.634507Z","submitted_at":"2025-02-18T18:56:18Z","title":"AV-Flow: Transforming Text to Audio-Visual Human-like Interactions"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2502.13133."}