{"as_of":"2026-08-07T23:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2290218d17eefcac2aed95ef9a4c783b5847ffeb985f54eff09e7c5bbf5e5224","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T13:21:48.225801Z","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":"2026-05-11T17:06:04.186716Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.02542","last_updated":"2025-04-07T09:32:46Z","snapshot_observed_at":"2026-08-07T16:11:41.005225Z","submitted_at":"2025-04-03T12:44:41Z","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02542","snapshot_observed_at":"2026-08-07T13:21:48.225801Z","title":"Audio-visual controlled video diffusion with masked selective state spaces modeling for natural talking head generation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22141","last_updated":"2025-08-27T16:33:34Z","snapshot_observed_at":"2026-08-07T20:49:32.346427Z","submitted_at":"2025-05-28T09:04:00Z","title":"FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:48.225801Z"},"links":{"cited_paper":"/paper/2504.02542","citing_paper":"/paper/2505.22141"},"observation_digest":"sha256:33c9841afe607d8bd1354d70edf76223e9221d1e07079cac19fb2c07ed51717b","observation_id":"cbc3f914-32d9-48ae-90f3-84d21e7d19d5","resolution":{"observed_at":"2026-08-07T13:21:48.225801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02542","last_updated":"2025-04-07T09:32:46Z","snapshot_observed_at":"2026-08-07T16:11:41.005225Z","submitted_at":"2025-04-03T12:44:41Z","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02542","snapshot_observed_at":"2026-08-06T19:38:20.474478Z","title":"Audio-visual con- trolled video diffusion with masked selective state spaces modeling for natural talking head generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.05092","last_updated":"2025-07-07T15:13:46Z","snapshot_observed_at":"2026-08-07T20:50:59.824621Z","submitted_at":"2025-07-07T15:13:46Z","title":"MoDiT: Learning Highly Consistent 3D Motion Coefficients with Diffusion Transformer for Talking Head Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:38:20.474478Z"},"links":{"cited_paper":"/paper/2504.02542","citing_paper":"/paper/2507.05092"},"observation_digest":"sha256:7971f705afe638eaaa699da99827fb8c85073883ef51a738ed64d611e97a5840","observation_id":"aa640803-062e-4a2a-9704-f5eec816209f","resolution":{"observed_at":"2026-08-06T19:38:20.474478Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02542","last_updated":"2025-04-07T09:32:46Z","snapshot_observed_at":"2026-08-07T16:11:41.005225Z","submitted_at":"2025-04-03T12:44:41Z","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation","version":3},"cited_work":{"arxiv_id":"2504.02542","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.02542","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Audio-visual con- trolled video diffusion with masked selective state spaces modeling for natural talking head generation","venue":null,"work_id":"ba649907-da24-4054-b28b-68c090cfb342","year":2025},"citing_paper":{"arxiv_id":"2605.01638","last_updated":"2026-05-02T22:56:17Z","snapshot_observed_at":"2026-07-06T23:14:47.444386Z","submitted_at":"2026-05-02T22:56:17Z","title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-09T14:04:52.065878Z"},"links":{"cited_paper":"/paper/2504.02542","citing_paper":"/paper/2605.01638"},"observation_digest":"sha256:3ddf336cc09a31cd0174f9b30406bfda4b631d4bcc6bd663e24b5a52d76b9775","observation_id":"3d0cca68-d6de-419f-aec7-2385b6d73fe2","resolution":{"observed_at":"2026-05-11T17:06:04.189108Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2504.02542/citation-record","integrity":"/paper/2504.02542/integrity","json":"/paper/2504.02542/citation-record.json","paper":"/paper/2504.02542"},"outbound":[],"paper":{"arxiv_id":"2504.02542","last_updated":"2025-04-07T09:32:46Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:11:41.005225Z","submitted_at":"2025-04-03T12:44:41Z","title":"Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation"},"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 3 inbound Pith citation observations for arXiv:2504.02542."}