{"as_of":"2026-08-15T07:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:78b3171d79f57cb0ed941d3e2b3a824c64647ac9349a9826d80b4d45bbea0b12","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":"2026-08-15T06:32:42.880941+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":"2026-08-12T20:55:15.793378Z","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":"2026-08-12T05:44:30.363492Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.13103","last_updated":"2025-07-06T11:50:10Z","snapshot_observed_at":"2026-08-14T17:05:27.065660Z","submitted_at":"2023-10-19T19:01:26Z","title":"AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13103","snapshot_observed_at":"2026-08-12T20:55:15.793378Z","title":"Hashmi, S","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09266","last_updated":"2024-11-14T08:07:02Z","snapshot_observed_at":"2026-08-14T19:24:35.183686Z","submitted_at":"2024-11-14T08:07:02Z","title":"How Good is ChatGPT at Audiovisual Deepfake Detection: A Comparative Study of ChatGPT, AI Models and Human Perception","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T20:55:15.793378Z"},"links":{"cited_paper":"/paper/2310.13103","citing_paper":"/paper/2411.09266"},"observation_digest":"sha256:6fc7a9a241df98e390998ccfc3ca44f7473ea037e63c4e041e3fa099a46bd5b3","observation_id":"7fdbee84-db87-4647-8354-2b3e6304880f","resolution":{"observed_at":"2026-08-12T20:55:15.793378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13103","last_updated":"2025-07-06T11:50:10Z","snapshot_observed_at":"2026-08-14T17:05:27.065660Z","submitted_at":"2023-10-19T19:01:26Z","title":"AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection","version":2},"cited_work":{"arxiv_id":"2310.13103","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.13103","snapshot_observed_at":"2026-08-12T05:44:30.363492Z","title":"AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection","venue":"cs.CV","work_id":"38ad3a8c-ab5c-4938-914e-4efb3a34d968","year":2023},"citing_paper":{"arxiv_id":"2412.00175","last_updated":"2025-05-29T14:44:11Z","snapshot_observed_at":"2026-08-12T20:40:20.763413Z","submitted_at":"2024-11-29T18:58:20Z","title":"Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T05:44:29.979061Z"},"links":{"cited_paper":"/paper/2310.13103","citing_paper":"/paper/2412.00175"},"observation_digest":"sha256:30b46fc49f2245caced6702b532f6420cf8b72a3b97b9435645bff072e3a8b55","observation_id":"85c606d9-92f6-44ac-964a-1ca897a6c2f6","resolution":{"observed_at":"2026-08-12T05:44:30.367926Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.13103/citation-record","integrity":"/paper/2310.13103/integrity","json":"/paper/2310.13103/citation-record.json","paper":"/paper/2310.13103"},"outbound":[],"paper":{"arxiv_id":"2310.13103","last_updated":"2025-07-06T11:50:10Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T17:05:27.065660Z","submitted_at":"2023-10-19T19:01:26Z","title":"AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2310.13103."}