{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:STIAK5Y3KTND4HI3AS2YUWFU33","short_pith_number":"pith:STIAK5Y3","schema_version":"1.0","canonical_sha256":"94d005771b54da3e1d1b04b58a58b4defe6b2347929ecffc83baa5669fd1ac9c","source":{"kind":"arxiv","id":"2403.16638","version":1},"attestation_state":"computed","paper":{"title":"AI-Generated Video Detection via Spatio-Temporal Anomaly Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Gang Cao, Jianfa Bai, Man Lin","submitted_at":"2024-03-25T11:26:18Z","abstract_excerpt":"The advancement of generation models has led to the emergence of highly realistic artificial intelligence (AI)-generated videos. Malicious users can easily create non-existent videos to spread false information. This letter proposes an effective AI-generated video detection (AIGVDet) scheme by capturing the forensic traces with a two-branch spatio-temporal convolutional neural network (CNN). Specifically, two ResNet sub-detectors are learned separately for identifying the anomalies in spatical and optical flow domains, respectively. Results of such sub-detectors are fused to further enhance th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.16638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T11:26:18Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"5a86e2d6e37861ca4dade1b16bfb676000f6356caab46b061fa3afe2a6fd843e","abstract_canon_sha256":"fff383cf21f4cc37095d0d0e05c23597bf5db0e50584468b811135e46c64358a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:19.119472Z","signature_b64":"5YKuE2w07H4q9amt3yAJ0J++hwimkBeqYL2VFVKew/PAVx4SA7MLghbePjP9AKK0ysGZYkhicII8HEFxbiFHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94d005771b54da3e1d1b04b58a58b4defe6b2347929ecffc83baa5669fd1ac9c","last_reissued_at":"2026-07-05T08:00:19.119048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:19.119048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI-Generated Video Detection via Spatio-Temporal Anomaly Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Gang Cao, Jianfa Bai, Man Lin","submitted_at":"2024-03-25T11:26:18Z","abstract_excerpt":"The advancement of generation models has led to the emergence of highly realistic artificial intelligence (AI)-generated videos. Malicious users can easily create non-existent videos to spread false information. This letter proposes an effective AI-generated video detection (AIGVDet) scheme by capturing the forensic traces with a two-branch spatio-temporal convolutional neural network (CNN). Specifically, two ResNet sub-detectors are learned separately for identifying the anomalies in spatical and optical flow domains, respectively. Results of such sub-detectors are fused to further enhance th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16638","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.16638/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.16638","created_at":"2026-07-05T08:00:19.119103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16638v1","created_at":"2026-07-05T08:00:19.119103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16638","created_at":"2026-07-05T08:00:19.119103+00:00"},{"alias_kind":"pith_short_12","alias_value":"STIAK5Y3KTND","created_at":"2026-07-05T08:00:19.119103+00:00"},{"alias_kind":"pith_short_16","alias_value":"STIAK5Y3KTND4HI3","created_at":"2026-07-05T08:00:19.119103+00:00"},{"alias_kind":"pith_short_8","alias_value":"STIAK5Y3","created_at":"2026-07-05T08:00:19.119103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20103","citing_title":"BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33","json":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33.json","graph_json":"https://pith.science/api/pith-number/STIAK5Y3KTND4HI3AS2YUWFU33/graph.json","events_json":"https://pith.science/api/pith-number/STIAK5Y3KTND4HI3AS2YUWFU33/events.json","paper":"https://pith.science/paper/STIAK5Y3"},"agent_actions":{"view_html":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33","download_json":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33.json","view_paper":"https://pith.science/paper/STIAK5Y3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16638&json=true","fetch_graph":"https://pith.science/api/pith-number/STIAK5Y3KTND4HI3AS2YUWFU33/graph.json","fetch_events":"https://pith.science/api/pith-number/STIAK5Y3KTND4HI3AS2YUWFU33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33/action/storage_attestation","attest_author":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33/action/author_attestation","sign_citation":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33/action/citation_signature","submit_replication":"https://pith.science/pith/STIAK5Y3KTND4HI3AS2YUWFU33/action/replication_record"}},"created_at":"2026-07-05T08:00:19.119103+00:00","updated_at":"2026-07-05T08:00:19.119103+00:00"}