{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:642QPUQDZ6JUQB7UWGJPS5S57J","short_pith_number":"pith:642QPUQD","schema_version":"1.0","canonical_sha256":"f73507d203cf934807f4b192f9765dfa6f3b5ceafdf6a8c986d1d101a4318398","source":{"kind":"arxiv","id":"2510.08073","version":2},"attestation_state":"computed","paper":{"title":"Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Han, Daiyuan Li, Feng Liu, Guoxuan Pang, Jiahao Yang, Mingkui Tan, Shuhai Zhang, Shutao Li, ZiHao Lian","submitted_at":"2025-10-09T11:00:35Z","abstract_excerpt":"AI-generated videos have achieved near-perfect visual realism (e.g., Sora), urgently necessitating reliable detection mechanisms. However, detecting such videos faces significant challenges in modeling high-dimensional spatiotemporal dynamics and identifying subtle anomalies that violate physical laws. In this paper, we propose the first physics-driven AI-generated video detection paradigm based on probability flow conservation principles. Specifically, we propose a statistic called Normalized Spatiotemporal Gradient (NSG), which quantifies the ratio of spatial probability gradients to tempora"},"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":"2510.08073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-09T11:00:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"17ace5f1314a932370e22d2f042ce806ec93a65736ecbb2b385e0db541ff369a","abstract_canon_sha256":"5a85c078a5124402cd5708537e193b39c37e78f28d43aaa801f81ac0d942d185"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:19.764386Z","signature_b64":"nSdrGPtD/8kdCC42+NJiJpjcVg1fqzf3mk3Kzgo7XTnmZJbHAJ86tH7VDE/hoXoMfuTk8Q/6F3LZPS4ungm+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f73507d203cf934807f4b192f9765dfa6f3b5ceafdf6a8c986d1d101a4318398","last_reissued_at":"2026-06-11T01:09:19.763398Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:19.763398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Han, Daiyuan Li, Feng Liu, Guoxuan Pang, Jiahao Yang, Mingkui Tan, Shuhai Zhang, Shutao Li, ZiHao Lian","submitted_at":"2025-10-09T11:00:35Z","abstract_excerpt":"AI-generated videos have achieved near-perfect visual realism (e.g., Sora), urgently necessitating reliable detection mechanisms. However, detecting such videos faces significant challenges in modeling high-dimensional spatiotemporal dynamics and identifying subtle anomalies that violate physical laws. In this paper, we propose the first physics-driven AI-generated video detection paradigm based on probability flow conservation principles. Specifically, we propose a statistic called Normalized Spatiotemporal Gradient (NSG), which quantifies the ratio of spatial probability gradients to tempora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.08073","kind":"arxiv","version":2},"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/2510.08073/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":"2510.08073","created_at":"2026-06-11T01:09:19.763565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.08073v2","created_at":"2026-06-11T01:09:19.763565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.08073","created_at":"2026-06-11T01:09:19.763565+00:00"},{"alias_kind":"pith_short_12","alias_value":"642QPUQDZ6JU","created_at":"2026-06-11T01:09:19.763565+00:00"},{"alias_kind":"pith_short_16","alias_value":"642QPUQDZ6JUQB7U","created_at":"2026-06-11T01:09:19.763565+00:00"},{"alias_kind":"pith_short_8","alias_value":"642QPUQD","created_at":"2026-06-11T01:09:19.763565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2512.15693","citing_title":"Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17133","citing_title":"CAM-VFD: Cross-Attention Multimodal Video Forgery Detection","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10248","citing_title":"RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09296","citing_title":"Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04608","citing_title":"Beyond Semantics: Uncovering the Physics of Fakes via Universal Physical Descriptors for Cross-Modal Synthetic Detection","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J","json":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J.json","graph_json":"https://pith.science/api/pith-number/642QPUQDZ6JUQB7UWGJPS5S57J/graph.json","events_json":"https://pith.science/api/pith-number/642QPUQDZ6JUQB7UWGJPS5S57J/events.json","paper":"https://pith.science/paper/642QPUQD"},"agent_actions":{"view_html":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J","download_json":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J.json","view_paper":"https://pith.science/paper/642QPUQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.08073&json=true","fetch_graph":"https://pith.science/api/pith-number/642QPUQDZ6JUQB7UWGJPS5S57J/graph.json","fetch_events":"https://pith.science/api/pith-number/642QPUQDZ6JUQB7UWGJPS5S57J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J/action/storage_attestation","attest_author":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J/action/author_attestation","sign_citation":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J/action/citation_signature","submit_replication":"https://pith.science/pith/642QPUQDZ6JUQB7UWGJPS5S57J/action/replication_record"}},"created_at":"2026-06-11T01:09:19.763565+00:00","updated_at":"2026-06-11T01:09:19.763565+00:00"}