{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NII7H55Q3GABEW5GZGFSY35EIM","short_pith_number":"pith:NII7H55Q","schema_version":"1.0","canonical_sha256":"6a11f3f7b0d980125ba6c98b2c6fa4431a3d95f8c09ffbd0bc502633d7f076cf","source":{"kind":"arxiv","id":"2508.00701","version":2},"attestation_state":"computed","paper":{"title":"D3: Training-Free AI-Generated Video Detection Using Second-Order Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Shen, Chende Zheng, Chenhao Lin, Cong Wang, Le Yang, Minghui Yang, Ruiqi suo, Shuai Liu, Zhengyu Zhao","submitted_at":"2025-08-01T15:17:51Z","abstract_excerpt":"The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the dissemination of synthetic content. However, existing detection methodologies remain limited by their insufficient exploration of temporal artifacts in synthetic videos. To bridge this gap, we establish a theoretical framework through second-order dynamical analysis under Newtonian mechanics, subsequently extending the Second-order Central Difference features tailored for temporal artifact detection. Building on this theoretical"},"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":"2508.00701","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-01T15:17:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c209ab2a1336d31f8e2a1635095d3f50c3b360566b43cb89a37efd1abb00770f","abstract_canon_sha256":"ec33b2176c2c26c27bc1a6398ae3da8a092d947af6b5c41e5e4a9fbb49fd8054"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:28.211283Z","signature_b64":"moSKPByhEqF87GO+KJ/FMrYfjnw7vuOLcT1y83PuhLZMTzVYz8Qm6WHt/E0VSJqx3cYPH/AHF2gQFfiCPgO4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a11f3f7b0d980125ba6c98b2c6fa4431a3d95f8c09ffbd0bc502633d7f076cf","last_reissued_at":"2026-07-05T11:48:28.210777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:28.210777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D3: Training-Free AI-Generated Video Detection Using Second-Order Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Shen, Chende Zheng, Chenhao Lin, Cong Wang, Le Yang, Minghui Yang, Ruiqi suo, Shuai Liu, Zhengyu Zhao","submitted_at":"2025-08-01T15:17:51Z","abstract_excerpt":"The evolution of video generation techniques, such as Sora, has made it increasingly easy to produce high-fidelity AI-generated videos, raising public concern over the dissemination of synthetic content. However, existing detection methodologies remain limited by their insufficient exploration of temporal artifacts in synthetic videos. To bridge this gap, we establish a theoretical framework through second-order dynamical analysis under Newtonian mechanics, subsequently extending the Second-order Central Difference features tailored for temporal artifact detection. Building on this theoretical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00701","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/2508.00701/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":"2508.00701","created_at":"2026-07-05T11:48:28.210840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00701v2","created_at":"2026-07-05T11:48:28.210840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00701","created_at":"2026-07-05T11:48:28.210840+00:00"},{"alias_kind":"pith_short_12","alias_value":"NII7H55Q3GAB","created_at":"2026-07-05T11:48:28.210840+00:00"},{"alias_kind":"pith_short_16","alias_value":"NII7H55Q3GABEW5G","created_at":"2026-07-05T11:48:28.210840+00:00"},{"alias_kind":"pith_short_8","alias_value":"NII7H55Q","created_at":"2026-07-05T11:48:28.210840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04706","citing_title":"ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02402","citing_title":"Explainable Forensics of Manipulated Segments in Untrimmed Long Videos","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17311","citing_title":"SpecSem-Net: Integrating Spectral and Semantic Features for Robust AI-generated Video Detection","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10248","citing_title":"RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM","json":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM.json","graph_json":"https://pith.science/api/pith-number/NII7H55Q3GABEW5GZGFSY35EIM/graph.json","events_json":"https://pith.science/api/pith-number/NII7H55Q3GABEW5GZGFSY35EIM/events.json","paper":"https://pith.science/paper/NII7H55Q"},"agent_actions":{"view_html":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM","download_json":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM.json","view_paper":"https://pith.science/paper/NII7H55Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00701&json=true","fetch_graph":"https://pith.science/api/pith-number/NII7H55Q3GABEW5GZGFSY35EIM/graph.json","fetch_events":"https://pith.science/api/pith-number/NII7H55Q3GABEW5GZGFSY35EIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM/action/storage_attestation","attest_author":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM/action/author_attestation","sign_citation":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM/action/citation_signature","submit_replication":"https://pith.science/pith/NII7H55Q3GABEW5GZGFSY35EIM/action/replication_record"}},"created_at":"2026-07-05T11:48:28.210840+00:00","updated_at":"2026-07-05T11:48:28.210840+00:00"}