{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JBQPEATEMZOAPL536YH2R4RJJ6","short_pith_number":"pith:JBQPEATE","schema_version":"1.0","canonical_sha256":"4860f20264665c07afbbf60fa8f2294f87a3b15af7fe5214571ff4f9cd01803f","source":{"kind":"arxiv","id":"2402.00126","version":2},"attestation_state":"computed","paper":{"title":"Common Sense Reasoning for Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ali Shahriyari, Ben Colman, Gaurav Bharaj, Xiao Guo, Yue Zhang","submitted_at":"2024-01-31T19:11:58Z","abstract_excerpt":"State-of-the-art deepfake detection approaches rely on image-based features extracted via neural networks. While these approaches trained in a supervised manner extract likely fake features, they may fall short in representing unnatural `non-physical' semantic facial attributes -- blurry hairlines, double eyebrows, rigid eye pupils, or unnatural skin shading. However, such facial attributes are easily perceived by humans and used to discern the authenticity of an image based on human common sense. Furthermore, image-based feature extraction methods that provide visual explanations via saliency"},"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":"2402.00126","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T19:11:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9e1c6dd045034b577010693bf2ff2aedab5fd7acfee153b4ef1e468e492b87dc","abstract_canon_sha256":"2e1dfeed7f99a4cb62f9e6c7c2c22e0f29eb0c8c052a47a51127897d006ee7d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:24.864283Z","signature_b64":"pxqS/C/Po1LNwNguytz1kBC1RlhXuB/gH1PWaiTILqaMvanBwm3vBuq8Cu2JsiJLesS7+YCDodgwfhYEtA6SAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4860f20264665c07afbbf60fa8f2294f87a3b15af7fe5214571ff4f9cd01803f","last_reissued_at":"2026-07-05T08:45:24.863843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:24.863843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Common Sense Reasoning for Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ali Shahriyari, Ben Colman, Gaurav Bharaj, Xiao Guo, Yue Zhang","submitted_at":"2024-01-31T19:11:58Z","abstract_excerpt":"State-of-the-art deepfake detection approaches rely on image-based features extracted via neural networks. While these approaches trained in a supervised manner extract likely fake features, they may fall short in representing unnatural `non-physical' semantic facial attributes -- blurry hairlines, double eyebrows, rigid eye pupils, or unnatural skin shading. However, such facial attributes are easily perceived by humans and used to discern the authenticity of an image based on human common sense. Furthermore, image-based feature extraction methods that provide visual explanations via saliency"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00126","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/2402.00126/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":"2402.00126","created_at":"2026-07-05T08:45:24.863896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00126v2","created_at":"2026-07-05T08:45:24.863896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00126","created_at":"2026-07-05T08:45:24.863896+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBQPEATEMZOA","created_at":"2026-07-05T08:45:24.863896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBQPEATEMZOAPL53","created_at":"2026-07-05T08:45:24.863896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBQPEATE","created_at":"2026-07-05T08:45:24.863896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26552","citing_title":"Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31192","citing_title":"The Regularizing Power of Language-Training Deepfake Detectors","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10071","citing_title":"MFVLR: Multi-domain Fine-grained Vision-Language Reconstruction for Generalizable Diffusion Face Forgery Detection and Localization","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6","json":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6.json","graph_json":"https://pith.science/api/pith-number/JBQPEATEMZOAPL536YH2R4RJJ6/graph.json","events_json":"https://pith.science/api/pith-number/JBQPEATEMZOAPL536YH2R4RJJ6/events.json","paper":"https://pith.science/paper/JBQPEATE"},"agent_actions":{"view_html":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6","download_json":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6.json","view_paper":"https://pith.science/paper/JBQPEATE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00126&json=true","fetch_graph":"https://pith.science/api/pith-number/JBQPEATEMZOAPL536YH2R4RJJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/JBQPEATEMZOAPL536YH2R4RJJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6/action/storage_attestation","attest_author":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6/action/author_attestation","sign_citation":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6/action/citation_signature","submit_replication":"https://pith.science/pith/JBQPEATEMZOAPL536YH2R4RJJ6/action/replication_record"}},"created_at":"2026-07-05T08:45:24.863896+00:00","updated_at":"2026-07-05T08:45:24.863896+00:00"}