{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OKRC7RHVZSLEWUDM2PXVOQOR6X","short_pith_number":"pith:OKRC7RHV","schema_version":"1.0","canonical_sha256":"72a22fc4f5cc964b506cd3ef5741d1f5e15a86a8d9b673f7a0182e2fe4ac9c01","source":{"kind":"arxiv","id":"2407.10550","version":1},"attestation_state":"computed","paper":{"title":"Learning Natural Consistency Representation for Face Forgery Video Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Zhang, Fanzhao Lin, Jianmin Li, Shikun Li, Shiming Ge, Zihao Xiao","submitted_at":"2024-07-15T09:00:02Z","abstract_excerpt":"Face Forgery videos have elicited critical social public concerns and various detectors have been proposed. However, fully-supervised detectors may lead to easily overfitting to specific forgery methods or videos, and existing self-supervised detectors are strict on auxiliary tasks, such as requiring audio or multi-modalities, leading to limited generalization and robustness. In this paper, we examine whether we can address this issue by leveraging visual-only real face videos. To this end, we propose to learn the Natural Consistency representation (NACO) of real face videos in a self-supervis"},"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":"2407.10550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-15T09:00:02Z","cross_cats_sorted":[],"title_canon_sha256":"9eb076bcdcbc80cfb4c02e54b1db6ccf337b3173391fd625fe75ab49b1d6341c","abstract_canon_sha256":"e00fd514d0d253d0bdd00b34588e1c9096826799bec671be0f64312000bff131"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:00.977737Z","signature_b64":"8Awhdij/C3wGPaVLdMZfxk0tb/EEXqCVp9GMkjivppvUy/3lrcrnExaAD7ED9ideHkrb2yRYetab0BcEJQo1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72a22fc4f5cc964b506cd3ef5741d1f5e15a86a8d9b673f7a0182e2fe4ac9c01","last_reissued_at":"2026-07-05T08:44:00.977305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:00.977305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Natural Consistency Representation for Face Forgery Video Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Zhang, Fanzhao Lin, Jianmin Li, Shikun Li, Shiming Ge, Zihao Xiao","submitted_at":"2024-07-15T09:00:02Z","abstract_excerpt":"Face Forgery videos have elicited critical social public concerns and various detectors have been proposed. However, fully-supervised detectors may lead to easily overfitting to specific forgery methods or videos, and existing self-supervised detectors are strict on auxiliary tasks, such as requiring audio or multi-modalities, leading to limited generalization and robustness. In this paper, we examine whether we can address this issue by leveraging visual-only real face videos. To this end, we propose to learn the Natural Consistency representation (NACO) of real face videos in a self-supervis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10550","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/2407.10550/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":"2407.10550","created_at":"2026-07-05T08:44:00.977371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10550v1","created_at":"2026-07-05T08:44:00.977371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10550","created_at":"2026-07-05T08:44:00.977371+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKRC7RHVZSLE","created_at":"2026-07-05T08:44:00.977371+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKRC7RHVZSLEWUDM","created_at":"2026-07-05T08:44:00.977371+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKRC7RHV","created_at":"2026-07-05T08:44:00.977371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17573","citing_title":"Deepfake Detection in Social Media: A Temporal Artifact Analysis Using 3D Convolutional Neural Networks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X","json":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X.json","graph_json":"https://pith.science/api/pith-number/OKRC7RHVZSLEWUDM2PXVOQOR6X/graph.json","events_json":"https://pith.science/api/pith-number/OKRC7RHVZSLEWUDM2PXVOQOR6X/events.json","paper":"https://pith.science/paper/OKRC7RHV"},"agent_actions":{"view_html":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X","download_json":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X.json","view_paper":"https://pith.science/paper/OKRC7RHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10550&json=true","fetch_graph":"https://pith.science/api/pith-number/OKRC7RHVZSLEWUDM2PXVOQOR6X/graph.json","fetch_events":"https://pith.science/api/pith-number/OKRC7RHVZSLEWUDM2PXVOQOR6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X/action/storage_attestation","attest_author":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X/action/author_attestation","sign_citation":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X/action/citation_signature","submit_replication":"https://pith.science/pith/OKRC7RHVZSLEWUDM2PXVOQOR6X/action/replication_record"}},"created_at":"2026-07-05T08:44:00.977371+00:00","updated_at":"2026-07-05T08:44:00.977371+00:00"}