{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D77CHGWAGKDAOMQLBTUWKGMS2A","short_pith_number":"pith:D77CHGWA","schema_version":"1.0","canonical_sha256":"1ffe239ac0328607320b0ce9651992d02f9670dbaf438a92fff4cdbb10a6eb54","source":{"kind":"arxiv","id":"2401.13516","version":5},"attestation_state":"computed","paper":{"title":"Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Difei Gao, Juan Hu, Mike Zheng Shou, Qian Wang, Satoshi Tsutsui, Xin Liao, Zheng Qin","submitted_at":"2024-01-24T15:14:05Z","abstract_excerpt":"Deepfake videos are becoming increasingly realistic, showing few tampering traces on facial areasthat vary between frames. Consequently, existing Deepfake detection methods struggle to detect unknown domain Deepfake videos while accurately locating the tampered region. To address thislimitation, we propose Delocate, a novel Deepfake detection model that can both recognize andlocalize unknown domain Deepfake videos. Ourmethod consists of two stages named recoveringand localization. In the recovering stage, the modelrandomly masks regions of interest (ROIs) and reconstructs real faces without ta"},"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":"2401.13516","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-24T15:14:05Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"1cad650adc1b7d94bc3119fd818920b98e7f4349eff1b66ae7b3396c5a1e8bb4","abstract_canon_sha256":"350d2146479b79706f2121c6885e0e42b1ef3beae2e8e332ed903c1710d11b88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:17:30.768103Z","signature_b64":"fwEGht4/3AZEXX9pMjb295FtUgHDIL8M0X2/XDTJ6xQ1fT9C6i9FBTs7RFLX0nDmWfyVcM0f6/sFjERtuzCZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ffe239ac0328607320b0ce9651992d02f9670dbaf438a92fff4cdbb10a6eb54","last_reissued_at":"2026-07-05T08:17:30.767594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:17:30.767594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Difei Gao, Juan Hu, Mike Zheng Shou, Qian Wang, Satoshi Tsutsui, Xin Liao, Zheng Qin","submitted_at":"2024-01-24T15:14:05Z","abstract_excerpt":"Deepfake videos are becoming increasingly realistic, showing few tampering traces on facial areasthat vary between frames. Consequently, existing Deepfake detection methods struggle to detect unknown domain Deepfake videos while accurately locating the tampered region. To address thislimitation, we propose Delocate, a novel Deepfake detection model that can both recognize andlocalize unknown domain Deepfake videos. Ourmethod consists of two stages named recoveringand localization. In the recovering stage, the modelrandomly masks regions of interest (ROIs) and reconstructs real faces without ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13516","kind":"arxiv","version":5},"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/2401.13516/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":"2401.13516","created_at":"2026-07-05T08:17:30.767657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13516v5","created_at":"2026-07-05T08:17:30.767657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13516","created_at":"2026-07-05T08:17:30.767657+00:00"},{"alias_kind":"pith_short_12","alias_value":"D77CHGWAGKDA","created_at":"2026-07-05T08:17:30.767657+00:00"},{"alias_kind":"pith_short_16","alias_value":"D77CHGWAGKDAOMQL","created_at":"2026-07-05T08:17:30.767657+00:00"},{"alias_kind":"pith_short_8","alias_value":"D77CHGWA","created_at":"2026-07-05T08:17:30.767657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07216","citing_title":"Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14574","citing_title":"M3D-Net: Multi-Modal 3D Facial Feature Reconstruction Network for Deepfake Detection","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A","json":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A.json","graph_json":"https://pith.science/api/pith-number/D77CHGWAGKDAOMQLBTUWKGMS2A/graph.json","events_json":"https://pith.science/api/pith-number/D77CHGWAGKDAOMQLBTUWKGMS2A/events.json","paper":"https://pith.science/paper/D77CHGWA"},"agent_actions":{"view_html":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A","download_json":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A.json","view_paper":"https://pith.science/paper/D77CHGWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13516&json=true","fetch_graph":"https://pith.science/api/pith-number/D77CHGWAGKDAOMQLBTUWKGMS2A/graph.json","fetch_events":"https://pith.science/api/pith-number/D77CHGWAGKDAOMQLBTUWKGMS2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A/action/storage_attestation","attest_author":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A/action/author_attestation","sign_citation":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A/action/citation_signature","submit_replication":"https://pith.science/pith/D77CHGWAGKDAOMQLBTUWKGMS2A/action/replication_record"}},"created_at":"2026-07-05T08:17:30.767657+00:00","updated_at":"2026-07-05T08:17:30.767657+00:00"}