{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2F2WX52QTXRKDSCX5IY4EOLN4G","short_pith_number":"pith:2F2WX52Q","schema_version":"1.0","canonical_sha256":"d1756bf7509de2a1c857ea31c2396de1acc7ec95dc614006c3f928e0544d6c98","source":{"kind":"arxiv","id":"2505.04460","version":1},"attestation_state":"computed","paper":{"title":"Learning Real Facial Concepts for Independent Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Harry Cheng, Ming-Hui Liu, Tianyi Wang, Xin Luo, Xin-Shun Xu","submitted_at":"2025-05-07T14:31:04Z","abstract_excerpt":"Deepfake detection models often struggle with generalization to unseen datasets, manifesting as misclassifying real instances as fake in target domains. This is primarily due to an overreliance on forgery artifacts and a limited understanding of real faces. To address this challenge, we propose a novel approach RealID to enhance generalization by learning a comprehensive concept of real faces while assessing the probabilities of belonging to the real and fake classes independently. RealID comprises two key modules: the Real Concept Capture Module (RealC2) and the Independent Dual-Decision Clas"},"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":"2505.04460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-07T14:31:04Z","cross_cats_sorted":[],"title_canon_sha256":"b6a4bb3c1786a0e342c1d67d01f6571501d812a66ac1140f8e6972d4a3f9f008","abstract_canon_sha256":"d0c885820a1dae45a1213f536c9944f56832592eb046be6895c55716ec6db307"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:52.225131Z","signature_b64":"AOmfHJf57Uh8xf0NmOzetaB4uT+bTJPKYfvXssFSkEx6Um2Gpv7sw9lCTdE5NfOrMio5dUIY5ev2WNwMqYLmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1756bf7509de2a1c857ea31c2396de1acc7ec95dc614006c3f928e0544d6c98","last_reissued_at":"2026-07-05T10:59:52.224665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:52.224665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Real Facial Concepts for Independent Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Harry Cheng, Ming-Hui Liu, Tianyi Wang, Xin Luo, Xin-Shun Xu","submitted_at":"2025-05-07T14:31:04Z","abstract_excerpt":"Deepfake detection models often struggle with generalization to unseen datasets, manifesting as misclassifying real instances as fake in target domains. This is primarily due to an overreliance on forgery artifacts and a limited understanding of real faces. To address this challenge, we propose a novel approach RealID to enhance generalization by learning a comprehensive concept of real faces while assessing the probabilities of belonging to the real and fake classes independently. RealID comprises two key modules: the Real Concept Capture Module (RealC2) and the Independent Dual-Decision Clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04460","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/2505.04460/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":"2505.04460","created_at":"2026-07-05T10:59:52.224719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04460v1","created_at":"2026-07-05T10:59:52.224719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04460","created_at":"2026-07-05T10:59:52.224719+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F2WX52QTXRK","created_at":"2026-07-05T10:59:52.224719+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F2WX52QTXRKDSCX","created_at":"2026-07-05T10:59:52.224719+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F2WX52Q","created_at":"2026-07-05T10:59:52.224719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02645","citing_title":"Fair Deepfake Detectors Can Generalize","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G","json":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G.json","graph_json":"https://pith.science/api/pith-number/2F2WX52QTXRKDSCX5IY4EOLN4G/graph.json","events_json":"https://pith.science/api/pith-number/2F2WX52QTXRKDSCX5IY4EOLN4G/events.json","paper":"https://pith.science/paper/2F2WX52Q"},"agent_actions":{"view_html":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G","download_json":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G.json","view_paper":"https://pith.science/paper/2F2WX52Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04460&json=true","fetch_graph":"https://pith.science/api/pith-number/2F2WX52QTXRKDSCX5IY4EOLN4G/graph.json","fetch_events":"https://pith.science/api/pith-number/2F2WX52QTXRKDSCX5IY4EOLN4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G/action/storage_attestation","attest_author":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G/action/author_attestation","sign_citation":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G/action/citation_signature","submit_replication":"https://pith.science/pith/2F2WX52QTXRKDSCX5IY4EOLN4G/action/replication_record"}},"created_at":"2026-07-05T10:59:52.224719+00:00","updated_at":"2026-07-05T10:59:52.224719+00:00"}