{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VK5X5PVUNEIHVROVCUSSZDOXQB","short_pith_number":"pith:VK5X5PVU","schema_version":"1.0","canonical_sha256":"aabb7ebeb469107ac5d515252c8dd7805819f149594f7087f92e7261788aba1b","source":{"kind":"arxiv","id":"2404.08452","version":3},"attestation_state":"computed","paper":{"title":"MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex C. Kot, Anwei Luo, Chenqi Kong, Haoliang Li, Peijun Bao, Shiqi Wang, Yi Yu, Zengwei Zheng","submitted_at":"2024-04-12T13:02:08Z","abstract_excerpt":"Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance. However, these approaches still exhibit the following limitations: (1) Fully fine-tuning ViT-based models from ImageNet weights demands substantial computational and storage resources; (2) ViT-based methods struggle to capture local forgery clues, leading to model bias; (3) These methods limit their scope on only one or few face forgery features, res"},"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":"2404.08452","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-12T13:02:08Z","cross_cats_sorted":[],"title_canon_sha256":"5eddc98da1aa81ea48b3f9aa1c45a4a577f1560937c6f67305af817ff75cc597","abstract_canon_sha256":"6f3d60cedeaeadcfd73fab76508f50961cd84af69ebe881509f174638a791b0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:13.891472Z","signature_b64":"clMC+HHclt+C4bmtpJu75ZopA96IeKHudb9LjwZ/EMGAexZ/L10yDMjulmHZIdY/dzBAtYqYfo3o4Bs++lz1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aabb7ebeb469107ac5d515252c8dd7805819f149594f7087f92e7261788aba1b","last_reissued_at":"2026-07-05T11:56:13.890984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:13.890984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex C. Kot, Anwei Luo, Chenqi Kong, Haoliang Li, Peijun Bao, Shiqi Wang, Yi Yu, Zengwei Zheng","submitted_at":"2024-04-12T13:02:08Z","abstract_excerpt":"Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection performance. However, these approaches still exhibit the following limitations: (1) Fully fine-tuning ViT-based models from ImageNet weights demands substantial computational and storage resources; (2) ViT-based methods struggle to capture local forgery clues, leading to model bias; (3) These methods limit their scope on only one or few face forgery features, res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08452","kind":"arxiv","version":3},"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/2404.08452/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":"2404.08452","created_at":"2026-07-05T11:56:13.891043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08452v3","created_at":"2026-07-05T11:56:13.891043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08452","created_at":"2026-07-05T11:56:13.891043+00:00"},{"alias_kind":"pith_short_12","alias_value":"VK5X5PVUNEIH","created_at":"2026-07-05T11:56:13.891043+00:00"},{"alias_kind":"pith_short_16","alias_value":"VK5X5PVUNEIHVROV","created_at":"2026-07-05T11:56:13.891043+00:00"},{"alias_kind":"pith_short_8","alias_value":"VK5X5PVU","created_at":"2026-07-05T11:56:13.891043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.32040","citing_title":"FaceMoE: Mixture of Experts for Low-Resolution Face Recognition","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":230,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01041","citing_title":"Generalizable Deepfake Detection Based on Forgery-aware Layer Masking and Multi-artifact Subspace Decomposition","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12941","citing_title":"Direct Discrepancy Replay: Distribution-Discrepancy Condensation and Manifold-Consistent Replay for Continual Face Forgery Detection","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB","json":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB.json","graph_json":"https://pith.science/api/pith-number/VK5X5PVUNEIHVROVCUSSZDOXQB/graph.json","events_json":"https://pith.science/api/pith-number/VK5X5PVUNEIHVROVCUSSZDOXQB/events.json","paper":"https://pith.science/paper/VK5X5PVU"},"agent_actions":{"view_html":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB","download_json":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB.json","view_paper":"https://pith.science/paper/VK5X5PVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08452&json=true","fetch_graph":"https://pith.science/api/pith-number/VK5X5PVUNEIHVROVCUSSZDOXQB/graph.json","fetch_events":"https://pith.science/api/pith-number/VK5X5PVUNEIHVROVCUSSZDOXQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB/action/storage_attestation","attest_author":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB/action/author_attestation","sign_citation":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB/action/citation_signature","submit_replication":"https://pith.science/pith/VK5X5PVUNEIHVROVCUSSZDOXQB/action/replication_record"}},"created_at":"2026-07-05T11:56:13.891043+00:00","updated_at":"2026-07-05T11:56:13.891043+00:00"}