{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KHDNSXL57BLDMU677R6XT3B6UM","short_pith_number":"pith:KHDNSXL5","schema_version":"1.0","canonical_sha256":"51c6d95d7df8563653dffc7d79ec3ea31cf715b25fc7d62e98a6821b7f0c3ef0","source":{"kind":"arxiv","id":"2306.00863","version":2},"attestation_state":"computed","paper":{"title":"DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Nie, Rui Shao, Tianxing Wu, Ziwei Liu","submitted_at":"2023-06-01T16:23:22Z","abstract_excerpt":"Existing deepfake detection methods fail to generalize well to unseen or degraded samples, which can be attributed to the over-fitting of low-level forgery patterns. Here we argue that high-level semantics are also indispensable recipes for generalizable forgery detection. Recently, large pre-trained Vision Transformers (ViTs) have shown promising generalization capability. In this paper, we propose the first parameter-efficient tuning approach for deepfake detection, namely DeepFake-Adapter, to effectively and efficiently adapt the generalizable high-level semantics from large pre-trained ViT"},"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":"2306.00863","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T16:23:22Z","cross_cats_sorted":[],"title_canon_sha256":"aaa4ac45d461ab8aae7c94772a4540a1d822d6d6924d34acf85290682438f45a","abstract_canon_sha256":"b9eda1f220f94fa9cffb769bd7baf53873fea4cd898b0167d11a710574f6b30e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:40.168970Z","signature_b64":"WtdCz3nkTcw59kGtkkzlA3dE1/W6RWLXut0HH9E+QbMdZ0058HeiXRHN0sv4UhwphMd7xzA2ctVf1OidgEGuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51c6d95d7df8563653dffc7d79ec3ea31cf715b25fc7d62e98a6821b7f0c3ef0","last_reissued_at":"2026-07-05T09:45:40.168536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:40.168536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepFake-Adapter: Dual-Level Adapter for DeepFake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Nie, Rui Shao, Tianxing Wu, Ziwei Liu","submitted_at":"2023-06-01T16:23:22Z","abstract_excerpt":"Existing deepfake detection methods fail to generalize well to unseen or degraded samples, which can be attributed to the over-fitting of low-level forgery patterns. Here we argue that high-level semantics are also indispensable recipes for generalizable forgery detection. Recently, large pre-trained Vision Transformers (ViTs) have shown promising generalization capability. In this paper, we propose the first parameter-efficient tuning approach for deepfake detection, namely DeepFake-Adapter, to effectively and efficiently adapt the generalizable high-level semantics from large pre-trained ViT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00863","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/2306.00863/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":"2306.00863","created_at":"2026-07-05T09:45:40.168581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00863v2","created_at":"2026-07-05T09:45:40.168581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00863","created_at":"2026-07-05T09:45:40.168581+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHDNSXL57BLD","created_at":"2026-07-05T09:45:40.168581+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHDNSXL57BLDMU67","created_at":"2026-07-05T09:45:40.168581+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHDNSXL5","created_at":"2026-07-05T09:45:40.168581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM","json":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM.json","graph_json":"https://pith.science/api/pith-number/KHDNSXL57BLDMU677R6XT3B6UM/graph.json","events_json":"https://pith.science/api/pith-number/KHDNSXL57BLDMU677R6XT3B6UM/events.json","paper":"https://pith.science/paper/KHDNSXL5"},"agent_actions":{"view_html":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM","download_json":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM.json","view_paper":"https://pith.science/paper/KHDNSXL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00863&json=true","fetch_graph":"https://pith.science/api/pith-number/KHDNSXL57BLDMU677R6XT3B6UM/graph.json","fetch_events":"https://pith.science/api/pith-number/KHDNSXL57BLDMU677R6XT3B6UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM/action/storage_attestation","attest_author":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM/action/author_attestation","sign_citation":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM/action/citation_signature","submit_replication":"https://pith.science/pith/KHDNSXL57BLDMU677R6XT3B6UM/action/replication_record"}},"created_at":"2026-07-05T09:45:40.168581+00:00","updated_at":"2026-07-05T09:45:40.168581+00:00"}