{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6G7GE3D5VVUNE46JJ7YWH7WJBC","short_pith_number":"pith:6G7GE3D5","schema_version":"1.0","canonical_sha256":"f1be626c7dad68d273c94ff163fec908ab9fa04985575340c6d0415ccd6b6fba","source":{"kind":"arxiv","id":"2408.09647","version":2},"attestation_state":"computed","paper":{"title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Wu, Chuangchuang Tan, Guanghua Gu, Huan Liu, Renshuai Tao, Yao Zhao, Yunchao Wei","submitted_at":"2024-08-19T02:14:25Z","abstract_excerpt":"This work focuses on AIGC detection to develop universal detectors capable of identifying various types of forgery images. Recent studies have found large pre-trained models, such as CLIP, are effective for generalizable deepfake detection along with linear classifiers. However, two critical issues remain unresolved: 1) understanding why CLIP features are effective on deepfake detection through a linear classifier; and 2) exploring the detection potential of CLIP. In this study, we delve into the underlying mechanisms of CLIP's detection capabilities by decoding its detection features into tex"},"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":"2408.09647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-19T02:14:25Z","cross_cats_sorted":[],"title_canon_sha256":"63f8b20d87d23e95a1e0f65c1f99a1a07c2f94d949a8fcd89df79165a4812a96","abstract_canon_sha256":"e62bd5fdbf66a61483f9a2f609a44dacaf281d2d54aa410c72767156349dec9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:52.922540Z","signature_b64":"c2hiULV348liPcKTH/LC8OeC/5EMyIWoSzbgwfTUSXVLenKGTHQSCkxDOl6l1HtmnALHlng/9+yoqPZ4cZr9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1be626c7dad68d273c94ff163fec908ab9fa04985575340c6d0415ccd6b6fba","last_reissued_at":"2026-07-05T09:44:52.922079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:52.922079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Wu, Chuangchuang Tan, Guanghua Gu, Huan Liu, Renshuai Tao, Yao Zhao, Yunchao Wei","submitted_at":"2024-08-19T02:14:25Z","abstract_excerpt":"This work focuses on AIGC detection to develop universal detectors capable of identifying various types of forgery images. Recent studies have found large pre-trained models, such as CLIP, are effective for generalizable deepfake detection along with linear classifiers. However, two critical issues remain unresolved: 1) understanding why CLIP features are effective on deepfake detection through a linear classifier; and 2) exploring the detection potential of CLIP. In this study, we delve into the underlying mechanisms of CLIP's detection capabilities by decoding its detection features into tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09647","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/2408.09647/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":"2408.09647","created_at":"2026-07-05T09:44:52.922135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09647v2","created_at":"2026-07-05T09:44:52.922135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09647","created_at":"2026-07-05T09:44:52.922135+00:00"},{"alias_kind":"pith_short_12","alias_value":"6G7GE3D5VVUN","created_at":"2026-07-05T09:44:52.922135+00:00"},{"alias_kind":"pith_short_16","alias_value":"6G7GE3D5VVUNE46J","created_at":"2026-07-05T09:44:52.922135+00:00"},{"alias_kind":"pith_short_8","alias_value":"6G7GE3D5","created_at":"2026-07-05T09:44:52.922135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06254","citing_title":"VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03833","citing_title":"SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC","json":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC.json","graph_json":"https://pith.science/api/pith-number/6G7GE3D5VVUNE46JJ7YWH7WJBC/graph.json","events_json":"https://pith.science/api/pith-number/6G7GE3D5VVUNE46JJ7YWH7WJBC/events.json","paper":"https://pith.science/paper/6G7GE3D5"},"agent_actions":{"view_html":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC","download_json":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC.json","view_paper":"https://pith.science/paper/6G7GE3D5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09647&json=true","fetch_graph":"https://pith.science/api/pith-number/6G7GE3D5VVUNE46JJ7YWH7WJBC/graph.json","fetch_events":"https://pith.science/api/pith-number/6G7GE3D5VVUNE46JJ7YWH7WJBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC/action/storage_attestation","attest_author":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC/action/author_attestation","sign_citation":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC/action/citation_signature","submit_replication":"https://pith.science/pith/6G7GE3D5VVUNE46JJ7YWH7WJBC/action/replication_record"}},"created_at":"2026-07-05T09:44:52.922135+00:00","updated_at":"2026-07-05T09:44:52.922135+00:00"}