{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5SSBJ44OH57URQZGSFZP2TKBZB","short_pith_number":"pith:5SSBJ44O","schema_version":"1.0","canonical_sha256":"eca414f38e3f7f48c3269172fd4d41c879fcc6ad2a9de6ea6aee414c8d94bea0","source":{"kind":"arxiv","id":"2508.09475","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Liang, Chunjie Zhang, Renshuai Tao, Shibo Yao, Xiaolong Zheng","submitted_at":"2025-08-13T04:06:09Z","abstract_excerpt":"Recent deepfake detection studies often treat unseen sample detection as a ``zero-shot\" task, training on images generated by known models but generalizing to unknown ones. A key real-world challenge arises when a model performs poorly on unknown samples, yet these samples remain available for analysis. This highlights that it should be approached as a ``few-shot\" task, where effectively utilizing a small number of samples can lead to significant improvement. Unlike typical few-shot tasks focused on semantic understanding, deepfake detection prioritizes image realism, which closely mirrors rea"},"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":"2508.09475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-13T04:06:09Z","cross_cats_sorted":[],"title_canon_sha256":"4c39fb9228e52d35d945f0b68a20d77709e6788854a57cd0163e010303171245","abstract_canon_sha256":"f4ab2f79871872c82aeca5eeae06ff1843b1173567b688d7b5ccebd4e4d77461"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:15.567683Z","signature_b64":"qO9U/ZcwQpfQmdvIuOj/vaZcegyouLOqTeHlHs7/LD6rvXW3Pi/CIXN+IwUGQ/frSzZpqW+bshA8ZW6vA8TKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eca414f38e3f7f48c3269172fd4d41c879fcc6ad2a9de6ea6aee414c8d94bea0","last_reissued_at":"2026-07-05T11:53:15.567243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:15.567243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Failed Samples: A Few-Shot and Training-Free Framework for Generalized Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Liang, Chunjie Zhang, Renshuai Tao, Shibo Yao, Xiaolong Zheng","submitted_at":"2025-08-13T04:06:09Z","abstract_excerpt":"Recent deepfake detection studies often treat unseen sample detection as a ``zero-shot\" task, training on images generated by known models but generalizing to unknown ones. A key real-world challenge arises when a model performs poorly on unknown samples, yet these samples remain available for analysis. This highlights that it should be approached as a ``few-shot\" task, where effectively utilizing a small number of samples can lead to significant improvement. Unlike typical few-shot tasks focused on semantic understanding, deepfake detection prioritizes image realism, which closely mirrors rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09475","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/2508.09475/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":"2508.09475","created_at":"2026-07-05T11:53:15.567299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09475v1","created_at":"2026-07-05T11:53:15.567299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09475","created_at":"2026-07-05T11:53:15.567299+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SSBJ44OH57U","created_at":"2026-07-05T11:53:15.567299+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SSBJ44OH57URQZG","created_at":"2026-07-05T11:53:15.567299+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SSBJ44O","created_at":"2026-07-05T11:53:15.567299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB","json":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB.json","graph_json":"https://pith.science/api/pith-number/5SSBJ44OH57URQZGSFZP2TKBZB/graph.json","events_json":"https://pith.science/api/pith-number/5SSBJ44OH57URQZGSFZP2TKBZB/events.json","paper":"https://pith.science/paper/5SSBJ44O"},"agent_actions":{"view_html":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB","download_json":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB.json","view_paper":"https://pith.science/paper/5SSBJ44O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09475&json=true","fetch_graph":"https://pith.science/api/pith-number/5SSBJ44OH57URQZGSFZP2TKBZB/graph.json","fetch_events":"https://pith.science/api/pith-number/5SSBJ44OH57URQZGSFZP2TKBZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB/action/storage_attestation","attest_author":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB/action/author_attestation","sign_citation":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB/action/citation_signature","submit_replication":"https://pith.science/pith/5SSBJ44OH57URQZGSFZP2TKBZB/action/replication_record"}},"created_at":"2026-07-05T11:53:15.567299+00:00","updated_at":"2026-07-05T11:53:15.567299+00:00"}