{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X6RFOUVS2R5PT5VGHUELBPA5LD","short_pith_number":"pith:X6RFOUVS","schema_version":"1.0","canonical_sha256":"bfa25752b2d47af9f6a63d08b0bc1d58f538cbe049c141b863682f356c834940","source":{"kind":"arxiv","id":"2311.11549","version":1},"attestation_state":"computed","paper":{"title":"Unearthing Common Inconsistency for Generalisable Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beilin Chu, Linna Zhou, Weike You, Xuan Xu","submitted_at":"2023-11-20T06:04:09Z","abstract_excerpt":"Deepfake has emerged for several years, yet efficient detection techniques could generalize over different manipulation methods require further research. While current image-level detection method fails to generalize to unseen domains, owing to the domain-shift phenomenon brought by CNN's strong inductive bias towards Deepfake texture, video-level one shows its potential to have both generalization across multiple domains and robustness to compression. We argue that although distinct face manipulation tools have different inherent bias, they all disrupt the consistency between frames, which is"},"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":"2311.11549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T06:04:09Z","cross_cats_sorted":[],"title_canon_sha256":"d38888676da423e8082b492fd54f9a1a4ab2b21ceaead8d6154dc9d082f80e3a","abstract_canon_sha256":"dfd8852b7652bdd56b0a226c15f63a17da582f4da2019376ab4ec00724e8880f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:35.248652Z","signature_b64":"SxhnnAUbFtM3hgCpYU7vAJpIBiibi/0Wu1tWtyRh47+UWVLUu/nU+6SQmkGGBlss6Ts3J03nxtWZZUr/PSq6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa25752b2d47af9f6a63d08b0bc1d58f538cbe049c141b863682f356c834940","last_reissued_at":"2026-07-05T07:14:35.248167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:35.248167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unearthing Common Inconsistency for Generalisable Deepfake Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beilin Chu, Linna Zhou, Weike You, Xuan Xu","submitted_at":"2023-11-20T06:04:09Z","abstract_excerpt":"Deepfake has emerged for several years, yet efficient detection techniques could generalize over different manipulation methods require further research. While current image-level detection method fails to generalize to unseen domains, owing to the domain-shift phenomenon brought by CNN's strong inductive bias towards Deepfake texture, video-level one shows its potential to have both generalization across multiple domains and robustness to compression. We argue that although distinct face manipulation tools have different inherent bias, they all disrupt the consistency between frames, which is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11549","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/2311.11549/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":"2311.11549","created_at":"2026-07-05T07:14:35.248250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11549v1","created_at":"2026-07-05T07:14:35.248250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11549","created_at":"2026-07-05T07:14:35.248250+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6RFOUVS2R5P","created_at":"2026-07-05T07:14:35.248250+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6RFOUVS2R5PT5VG","created_at":"2026-07-05T07:14:35.248250+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6RFOUVS","created_at":"2026-07-05T07:14:35.248250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.18084","citing_title":"RL-Driven Data Generation for Robust Vision-Based Dexterous Grasping","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD","json":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD.json","graph_json":"https://pith.science/api/pith-number/X6RFOUVS2R5PT5VGHUELBPA5LD/graph.json","events_json":"https://pith.science/api/pith-number/X6RFOUVS2R5PT5VGHUELBPA5LD/events.json","paper":"https://pith.science/paper/X6RFOUVS"},"agent_actions":{"view_html":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD","download_json":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD.json","view_paper":"https://pith.science/paper/X6RFOUVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11549&json=true","fetch_graph":"https://pith.science/api/pith-number/X6RFOUVS2R5PT5VGHUELBPA5LD/graph.json","fetch_events":"https://pith.science/api/pith-number/X6RFOUVS2R5PT5VGHUELBPA5LD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD/action/storage_attestation","attest_author":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD/action/author_attestation","sign_citation":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD/action/citation_signature","submit_replication":"https://pith.science/pith/X6RFOUVS2R5PT5VGHUELBPA5LD/action/replication_record"}},"created_at":"2026-07-05T07:14:35.248250+00:00","updated_at":"2026-07-05T07:14:35.248250+00:00"}