{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NB73K33UPUSUJPCVBCTLLEDQ7A","short_pith_number":"pith:NB73K33U","schema_version":"1.0","canonical_sha256":"687fb56f747d2544bc5508a6b59070f8159a4c2ea4931342a51fc1e081a6f12b","source":{"kind":"arxiv","id":"2103.16076","version":1},"attestation_state":"computed","paper":{"title":"Face Forensics in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbing Shen, Tianfei Zhou, Wenguan Wang, Zhiyuan Liang","submitted_at":"2021-03-30T05:06:19Z","abstract_excerpt":"On existing public benchmarks, face forgery detection techniques have achieved great success. However, when used in multi-person videos, which often contain many people active in the scene with only a small subset having been manipulated, their performance remains far from being satisfactory. To take face forgery detection to a new level, we construct a novel large-scale dataset, called FFIW-10K, which comprises 10,000 high-quality forgery videos, with an average of three human faces in each frame. The manipulation procedure is fully automatic, controlled by a domain-adversarial quality assess"},"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":"2103.16076","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T05:06:19Z","cross_cats_sorted":[],"title_canon_sha256":"08c9446a5c78eac0ac216dc03cfde5baa09fa116f75e1807d9e0caa36321efc1","abstract_canon_sha256":"23a3c8ecf96a9437aa505729e72e3c6f3c4fdd3711bc4b001e3ebd14861b162f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:47.999832Z","signature_b64":"pNzCVMTbyK7tYqEkvKdDyDK2agSIfIW4xTiXWaeUQee8QYHDKyahXROp2p53W2eFTcUVG89g3TISYMVndWzeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"687fb56f747d2544bc5508a6b59070f8159a4c2ea4931342a51fc1e081a6f12b","last_reissued_at":"2026-07-05T02:27:47.999380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:47.999380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Face Forensics in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianbing Shen, Tianfei Zhou, Wenguan Wang, Zhiyuan Liang","submitted_at":"2021-03-30T05:06:19Z","abstract_excerpt":"On existing public benchmarks, face forgery detection techniques have achieved great success. However, when used in multi-person videos, which often contain many people active in the scene with only a small subset having been manipulated, their performance remains far from being satisfactory. To take face forgery detection to a new level, we construct a novel large-scale dataset, called FFIW-10K, which comprises 10,000 high-quality forgery videos, with an average of three human faces in each frame. The manipulation procedure is fully automatic, controlled by a domain-adversarial quality assess"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16076","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/2103.16076/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":"2103.16076","created_at":"2026-07-05T02:27:47.999437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16076v1","created_at":"2026-07-05T02:27:47.999437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16076","created_at":"2026-07-05T02:27:47.999437+00:00"},{"alias_kind":"pith_short_12","alias_value":"NB73K33UPUSU","created_at":"2026-07-05T02:27:47.999437+00:00"},{"alias_kind":"pith_short_16","alias_value":"NB73K33UPUSUJPCV","created_at":"2026-07-05T02:27:47.999437+00:00"},{"alias_kind":"pith_short_8","alias_value":"NB73K33U","created_at":"2026-07-05T02:27:47.999437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04150","citing_title":"Revisiting Simple Baselines for In-The-Wild Deepfake Detection","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A","json":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A.json","graph_json":"https://pith.science/api/pith-number/NB73K33UPUSUJPCVBCTLLEDQ7A/graph.json","events_json":"https://pith.science/api/pith-number/NB73K33UPUSUJPCVBCTLLEDQ7A/events.json","paper":"https://pith.science/paper/NB73K33U"},"agent_actions":{"view_html":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A","download_json":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A.json","view_paper":"https://pith.science/paper/NB73K33U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16076&json=true","fetch_graph":"https://pith.science/api/pith-number/NB73K33UPUSUJPCVBCTLLEDQ7A/graph.json","fetch_events":"https://pith.science/api/pith-number/NB73K33UPUSUJPCVBCTLLEDQ7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A/action/storage_attestation","attest_author":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A/action/author_attestation","sign_citation":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A/action/citation_signature","submit_replication":"https://pith.science/pith/NB73K33UPUSUJPCVBCTLLEDQ7A/action/replication_record"}},"created_at":"2026-07-05T02:27:47.999437+00:00","updated_at":"2026-07-05T02:27:47.999437+00:00"}