{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:C3K3I4BLDFPIUFWBEFUF6RMST6","short_pith_number":"pith:C3K3I4BL","schema_version":"1.0","canonical_sha256":"16d5b4702b195e8a16c121685f45929fb80c67c2edfd6578f635045e0181528f","source":{"kind":"arxiv","id":"2006.07397","version":4},"attestation_state":"computed","paper":{"title":"The DeepFake Detection Challenge (DFDC) Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A model trained only on the DFDC dataset detects deepfakes in real in-the-wild videos.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ben Pflaum, Brian Dolhansky, Cristian Canton Ferrer, Jikuo Lu, Joanna Bitton, Menglin Wang, Russ Howes","submitted_at":"2020-06-12T18:15:55Z","abstract_excerpt":"Deepfakes are a recent off-the-shelf manipulation technique that allows anyone to swap two identities in a single video. In addition to Deepfakes, a variety of GAN-based face swapping methods have also been published with accompanying code. To counter this emerging threat, we have constructed an extremely large face swap video dataset to enable the training of detection models, and organized the accompanying DeepFake Detection Challenge (DFDC) Kaggle competition. Importantly, all recorded subjects agreed to participate in and have their likenesses modified during the construction of the face-s"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.07397","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-12T18:15:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9af6880dee01339603da62e58003412ce9dd84cff01e281793afeefc301d6cae","abstract_canon_sha256":"805be560cf614013e9a6a5e23348cd8eba41ae2a0c794e3de508ada1ecc87553"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:14.046827Z","signature_b64":"TSoHduA6KXMgsnl6zLykNVpSwZAftIk9XW+kkUJwPiTbbyBhlb+Ys4ahpacx3tc4pOoS8Rt4ro0my4iYQLovBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16d5b4702b195e8a16c121685f45929fb80c67c2edfd6578f635045e0181528f","last_reissued_at":"2026-07-05T01:47:14.046325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:14.046325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The DeepFake Detection Challenge (DFDC) Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A model trained only on the DFDC dataset detects deepfakes in real in-the-wild videos.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ben Pflaum, Brian Dolhansky, Cristian Canton Ferrer, Jikuo Lu, Joanna Bitton, Menglin Wang, Russ Howes","submitted_at":"2020-06-12T18:15:55Z","abstract_excerpt":"Deepfakes are a recent off-the-shelf manipulation technique that allows anyone to swap two identities in a single video. In addition to Deepfakes, a variety of GAN-based face swapping methods have also been published with accompanying code. To counter this emerging threat, we have constructed an extremely large face swap video dataset to enable the training of detection models, and organized the accompanying DeepFake Detection Challenge (DFDC) Kaggle competition. Importantly, all recorded subjects agreed to participate in and have their likenesses modified during the construction of the face-s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"a Deepfake detection model trained only on the DFDC can generalize to real 'in-the-wild' Deepfake videos, and such a model can be a valuable analysis tool when analyzing potentially Deepfaked videos.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The face-swap methods and actor diversity in the dataset sufficiently represent the distribution of real-world deepfakes encountered outside the competition.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The DFDC dataset is the largest public collection of face-swapped videos and supports detectors that generalize to in-the-wild deepfakes.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A model trained only on the DFDC dataset detects deepfakes in real in-the-wild videos.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8753ecbd1d17ba74ddeca7fdb6391cea091dc3f9129d3a6621c1b16e0e3179e3"},"source":{"id":"2006.07397","kind":"arxiv","version":4},"verdict":{"id":"aad377ca-a4fc-4cd0-855f-3f8233361434","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T16:44:50.201889Z","strongest_claim":"a Deepfake detection model trained only on the DFDC can generalize to real 'in-the-wild' Deepfake videos, and such a model can be a valuable analysis tool when analyzing potentially Deepfaked videos.","one_line_summary":"The DFDC dataset is the largest public collection of face-swapped videos and supports detectors that generalize to in-the-wild deepfakes.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The face-swap methods and actor diversity in the dataset sufficiently represent the distribution of real-world deepfakes encountered outside the competition.","pith_extraction_headline":"A model trained only on the DFDC dataset detects deepfakes in real in-the-wild videos."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.07397/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":34,"sample":[{"doi":"","year":2017,"title":"Quo vadis, action recognition? a new model and the kinetics dataset","work_id":"c9907ac5-0337-4ec4-a079-61ff40e1e009","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Deepfakes: A loom- ing challenge for privacy, democracy, and national security","work_id":"635f8853-d2c6-416f-8667-c34c2f7ea283","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Xception: Deep learning with depthwise separable convolutions","work_id":"60421e05-6da8-4541-b3b7-9a2b9e50b840","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"https://github.com/ NTech-Lab/deepfake-detection-challenge","work_id":"b529f679-d532-4be1-89a3-1f1e25b39f40","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1910,"title":"The deepfake detection chal- lenge (DFDC) preview dataset","work_id":"008691a4-eff9-4551-bc03-6ce536de4714","ref_index":5,"cited_arxiv_id":"1910.08854","is_internal_anchor":false}],"resolved_work":34,"snapshot_sha256":"5d005031b62af56c9778f1609bd6745ea2c8e4cbeca954d2c98b40e4dc96e7b8","internal_anchors":2},"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":"2006.07397","created_at":"2026-07-05T01:47:14.046392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07397v4","created_at":"2026-07-05T01:47:14.046392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07397","created_at":"2026-07-05T01:47:14.046392+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3K3I4BLDFPI","created_at":"2026-07-05T01:47:14.046392+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3K3I4BLDFPIUFWB","created_at":"2026-07-05T01:47:14.046392+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3K3I4BL","created_at":"2026-07-05T01:47:14.046392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":47,"internal_anchor_count":47,"sample":[{"citing_arxiv_id":"2607.08156","citing_title":"Unified Face Attack Detection via Fine-Grained Semantic Guidance","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2607.07216","citing_title":"Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06254","citing_title":"VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21475","citing_title":"Photonic Quantum Computing on Spin Memory Architecture with Tree-Encoded Fusion","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26384","citing_title":"What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19184","citing_title":"When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07916","citing_title":"The CIFAR Synthetic Evidence Corpus for Detecting AI-Generated Evidence","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.06666","citing_title":"Architecture-Adaptive Uncertainty Fusion for Deepfake Detection","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04706","citing_title":"ReConFuse: Reconstruction-Error Guided Semantic Fusion for AI-Generated Video Detection","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07613","citing_title":"Can You Trust What You See? Human and AI Detection of Synthetic Legal Evidence","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31192","citing_title":"The Regularizing Power of Language-Training Deepfake Detectors","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09881","citing_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2401.03717","citing_title":"Universal Time-Series Representation Learning: A Survey","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2408.05366","citing_title":"The DeepSpeak Dataset","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2412.19685","citing_title":"Generating Attribution Reports for Manipulated Facial Images: A Dataset and Baseline","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2504.14129","citing_title":"PVLM: Parsing-Aware Vision Language Model with Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17311","citing_title":"SpecSem-Net: Integrating Spectral and Semantic Features for Robust AI-generated Video Detection","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2508.06248","citing_title":"Deepfake Detection that Generalizes Across Benchmarks","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2512.00336","citing_title":"MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13281","citing_title":"VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2601.01041","citing_title":"Generalizable Deepfake Detection Based on Forgery-aware Layer Masking and Multi-artifact Subspace Decomposition","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04939","citing_title":"SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14091","citing_title":"Venus-DeFakerOne: Unified Fake Image Detection & Localization","ref_index":134,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27557","citing_title":"A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03558","citing_title":"LOGER: Local--Global Ensemble for Robust Deepfake Detection in the Wild","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6","json":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6.json","graph_json":"https://pith.science/api/pith-number/C3K3I4BLDFPIUFWBEFUF6RMST6/graph.json","events_json":"https://pith.science/api/pith-number/C3K3I4BLDFPIUFWBEFUF6RMST6/events.json","paper":"https://pith.science/paper/C3K3I4BL"},"agent_actions":{"view_html":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6","download_json":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6.json","view_paper":"https://pith.science/paper/C3K3I4BL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07397&json=true","fetch_graph":"https://pith.science/api/pith-number/C3K3I4BLDFPIUFWBEFUF6RMST6/graph.json","fetch_events":"https://pith.science/api/pith-number/C3K3I4BLDFPIUFWBEFUF6RMST6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6/action/storage_attestation","attest_author":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6/action/author_attestation","sign_citation":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6/action/citation_signature","submit_replication":"https://pith.science/pith/C3K3I4BLDFPIUFWBEFUF6RMST6/action/replication_record"}},"created_at":"2026-07-05T01:47:14.046392+00:00","updated_at":"2026-07-05T01:47:14.046392+00:00"}