{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ABM3DDWWJK32XRMJRXAGV754AQ","short_pith_number":"pith:ABM3DDWW","schema_version":"1.0","canonical_sha256":"0059b18ed64ab7abc5898dc06affbc040d3325f3ec473a99d975043d50ff0073","source":{"kind":"arxiv","id":"2503.02857","version":5},"attestation_state":"computed","paper":{"title":"Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CV","authors_text":"Aerin Kim, Arnab Karmakar, Ben Caffee, Changyeon Lee, Emmanuel Tanumihardja, Hannah Lee, Jongwook Choi, Kevin Farhat, Lin Qiu, Nuria Alina Chandra, Oren Etzioni, Ryan Murtfeldt, Sejin Paik","submitted_at":"2025-03-04T18:33:22Z","abstract_excerpt":"In the age of increasingly realistic generative AI, robust deepfake detection is essential for mitigating fraud and disinformation. While many deepfake detectors report high accuracy on academic datasets, we show that these academic benchmarks are out of date and not representative of real-world deepfakes. We introduce Deepfake-Eval-2024, a new deepfake detection benchmark consisting of in-the-wild deepfakes collected from social media and deepfake detection platform users in 2024. Deepfake-Eval-2024 consists of 45 hours of videos, 56.5 hours of audio, and 1,975 images, encompassing the latest"},"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":"2503.02857","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T18:33:22Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"b4632118b104eb49f2671607c85499d1cb76306731a960e0fe33c745e84954d6","abstract_canon_sha256":"c0f30a678b4a0ce6746e36f4a1323654e75a1dd1c852a274418af424cb8d4dfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:27.132738Z","signature_b64":"9PVOLxXR46RhkffdiFxjtfan7QrLgACS67yQxODZsL/+kPe1YqxdRmtLkLV+JCRnb0PxXYnyhtW8ADp/HXDxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0059b18ed64ab7abc5898dc06affbc040d3325f3ec473a99d975043d50ff0073","last_reissued_at":"2026-05-28T01:04:27.132087Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:27.132087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CV","authors_text":"Aerin Kim, Arnab Karmakar, Ben Caffee, Changyeon Lee, Emmanuel Tanumihardja, Hannah Lee, Jongwook Choi, Kevin Farhat, Lin Qiu, Nuria Alina Chandra, Oren Etzioni, Ryan Murtfeldt, Sejin Paik","submitted_at":"2025-03-04T18:33:22Z","abstract_excerpt":"In the age of increasingly realistic generative AI, robust deepfake detection is essential for mitigating fraud and disinformation. While many deepfake detectors report high accuracy on academic datasets, we show that these academic benchmarks are out of date and not representative of real-world deepfakes. We introduce Deepfake-Eval-2024, a new deepfake detection benchmark consisting of in-the-wild deepfakes collected from social media and deepfake detection platform users in 2024. Deepfake-Eval-2024 consists of 45 hours of videos, 56.5 hours of audio, and 1,975 images, encompassing the latest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02857","kind":"arxiv","version":5},"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/2503.02857/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":"2503.02857","created_at":"2026-05-28T01:04:27.132160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02857v5","created_at":"2026-05-28T01:04:27.132160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02857","created_at":"2026-05-28T01:04:27.132160+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABM3DDWWJK32","created_at":"2026-05-28T01:04:27.132160+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABM3DDWWJK32XRMJ","created_at":"2026-05-28T01:04:27.132160+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABM3DDWW","created_at":"2026-05-28T01:04:27.132160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"2605.16471","citing_title":"From AI-Generated Content to Agentic Action: Security and Safety Threats in Generative AI","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2603.01482","citing_title":"A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09007","citing_title":"Detecting Deception, Not Deepfakes: Why Media Forensics Needs Social Theories","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00251","citing_title":"Alethia: A Foundational Encoder for Voice Deepfakes","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16486","citing_title":"Aletheia: Physics-Conditioned Localized Artifact Attention (PhyLAA-X) for End-to-End Generalizable and Robust Deepfake Video Detection","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06912","citing_title":"Advancing Reliable Synthetic Video Detection: Insights from the SAFE Challenge","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26965","citing_title":"The Impact of AI-Generated Text on the Internet","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16749","citing_title":"ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02567","citing_title":"Automated In-the-Wild Data Collection for Continual AI Generated Image Detection","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ","json":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ.json","graph_json":"https://pith.science/api/pith-number/ABM3DDWWJK32XRMJRXAGV754AQ/graph.json","events_json":"https://pith.science/api/pith-number/ABM3DDWWJK32XRMJRXAGV754AQ/events.json","paper":"https://pith.science/paper/ABM3DDWW"},"agent_actions":{"view_html":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ","download_json":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ.json","view_paper":"https://pith.science/paper/ABM3DDWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02857&json=true","fetch_graph":"https://pith.science/api/pith-number/ABM3DDWWJK32XRMJRXAGV754AQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ABM3DDWWJK32XRMJRXAGV754AQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ/action/storage_attestation","attest_author":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ/action/author_attestation","sign_citation":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ/action/citation_signature","submit_replication":"https://pith.science/pith/ABM3DDWWJK32XRMJRXAGV754AQ/action/replication_record"}},"created_at":"2026-05-28T01:04:27.132160+00:00","updated_at":"2026-05-28T01:04:27.132160+00:00"}