{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F6UJSHIRUZN73TZ6BA34PLO47J","short_pith_number":"pith:F6UJSHIR","schema_version":"1.0","canonical_sha256":"2fa8991d11a65bfdcf3e0837c7addcfa60ad9f5c8c23895440a715960950770f","source":{"kind":"arxiv","id":"2406.09601","version":1},"attestation_state":"computed","paper":{"title":"Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Mao, Junfeng Yang, Pengyuan Shi, Qingyuan Liu, Yun-Yun Tsai","submitted_at":"2024-06-13T21:52:49Z","abstract_excerpt":"The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works to combat Deepfakes videos have developed detectors that are highly accurate at identifying GAN-generated samples. However, the robustness of these detectors on diffusion-generated videos generated from video creation tools (e.g., SORA by OpenAI, Runway Gen-2, and Pika, etc.) is still unexplored. In this paper, we propose a novel framework for detecting videos synthesized from multiple state-of-the-art (SOTA) generative models, "},"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":"2406.09601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T21:52:49Z","cross_cats_sorted":[],"title_canon_sha256":"099ffce40596e50a9171facf13f63e1866409323a34335760a515338d70a5b87","abstract_canon_sha256":"399aac9ce9cdd32c6212a74c45c594343d1847d5f4f1a3bca1b22dd7fb4b1b17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:56.769180Z","signature_b64":"xTnZ1WPqbGoM26Xb68VKeJeNzhFMMBfA7x+/ib0YS2Rg1zKaTSOOZyoUViXBQBblTOFhCH3igqkb1nXrUpGjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fa8991d11a65bfdcf3e0837c7addcfa60ad9f5c8c23895440a715960950770f","last_reissued_at":"2026-07-05T08:31:56.768716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:56.768716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Mao, Junfeng Yang, Pengyuan Shi, Qingyuan Liu, Yun-Yun Tsai","submitted_at":"2024-06-13T21:52:49Z","abstract_excerpt":"The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works to combat Deepfakes videos have developed detectors that are highly accurate at identifying GAN-generated samples. However, the robustness of these detectors on diffusion-generated videos generated from video creation tools (e.g., SORA by OpenAI, Runway Gen-2, and Pika, etc.) is still unexplored. In this paper, we propose a novel framework for detecting videos synthesized from multiple state-of-the-art (SOTA) generative models, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09601","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/2406.09601/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":"2406.09601","created_at":"2026-07-05T08:31:56.768774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09601v1","created_at":"2026-07-05T08:31:56.768774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09601","created_at":"2026-07-05T08:31:56.768774+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6UJSHIRUZN7","created_at":"2026-07-05T08:31:56.768774+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6UJSHIRUZN73TZ6","created_at":"2026-07-05T08:31:56.768774+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6UJSHIR","created_at":"2026-07-05T08:31:56.768774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00948","citing_title":"Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10248","citing_title":"RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04029","citing_title":"ATSS: Detecting AI-Generated Videos via Anomalous Temporal Self-Similarity","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00630","citing_title":"CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J","json":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J.json","graph_json":"https://pith.science/api/pith-number/F6UJSHIRUZN73TZ6BA34PLO47J/graph.json","events_json":"https://pith.science/api/pith-number/F6UJSHIRUZN73TZ6BA34PLO47J/events.json","paper":"https://pith.science/paper/F6UJSHIR"},"agent_actions":{"view_html":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J","download_json":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J.json","view_paper":"https://pith.science/paper/F6UJSHIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09601&json=true","fetch_graph":"https://pith.science/api/pith-number/F6UJSHIRUZN73TZ6BA34PLO47J/graph.json","fetch_events":"https://pith.science/api/pith-number/F6UJSHIRUZN73TZ6BA34PLO47J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J/action/storage_attestation","attest_author":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J/action/author_attestation","sign_citation":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J/action/citation_signature","submit_replication":"https://pith.science/pith/F6UJSHIRUZN73TZ6BA34PLO47J/action/replication_record"}},"created_at":"2026-07-05T08:31:56.768774+00:00","updated_at":"2026-07-05T08:31:56.768774+00:00"}