{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JTH5MMMNUMZIYIW2RBZVS3YYTV","short_pith_number":"pith:JTH5MMMN","schema_version":"1.0","canonical_sha256":"4ccfd6318da3328c22da8873596f189d7be26d82eda090a3939d4db45ddb1cb2","source":{"kind":"arxiv","id":"2409.07649","version":1},"attestation_state":"computed","paper":{"title":"DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxu Zhang, Hamza Daruger, Steven Hogue, Xiaohu Guo, Yapeng Tian","submitted_at":"2024-09-11T22:31:55Z","abstract_excerpt":"Audio-driven talking video generation has advanced significantly, but existing methods often depend on video-to-video translation techniques and traditional generative networks like GANs and they typically generate taking heads and co-speech gestures separately, leading to less coherent outputs. Furthermore, the gestures produced by these methods often appear overly smooth or subdued, lacking in diversity, and many gesture-centric approaches do not integrate talking head generation. To address these limitations, we introduce DiffTED, a new approach for one-shot audio-driven TED-style talking v"},"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":"2409.07649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-11T22:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"08a5387328d0ab721c5399cfca159d42c3d719f9b09da1aa963eacc72415a081","abstract_canon_sha256":"268cd288be0e43643962e5cf556970a635981a6a9960daeeb6cced361afdfa50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:13.019853Z","signature_b64":"flzj/Snr3K2KyVooFt/krz0tFWemIX0ftMezGK/L9wyub8+rFioyNtACieXJqhlhfoqGWOCy0+KYvkoO+AcgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ccfd6318da3328c22da8873596f189d7be26d82eda090a3939d4db45ddb1cb2","last_reissued_at":"2026-07-05T09:06:13.019447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:13.019447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffTED: One-shot Audio-driven TED Talk Video Generation with Diffusion-based Co-speech Gestures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenxu Zhang, Hamza Daruger, Steven Hogue, Xiaohu Guo, Yapeng Tian","submitted_at":"2024-09-11T22:31:55Z","abstract_excerpt":"Audio-driven talking video generation has advanced significantly, but existing methods often depend on video-to-video translation techniques and traditional generative networks like GANs and they typically generate taking heads and co-speech gestures separately, leading to less coherent outputs. Furthermore, the gestures produced by these methods often appear overly smooth or subdued, lacking in diversity, and many gesture-centric approaches do not integrate talking head generation. To address these limitations, we introduce DiffTED, a new approach for one-shot audio-driven TED-style talking v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07649","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/2409.07649/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":"2409.07649","created_at":"2026-07-05T09:06:13.019510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07649v1","created_at":"2026-07-05T09:06:13.019510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07649","created_at":"2026-07-05T09:06:13.019510+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTH5MMMNUMZI","created_at":"2026-07-05T09:06:13.019510+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTH5MMMNUMZIYIW2","created_at":"2026-07-05T09:06:13.019510+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTH5MMMN","created_at":"2026-07-05T09:06:13.019510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV","json":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV.json","graph_json":"https://pith.science/api/pith-number/JTH5MMMNUMZIYIW2RBZVS3YYTV/graph.json","events_json":"https://pith.science/api/pith-number/JTH5MMMNUMZIYIW2RBZVS3YYTV/events.json","paper":"https://pith.science/paper/JTH5MMMN"},"agent_actions":{"view_html":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV","download_json":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV.json","view_paper":"https://pith.science/paper/JTH5MMMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07649&json=true","fetch_graph":"https://pith.science/api/pith-number/JTH5MMMNUMZIYIW2RBZVS3YYTV/graph.json","fetch_events":"https://pith.science/api/pith-number/JTH5MMMNUMZIYIW2RBZVS3YYTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV/action/storage_attestation","attest_author":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV/action/author_attestation","sign_citation":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV/action/citation_signature","submit_replication":"https://pith.science/pith/JTH5MMMNUMZIYIW2RBZVS3YYTV/action/replication_record"}},"created_at":"2026-07-05T09:06:13.019510+00:00","updated_at":"2026-07-05T09:06:13.019510+00:00"}