{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QU3PQDQBZPG2O4R7WXCLCB35NS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"60b7879d271eef4bd51f05d72d042c11b91f870feb0ab4233deac5c09b558f3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T14:31:20Z","title_canon_sha256":"4c5b1a2e82205c094037ee46dca1ac3eeeb30c8c34e39a6276029fa7693c0efb"},"schema_version":"1.0","source":{"id":"2502.17198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17198","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17198v1","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17198","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"QU3PQDQBZPG2","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"pith_short_16","alias_value":"QU3PQDQBZPG2O4R7","created_at":"2026-07-05T10:19:07Z"},{"alias_kind":"pith_short_8","alias_value":"QU3PQDQB","created_at":"2026-07-05T10:19:07Z"}],"graph_snapshots":[{"event_id":"sha256:449c197496ff729419311ee9d68b551cb6796f26179caec30d4d1e0da3d4d161","target":"graph","created_at":"2026-07-05T10:19:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.17198/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Dimitra, a novel framework for audio-driven talking head generation, streamlined to learn lip motion, facial expression, as well as head pose motion. Specifically, we train a conditional Motion Diffusion Transformer (cMDT) by modeling facial motion sequences with 3D representation. We condition the cMDT with only two input signals, an audio-sequence, as well as a reference facial image. By extracting additional features directly from audio, Dimitra is able to increase quality and realism of generated videos. In particular, phoneme sequences contribute to the realism of lip motion, w","authors_text":"Antitza Dantcheva, Baptiste Chopin, Pranav Balaji, Tashvik Dhamija, Yaohui Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T14:31:20Z","title":"Dimitra: Audio-driven Diffusion model for Expressive Talking Head Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17198","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:74a0d6c0d2c605b0de5727bf552adb7b497c7203b8846290b244da3bb9897155","target":"record","created_at":"2026-07-05T10:19:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"60b7879d271eef4bd51f05d72d042c11b91f870feb0ab4233deac5c09b558f3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T14:31:20Z","title_canon_sha256":"4c5b1a2e82205c094037ee46dca1ac3eeeb30c8c34e39a6276029fa7693c0efb"},"schema_version":"1.0","source":{"id":"2502.17198","kind":"arxiv","version":1}},"canonical_sha256":"8536f80e01cbcda7723fb5c4b1077d6cbc20e49eea59c9dfd584c8d3e11f097c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8536f80e01cbcda7723fb5c4b1077d6cbc20e49eea59c9dfd584c8d3e11f097c","first_computed_at":"2026-07-05T10:19:07.076803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:07.076803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LyLLDJcL6do2O5i/Pd4E+4a/6BkAzKjeyGYyN9Ry3KFV8TjcmwiKY7OJZhfC/V2o7bjedA2cY03N9N5KUE15BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:07.077362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74a0d6c0d2c605b0de5727bf552adb7b497c7203b8846290b244da3bb9897155","sha256:449c197496ff729419311ee9d68b551cb6796f26179caec30d4d1e0da3d4d161"],"state_sha256":"4c545d8e94fc9d8863fa8d767f9bfdeaa6c2b0cfe9a5a53ea2dd7880d7da7c8a"}