{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JZYGYM3XSOLRJR2PQRHMVH76TD","short_pith_number":"pith:JZYGYM3X","schema_version":"1.0","canonical_sha256":"4e706c3377939714c74f844eca9ffe98ed252602e32ab4f9ae9512fb5edbff64","source":{"kind":"arxiv","id":"2506.00830","version":1},"attestation_state":"computed","paper":{"title":"SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoxuan Gu, Debang Li, Di Qiu, Guibin Chen, Hao Jiang, Jiahua Wang, Jialin Bai, Mingyuan Fan, Yahui Zhou, Youqiang Zhang, Zhengcong Fei","submitted_at":"2025-06-01T04:27:13Z","abstract_excerpt":"The generation and editing of audio-conditioned talking portraits guided by multimodal inputs, including text, images, and videos, remains under explored. In this paper, we present SkyReels-Audio, a unified framework for synthesizing high-fidelity and temporally coherent talking portrait videos. Built upon pretrained video diffusion transformers, our framework supports infinite-length generation and editing, while enabling diverse and controllable conditioning through multimodal inputs. We employ a hybrid curriculum learning strategy to progressively align audio with facial motion, enabling fi"},"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":"2506.00830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T04:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"36c898095e9f119369c11f12993063ca97918c140701eda5ff589b0d99e7439b","abstract_canon_sha256":"8ae1b0454cc03306898cd15117ed584778144a3c5a0d1a637984420668328219"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:41.248473Z","signature_b64":"O67BSuCL4dXube6M5UjwtGiC4Qn0KODKuH/1ZN+6UvCZfXfS3cxnLqlRZEtKf5hrQbYC/yprCRE6OWlWnrPqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e706c3377939714c74f844eca9ffe98ed252602e32ab4f9ae9512fb5edbff64","last_reissued_at":"2026-07-05T11:13:41.247660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:41.247660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoxuan Gu, Debang Li, Di Qiu, Guibin Chen, Hao Jiang, Jiahua Wang, Jialin Bai, Mingyuan Fan, Yahui Zhou, Youqiang Zhang, Zhengcong Fei","submitted_at":"2025-06-01T04:27:13Z","abstract_excerpt":"The generation and editing of audio-conditioned talking portraits guided by multimodal inputs, including text, images, and videos, remains under explored. In this paper, we present SkyReels-Audio, a unified framework for synthesizing high-fidelity and temporally coherent talking portrait videos. Built upon pretrained video diffusion transformers, our framework supports infinite-length generation and editing, while enabling diverse and controllable conditioning through multimodal inputs. We employ a hybrid curriculum learning strategy to progressively align audio with facial motion, enabling fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00830","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/2506.00830/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":"2506.00830","created_at":"2026-07-05T11:13:41.247721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00830v1","created_at":"2026-07-05T11:13:41.247721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00830","created_at":"2026-07-05T11:13:41.247721+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZYGYM3XSOLR","created_at":"2026-07-05T11:13:41.247721+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZYGYM3XSOLRJR2P","created_at":"2026-07-05T11:13:41.247721+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZYGYM3X","created_at":"2026-07-05T11:13:41.247721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14033","citing_title":"InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD","json":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD.json","graph_json":"https://pith.science/api/pith-number/JZYGYM3XSOLRJR2PQRHMVH76TD/graph.json","events_json":"https://pith.science/api/pith-number/JZYGYM3XSOLRJR2PQRHMVH76TD/events.json","paper":"https://pith.science/paper/JZYGYM3X"},"agent_actions":{"view_html":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD","download_json":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD.json","view_paper":"https://pith.science/paper/JZYGYM3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00830&json=true","fetch_graph":"https://pith.science/api/pith-number/JZYGYM3XSOLRJR2PQRHMVH76TD/graph.json","fetch_events":"https://pith.science/api/pith-number/JZYGYM3XSOLRJR2PQRHMVH76TD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/action/storage_attestation","attest_author":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/action/author_attestation","sign_citation":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/action/citation_signature","submit_replication":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/action/replication_record"}},"created_at":"2026-07-05T11:13:41.247721+00:00","updated_at":"2026-07-05T11:13:41.247721+00:00"}