{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JZYGYM3XSOLRJR2PQRHMVH76TD","short_pith_number":"pith:JZYGYM3X","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"},"canonical_sha256":"4e706c3377939714c74f844eca9ffe98ed252602e32ab4f9ae9512fb5edbff64","source":{"kind":"arxiv","id":"2506.00830","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00830","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00830v1","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00830","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"JZYGYM3XSOLR","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_16","alias_value":"JZYGYM3XSOLRJR2P","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_8","alias_value":"JZYGYM3X","created_at":"2026-07-05T11:13:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JZYGYM3XSOLRJR2PQRHMVH76TD","target":"record","payload":{"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"},"canonical_sha256":"4e706c3377939714c74f844eca9ffe98ed252602e32ab4f9ae9512fb5edbff64","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"},"source_kind":"arxiv","source_id":"2506.00830","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnFho5z6/kDAZxrsgmUX0OQ2NyvN6/0QgDKBU6ePIu9gmsojybfgnBlGx2JNfk6h1rGgq9s88mClZ/HtDSKWDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:12:40.577720Z"},"content_sha256":"a18ee2163893569311d3b0ab5af29db1634f15fada294f70fb2aae91eb3c7d06","schema_version":"1.0","event_id":"sha256:a18ee2163893569311d3b0ab5af29db1634f15fada294f70fb2aae91eb3c7d06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JZYGYM3XSOLRJR2PQRHMVH76TD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6yizAwjvD4CbK59R4+pVN8yB1efAkwKONGnVdV9MS7K36aFwsAHKfLDkmQMSkDU8UdRRy0ikAPkHsynVeuADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:12:40.578263Z"},"content_sha256":"4a479d733ce95d4320b171d00259f1a79d2d132e81ab9e06dc2fe0a5dbb86a8d","schema_version":"1.0","event_id":"sha256:4a479d733ce95d4320b171d00259f1a79d2d132e81ab9e06dc2fe0a5dbb86a8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/bundle.json","state_url":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T00:12:40Z","links":{"resolver":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD","bundle":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/bundle.json","state":"https://pith.science/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JZYGYM3XSOLRJR2PQRHMVH76TD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JZYGYM3XSOLRJR2PQRHMVH76TD","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":"8ae1b0454cc03306898cd15117ed584778144a3c5a0d1a637984420668328219","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T04:27:13Z","title_canon_sha256":"36c898095e9f119369c11f12993063ca97918c140701eda5ff589b0d99e7439b"},"schema_version":"1.0","source":{"id":"2506.00830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00830","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00830v1","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00830","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"JZYGYM3XSOLR","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_16","alias_value":"JZYGYM3XSOLRJR2P","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_8","alias_value":"JZYGYM3X","created_at":"2026-07-05T11:13:41Z"}],"graph_snapshots":[{"event_id":"sha256:4a479d733ce95d4320b171d00259f1a79d2d132e81ab9e06dc2fe0a5dbb86a8d","target":"graph","created_at":"2026-07-05T11:13:41Z","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/2506.00830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baoxuan Gu, Debang Li, Di Qiu, Guibin Chen, Hao Jiang, Jiahua Wang, Jialin Bai, Mingyuan Fan, Yahui Zhou, Youqiang Zhang, Zhengcong Fei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T04:27:13Z","title":"SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00830","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:a18ee2163893569311d3b0ab5af29db1634f15fada294f70fb2aae91eb3c7d06","target":"record","created_at":"2026-07-05T11:13:41Z","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":"8ae1b0454cc03306898cd15117ed584778144a3c5a0d1a637984420668328219","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T04:27:13Z","title_canon_sha256":"36c898095e9f119369c11f12993063ca97918c140701eda5ff589b0d99e7439b"},"schema_version":"1.0","source":{"id":"2506.00830","kind":"arxiv","version":1}},"canonical_sha256":"4e706c3377939714c74f844eca9ffe98ed252602e32ab4f9ae9512fb5edbff64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e706c3377939714c74f844eca9ffe98ed252602e32ab4f9ae9512fb5edbff64","first_computed_at":"2026-07-05T11:13:41.247660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:41.247660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O67BSuCL4dXube6M5UjwtGiC4Qn0KODKuH/1ZN+6UvCZfXfS3cxnLqlRZEtKf5hrQbYC/yprCRE6OWlWnrPqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:41.248473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a18ee2163893569311d3b0ab5af29db1634f15fada294f70fb2aae91eb3c7d06","sha256:4a479d733ce95d4320b171d00259f1a79d2d132e81ab9e06dc2fe0a5dbb86a8d"],"state_sha256":"8feaec8b66eadb49f0a1968c615f6a820bbea108f635c813b2c4622a3407dfd1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qWuOkOXdUlbYQbQPiREB9tcCZrgxCoTOh0feHZG2SXue2GjudkntDrtqYsxfpzFgerFkLUqnKeHoOp8oomIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:12:40.582156Z","bundle_sha256":"6555d912fad1fb3f9da6737a1108ab47667fc18f9b97f6922543b419e5f1cd76"}}