{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IRTRKRY2N3YOSHTNZV5Y3DGV4X","short_pith_number":"pith:IRTRKRY2","canonical_record":{"source":{"id":"2503.22265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T09:29:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b971c79527b40a52f787b12d94b9371449f184476a9505e8650be45b40158a10","abstract_canon_sha256":"b132ca1e372f5d0d65b0cb22c3dc55e6b530c3c15668acf900d4c8ce164ff3e4"},"schema_version":"1.0"},"canonical_sha256":"446715471a6ef0e91e6dcd7b8d8cd5e5fe0ebd18a92f0d80495ac49f1e3703ed","source":{"kind":"arxiv","id":"2503.22265","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22265","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22265v1","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22265","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"pith_short_12","alias_value":"IRTRKRY2N3YO","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"pith_short_16","alias_value":"IRTRKRY2N3YOSHTN","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"pith_short_8","alias_value":"IRTRKRY2","created_at":"2026-07-05T10:40:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IRTRKRY2N3YOSHTNZV5Y3DGV4X","target":"record","payload":{"canonical_record":{"source":{"id":"2503.22265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T09:29:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b971c79527b40a52f787b12d94b9371449f184476a9505e8650be45b40158a10","abstract_canon_sha256":"b132ca1e372f5d0d65b0cb22c3dc55e6b530c3c15668acf900d4c8ce164ff3e4"},"schema_version":"1.0"},"canonical_sha256":"446715471a6ef0e91e6dcd7b8d8cd5e5fe0ebd18a92f0d80495ac49f1e3703ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:51.144757Z","signature_b64":"1EUJ33xizY5kfBXGkztSdM9bEawcBbNOBr/8dWim3BdSllRPW+RaxT6y7FePb7w2GyRnL8kv/vylH2ihKIBBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446715471a6ef0e91e6dcd7b8d8cd5e5fe0ebd18a92f0d80495ac49f1e3703ed","last_reissued_at":"2026-07-05T10:40:51.144264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:51.144264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.22265","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":"2026-07-05T10:40:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIa3rxaMX76xr+B5ftpsBDBbQaG2RcGdbTa0T2shX9jV1PQ6TDg5vMmHVpIi4yQ5+vFbuEeYHdLy6MapcbstCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:46:35.120437Z"},"content_sha256":"dd51bac36c174c40c2afc5cf69cb9574b720608f069678ec6307160834a68933","schema_version":"1.0","event_id":"sha256:dd51bac36c174c40c2afc5cf69cb9574b720608f069678ec6307160834a68933"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IRTRKRY2N3YOSHTNZV5Y3DGV4X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chang Liu, Chaofan Ding, Haomin Zhang, Junjie Zheng, Xinhan Di, Zihao Chen","submitted_at":"2025-03-28T09:29:08Z","abstract_excerpt":"Currently, high-quality, synchronized audio is synthesized using various multi-modal joint learning frameworks, leveraging video and optional text inputs. In the video-to-audio benchmarks, video-to-audio quality, semantic alignment, and audio-visual synchronization are effectively achieved. However, in real-world scenarios, speech and audio often coexist in videos simultaneously, and the end-to-end generation of synchronous speech and audio given video and text conditions are not well studied. Therefore, we propose an end-to-end multi-modal generation framework that simultaneously produces spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22265","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/2503.22265/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":"2026-07-05T10:40:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7i2h81iOgqjKOinzhwHIzKhFHkfxXZKuNcCcaEVnNsbrdJFsXlA18NbQHJ3Wz4yTlS+Ap45oZ2nXWmWajul3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:46:35.120951Z"},"content_sha256":"d95ce2533e95eb1f5e9eb7118fc78ede968d9b1f76a15e7c124809fecf3d0c20","schema_version":"1.0","event_id":"sha256:d95ce2533e95eb1f5e9eb7118fc78ede968d9b1f76a15e7c124809fecf3d0c20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/bundle.json","state_url":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/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":"2026-08-06T22:46:35Z","links":{"resolver":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X","bundle":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/bundle.json","state":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IRTRKRY2N3YOSHTNZV5Y3DGV4X","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":"b132ca1e372f5d0d65b0cb22c3dc55e6b530c3c15668acf900d4c8ce164ff3e4","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T09:29:08Z","title_canon_sha256":"b971c79527b40a52f787b12d94b9371449f184476a9505e8650be45b40158a10"},"schema_version":"1.0","source":{"id":"2503.22265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22265","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22265v1","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22265","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"pith_short_12","alias_value":"IRTRKRY2N3YO","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"pith_short_16","alias_value":"IRTRKRY2N3YOSHTN","created_at":"2026-07-05T10:40:51Z"},{"alias_kind":"pith_short_8","alias_value":"IRTRKRY2","created_at":"2026-07-05T10:40:51Z"}],"graph_snapshots":[{"event_id":"sha256:d95ce2533e95eb1f5e9eb7118fc78ede968d9b1f76a15e7c124809fecf3d0c20","target":"graph","created_at":"2026-07-05T10:40:51Z","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/2503.22265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, high-quality, synchronized audio is synthesized using various multi-modal joint learning frameworks, leveraging video and optional text inputs. In the video-to-audio benchmarks, video-to-audio quality, semantic alignment, and audio-visual synchronization are effectively achieved. However, in real-world scenarios, speech and audio often coexist in videos simultaneously, and the end-to-end generation of synchronous speech and audio given video and text conditions are not well studied. Therefore, we propose an end-to-end multi-modal generation framework that simultaneously produces spe","authors_text":"Chang Liu, Chaofan Ding, Haomin Zhang, Junjie Zheng, Xinhan Di, Zihao Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T09:29:08Z","title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22265","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:dd51bac36c174c40c2afc5cf69cb9574b720608f069678ec6307160834a68933","target":"record","created_at":"2026-07-05T10:40:51Z","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":"b132ca1e372f5d0d65b0cb22c3dc55e6b530c3c15668acf900d4c8ce164ff3e4","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T09:29:08Z","title_canon_sha256":"b971c79527b40a52f787b12d94b9371449f184476a9505e8650be45b40158a10"},"schema_version":"1.0","source":{"id":"2503.22265","kind":"arxiv","version":1}},"canonical_sha256":"446715471a6ef0e91e6dcd7b8d8cd5e5fe0ebd18a92f0d80495ac49f1e3703ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"446715471a6ef0e91e6dcd7b8d8cd5e5fe0ebd18a92f0d80495ac49f1e3703ed","first_computed_at":"2026-07-05T10:40:51.144264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:51.144264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1EUJ33xizY5kfBXGkztSdM9bEawcBbNOBr/8dWim3BdSllRPW+RaxT6y7FePb7w2GyRnL8kv/vylH2ihKIBBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:51.144757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd51bac36c174c40c2afc5cf69cb9574b720608f069678ec6307160834a68933","sha256:d95ce2533e95eb1f5e9eb7118fc78ede968d9b1f76a15e7c124809fecf3d0c20"],"state_sha256":"91f46a406af6757caf79031065d7166f5f9fc7977be18c09f214c2db6ee22172"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VcyZpdYB/OZnILuclBMCs42TSrqAz5/GoreZEG9pi3TaY30dyld5nr8rho1r5Z67n4EL95t8RUMQNbKQswDfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:46:35.124360Z","bundle_sha256":"64340f077bac3d87c2b592e71d24d234fde551585f96d032b1d435c7f9b5f383"}}