{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6KEIHP2MCDJE6OIST6QVMWT3E4","short_pith_number":"pith:6KEIHP2M","canonical_record":{"source":{"id":"2507.10109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-14T09:50:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"318308457e35c2c2db0f2784be8ba5b485e9884f12f6f7fb149fe55659431fc9","abstract_canon_sha256":"b270e60c24f21b97143514ac736106a482843e905a4a14c3b3ac2c6665d1ece9"},"schema_version":"1.0"},"canonical_sha256":"f28883bf4c10d24f39129fa1565a7b27044f24e3c4cde158025748c50c737bce","source":{"kind":"arxiv","id":"2507.10109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10109","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10109v1","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10109","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"6KEIHP2MCDJE","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"pith_short_16","alias_value":"6KEIHP2MCDJE6OIS","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"pith_short_8","alias_value":"6KEIHP2M","created_at":"2026-07-05T11:36:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6KEIHP2MCDJE6OIST6QVMWT3E4","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-14T09:50:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"318308457e35c2c2db0f2784be8ba5b485e9884f12f6f7fb149fe55659431fc9","abstract_canon_sha256":"b270e60c24f21b97143514ac736106a482843e905a4a14c3b3ac2c6665d1ece9"},"schema_version":"1.0"},"canonical_sha256":"f28883bf4c10d24f39129fa1565a7b27044f24e3c4cde158025748c50c737bce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:45.241193Z","signature_b64":"YkgU4eKqNlD1HsF4kFURB9xbTMo5Q8+0tNegcwC6mCCoRBBodYrtPOQAB7YDqJcdVX8S729npoRrFTPJbVDPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f28883bf4c10d24f39129fa1565a7b27044f24e3c4cde158025748c50c737bce","last_reissued_at":"2026-07-05T11:36:45.240653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:45.240653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10109","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":"2026-07-05T11:36:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w0CjsOl3Duy80AbgypVeS4jAye8JWpPmGWjkzjQVCkdI7bK2U2SoULy7ReUWN/xuFgLX8EVbRYywMfE9Xq1OBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:56:12.405009Z"},"content_sha256":"76402e102904555d59156d4a42516d6ec3a9510cde996cf5c25131402bc425bf","schema_version":"1.0","event_id":"sha256:76402e102904555d59156d4a42516d6ec3a9510cde996cf5c25131402bc425bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6KEIHP2MCDJE6OIST6QVMWT3E4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chaofan Ding, Haohe Liu, Junjie Zheng, Lei Xie, Wenjie Tian, Xinfa Zhu, Xinhan Di, Zhixian Zhao, Zihao Chen","submitted_at":"2025-07-14T09:50:53Z","abstract_excerpt":"While recent video-to-audio (V2A) models can generate realistic background audio from visual input, they largely overlook speech, an essential part of many video soundtracks. This paper proposes a new task, video-to-soundtrack (V2ST) generation, which aims to jointly produce synchronized background audio and speech within a unified framework. To tackle V2ST, we introduce DualDub, a unified framework built on a multimodal language model that integrates a multimodal encoder, a cross-modal aligner, and dual decoding heads for simultaneous background audio and speech generation. Specifically, our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10109","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/2507.10109/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":"2026-07-05T11:36:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVLRFCUa8obkg3meOkwSX7KTaiXRNb0FYhO+8nhfGRnIqauXhr56t0kLmh4qVolE3cysFO/RrMo5WwRv44WPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:56:12.405529Z"},"content_sha256":"697f9fe33bb6167ed07ab03481ae178a90cf16ae44b393b1f834e612c13b6e9d","schema_version":"1.0","event_id":"sha256:697f9fe33bb6167ed07ab03481ae178a90cf16ae44b393b1f834e612c13b6e9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KEIHP2MCDJE6OIST6QVMWT3E4/bundle.json","state_url":"https://pith.science/pith/6KEIHP2MCDJE6OIST6QVMWT3E4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KEIHP2MCDJE6OIST6QVMWT3E4/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":"2026-08-09T05:56:12Z","links":{"resolver":"https://pith.science/pith/6KEIHP2MCDJE6OIST6QVMWT3E4","bundle":"https://pith.science/pith/6KEIHP2MCDJE6OIST6QVMWT3E4/bundle.json","state":"https://pith.science/pith/6KEIHP2MCDJE6OIST6QVMWT3E4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KEIHP2MCDJE6OIST6QVMWT3E4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6KEIHP2MCDJE6OIST6QVMWT3E4","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":"b270e60c24f21b97143514ac736106a482843e905a4a14c3b3ac2c6665d1ece9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-14T09:50:53Z","title_canon_sha256":"318308457e35c2c2db0f2784be8ba5b485e9884f12f6f7fb149fe55659431fc9"},"schema_version":"1.0","source":{"id":"2507.10109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10109","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10109v1","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10109","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"6KEIHP2MCDJE","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"pith_short_16","alias_value":"6KEIHP2MCDJE6OIS","created_at":"2026-07-05T11:36:45Z"},{"alias_kind":"pith_short_8","alias_value":"6KEIHP2M","created_at":"2026-07-05T11:36:45Z"}],"graph_snapshots":[{"event_id":"sha256:697f9fe33bb6167ed07ab03481ae178a90cf16ae44b393b1f834e612c13b6e9d","target":"graph","created_at":"2026-07-05T11:36:45Z","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/2507.10109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent video-to-audio (V2A) models can generate realistic background audio from visual input, they largely overlook speech, an essential part of many video soundtracks. This paper proposes a new task, video-to-soundtrack (V2ST) generation, which aims to jointly produce synchronized background audio and speech within a unified framework. To tackle V2ST, we introduce DualDub, a unified framework built on a multimodal language model that integrates a multimodal encoder, a cross-modal aligner, and dual decoding heads for simultaneous background audio and speech generation. Specifically, our ","authors_text":"Chaofan Ding, Haohe Liu, Junjie Zheng, Lei Xie, Wenjie Tian, Xinfa Zhu, Xinhan Di, Zhixian Zhao, Zihao Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-14T09:50:53Z","title":"DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10109","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":"sha256:76402e102904555d59156d4a42516d6ec3a9510cde996cf5c25131402bc425bf","target":"record","created_at":"2026-07-05T11:36:45Z","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":"b270e60c24f21b97143514ac736106a482843e905a4a14c3b3ac2c6665d1ece9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-14T09:50:53Z","title_canon_sha256":"318308457e35c2c2db0f2784be8ba5b485e9884f12f6f7fb149fe55659431fc9"},"schema_version":"1.0","source":{"id":"2507.10109","kind":"arxiv","version":1}},"canonical_sha256":"f28883bf4c10d24f39129fa1565a7b27044f24e3c4cde158025748c50c737bce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f28883bf4c10d24f39129fa1565a7b27044f24e3c4cde158025748c50c737bce","first_computed_at":"2026-07-05T11:36:45.240653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:45.240653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YkgU4eKqNlD1HsF4kFURB9xbTMo5Q8+0tNegcwC6mCCoRBBodYrtPOQAB7YDqJcdVX8S729npoRrFTPJbVDPCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:45.241193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76402e102904555d59156d4a42516d6ec3a9510cde996cf5c25131402bc425bf","sha256:697f9fe33bb6167ed07ab03481ae178a90cf16ae44b393b1f834e612c13b6e9d"],"state_sha256":"52c85c0df274f747add83c505c50b639264fb7fbbf92e4a40b1da26b40a873fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EnimV4CEnMGQR075jV3tOGKxjE0EtXDEN8NmnhjF/4tp87x3ki09LolAjrzUH8l0lK+OHt9c0I9+n19x42euDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:56:12.410408Z","bundle_sha256":"9d56805c8120a5fda0264cd24758619bdd5b2f98c585b4cca1e9eaeda92e9954"}}