{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CRZPAPKXJPOXLUEXGPFLJY3DFI","short_pith_number":"pith:CRZPAPKX","canonical_record":{"source":{"id":"2510.01284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-09-30T21:03:50Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"eaf2258893cf6399b57c826c3db6ad000d9d95ddfa1b691dfd5fb7a996ec484a","abstract_canon_sha256":"7ce7d15b63daa02ae8b8851c614d09cbf19336f1adae2c17ef4b109714a5f876"},"schema_version":"1.0"},"canonical_sha256":"1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4","source":{"kind":"arxiv","id":"2510.01284","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01284","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01284v1","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01284","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"CRZPAPKXJPOX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CRZPAPKXJPOXLUEX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CRZPAPKX","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CRZPAPKXJPOXLUEXGPFLJY3DFI","target":"record","payload":{"canonical_record":{"source":{"id":"2510.01284","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-09-30T21:03:50Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"eaf2258893cf6399b57c826c3db6ad000d9d95ddfa1b691dfd5fb7a996ec484a","abstract_canon_sha256":"7ce7d15b63daa02ae8b8851c614d09cbf19336f1adae2c17ef4b109714a5f876"},"schema_version":"1.0"},"canonical_sha256":"1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.035782Z","signature_b64":"0/e/j6Y++t3lvnDioOpVMg84/K0qtCo7JyGgy9BZ9N/ETRgCSoSdgJ0HuU+rXrM4NmB0TeNpTM8deMP1KGJpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4","last_reissued_at":"2026-05-17T23:38:46.035192Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.035192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.01284","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":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8yUxvqn4s5WY3hqy4EsuFQzrGNKuNFTaQNol2x/3/2fpeM8bHZJ8TUAKUlXpUuhGC/4qBmakVu5xA8gG5BrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T09:41:11.767978Z"},"content_sha256":"e47650ebb131049908f749da95b2982638fdc42f0c583a85c079ce0fcf06607d","schema_version":"1.0","event_id":"sha256:e47650ebb131049908f749da95b2982638fdc42f0c583a85c079ce0fcf06607d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CRZPAPKXJPOXLUEXGPFLJY3DFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block.","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Calder Katyal, Chetwin Low, Weimin Wang","submitted_at":"2025-09-30T21:03:50Z","abstract_excerpt":"Audio-video generation has often relied on complex multi-stage architectures or sequential synthesis of sound and visuals. We introduce Ovi, a unified paradigm for audio-video generation that models the two modalities as a single generative process. By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment. To facilitate fine-grained multimodal fusion modeling, we initialize an audio tower with an architecture identical to that of a strong pretrained video model. Trained from scratch on hund"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That initializing an audio tower with an architecture identical to a strong pretrained video model and then jointly training via bidirectional cross-attention on a vast video corpus will produce reliable cross-modal timing and semantic alignment without additional alignment losses or post-processing.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0a6ffc5657c0aa9898b238dbae0f54c6ad4605fe468ffdffa0f699d84adce477"},"source":{"id":"2510.01284","kind":"arxiv","version":1},"verdict":{"id":"cd90296c-aac0-4d45-af8b-ff608b2ecbbf","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T00:58:33.434002Z","strongest_claim":"By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment.","one_line_summary":"A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That initializing an audio tower with an architecture identical to a strong pretrained video model and then jointly training via bidirectional cross-attention on a vast video corpus will produce reliable cross-modal timing and semantic alignment without additional alignment losses or post-processing.","pith_extraction_headline":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block."},"references":{"count":20,"sample":[{"doi":"","year":null,"title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","work_id":"6e88ee95-1133-4302-a142-cdf8f9456a8d","ref_index":1,"cited_arxiv_id":"2406.02430","is_internal_anchor":true},{"doi":"","year":2025,"title":"com/research/video-generation-models-as-world-simulators","work_id":"e01a4ca3-169f-41c9-adf9-19a9dd64a994","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"HuMo: Human-centric video generation via collaborative multi-modal conditioning","work_id":"313111a9-b492-44f5-bf1f-6b5c2c642abf","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","work_id":"e5ad925a-4045-49b5-b301-208bcbf3eca8","ref_index":4,"cited_arxiv_id":"2407.05407","is_internal_anchor":true},{"doi":"","year":null,"title":"Ace-step: A step towards music generation foundation model.arXiv preprint arXiv:2506.00045","work_id":"0d4831b4-71c3-4405-b540-1683d26109f6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":20,"snapshot_sha256":"82668244fa647f84970ed0b7ad60dd132801c0e8ed2357f8d3cfae7048cb0fe5","internal_anchors":6},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dcc63dfbc2e0470515064e223638b706ac28e96ca692fa011a4f85b128f3a7aa"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"cd90296c-aac0-4d45-af8b-ff608b2ecbbf"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eD8rBbE3MMHLWA//GDPgMOxetowFbOQUGqculkVTQfYE22TCBHye6116F0/npW1ZzPvNG3nWeaVmIW4S8bz7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T09:41:11.768922Z"},"content_sha256":"572b7e122dff726cd0f8633d62083c1b18296a3f2dd94885c499c320babfdadf","schema_version":"1.0","event_id":"sha256:572b7e122dff726cd0f8633d62083c1b18296a3f2dd94885c499c320babfdadf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/bundle.json","state_url":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/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":"2026-05-23T09:41:11Z","links":{"resolver":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI","bundle":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/bundle.json","state":"https://pith.science/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRZPAPKXJPOXLUEXGPFLJY3DFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CRZPAPKXJPOXLUEXGPFLJY3DFI","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":"7ce7d15b63daa02ae8b8851c614d09cbf19336f1adae2c17ef4b109714a5f876","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-09-30T21:03:50Z","title_canon_sha256":"eaf2258893cf6399b57c826c3db6ad000d9d95ddfa1b691dfd5fb7a996ec484a"},"schema_version":"1.0","source":{"id":"2510.01284","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01284","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01284v1","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01284","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"CRZPAPKXJPOX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CRZPAPKXJPOXLUEX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CRZPAPKX","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:572b7e122dff726cd0f8633d62083c1b18296a3f2dd94885c499c320babfdadf","target":"graph","created_at":"2026-05-17T23:38:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That initializing an audio tower with an architecture identical to a strong pretrained video model and then jointly training via bidirectional cross-attention on a vast video corpus will produce reliable cross-modal timing and semantic alignment without additional alignment losses or post-processing."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block."}],"snapshot_sha256":"0a6ffc5657c0aa9898b238dbae0f54c6ad4605fe468ffdffa0f699d84adce477"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"dcc63dfbc2e0470515064e223638b706ac28e96ca692fa011a4f85b128f3a7aa"},"paper":{"abstract_excerpt":"Audio-video generation has often relied on complex multi-stage architectures or sequential synthesis of sound and visuals. We introduce Ovi, a unified paradigm for audio-video generation that models the two modalities as a single generative process. By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment. To facilitate fine-grained multimodal fusion modeling, we initialize an audio tower with an architecture identical to that of a strong pretrained video model. Trained from scratch on hund","authors_text":"Calder Katyal, Chetwin Low, Weimin Wang","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-09-30T21:03:50Z","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation"},"references":{"count":20,"internal_anchors":6,"resolved_work":20,"sample":[{"cited_arxiv_id":"2406.02430","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","work_id":"6e88ee95-1133-4302-a142-cdf8f9456a8d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"com/research/video-generation-models-as-world-simulators","work_id":"e01a4ca3-169f-41c9-adf9-19a9dd64a994","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"HuMo: Human-centric video generation via collaborative multi-modal conditioning","work_id":"313111a9-b492-44f5-bf1f-6b5c2c642abf","year":null},{"cited_arxiv_id":"2407.05407","doi":"","is_internal_anchor":true,"ref_index":4,"title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","work_id":"e5ad925a-4045-49b5-b301-208bcbf3eca8","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Ace-step: A step towards music generation foundation model.arXiv preprint arXiv:2506.00045","work_id":"0d4831b4-71c3-4405-b540-1683d26109f6","year":null}],"snapshot_sha256":"82668244fa647f84970ed0b7ad60dd132801c0e8ed2357f8d3cfae7048cb0fe5"},"source":{"id":"2510.01284","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-17T00:58:33.434002Z","id":"cd90296c-aac0-4d45-af8b-ff608b2ecbbf","model_set":{"reader":"grok-4.3"},"one_line_summary":"A single generative model uses twin DiT backbones with blockwise cross-attention and scaled-RoPE timing exchange to synthesize synchronized audio-video directly.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Ovi generates audio and video together in one process by fusing twin identical diffusion transformers block by block.","strongest_claim":"By using blockwise cross-modal fusion of twin-DiT modules, Ovi achieves natural synchronization and removes the need for separate pipelines or post hoc alignment.","weakest_assumption":"That initializing an audio tower with an architecture identical to a strong pretrained video model and then jointly training via bidirectional cross-attention on a vast video corpus will produce reliable cross-modal timing and semantic alignment without additional alignment losses or post-processing."}},"verdict_id":"cd90296c-aac0-4d45-af8b-ff608b2ecbbf"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e47650ebb131049908f749da95b2982638fdc42f0c583a85c079ce0fcf06607d","target":"record","created_at":"2026-05-17T23:38:46Z","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":"7ce7d15b63daa02ae8b8851c614d09cbf19336f1adae2c17ef4b109714a5f876","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-09-30T21:03:50Z","title_canon_sha256":"eaf2258893cf6399b57c826c3db6ad000d9d95ddfa1b691dfd5fb7a996ec484a"},"schema_version":"1.0","source":{"id":"2510.01284","kind":"arxiv","version":1}},"canonical_sha256":"1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1472f03d574bdd75d09733cab4e3632a17170d01c6e39b857b36a5aa06a2afc4","first_computed_at":"2026-05-17T23:38:46.035192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.035192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0/e/j6Y++t3lvnDioOpVMg84/K0qtCo7JyGgy9BZ9N/ETRgCSoSdgJ0HuU+rXrM4NmB0TeNpTM8deMP1KGJpCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.035782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.01284","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e47650ebb131049908f749da95b2982638fdc42f0c583a85c079ce0fcf06607d","sha256:572b7e122dff726cd0f8633d62083c1b18296a3f2dd94885c499c320babfdadf"],"state_sha256":"ecca5653196d25333c27f73c12e4fe7b431924548707a5b964d72b530f893cab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TgH6Qa1huAjywKBZ1jmbS9rf2fFBlt/FtvJINhBqT3hLowQdHIVsF+Zwgg6Fh0Q56A4mRe66hTXXC+CE0tAsBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T09:41:11.773305Z","bundle_sha256":"90e88ba9de528cfbbb80b582ba71ad32a8cd873015877bd7dddec0dea9f46a01"}}