{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SKKICACFLU4XO5ACHITALIT72N","short_pith_number":"pith:SKKICACF","canonical_record":{"source":{"id":"2604.19679","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T16:57:23Z","cross_cats_sorted":[],"title_canon_sha256":"69835bb041f7ce804938e1fb7534703948c8edf0ffbc5eca0466f7b245d9a570","abstract_canon_sha256":"2d000907476a101831f0f4775792a31aabe6f4913c59ef9d3c62d2d6f26442ac"},"schema_version":"1.0"},"canonical_sha256":"92948100455d397774023a2605a27fd37cf7541a89d4164e9619ae6a3230b993","source":{"kind":"arxiv","id":"2604.19679","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.19679","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2604.19679v3","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19679","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"SKKICACFLU4X","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"SKKICACFLU4XO5AC","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"SKKICACF","created_at":"2026-06-30T02:18:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SKKICACFLU4XO5ACHITALIT72N","target":"record","payload":{"canonical_record":{"source":{"id":"2604.19679","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T16:57:23Z","cross_cats_sorted":[],"title_canon_sha256":"69835bb041f7ce804938e1fb7534703948c8edf0ffbc5eca0466f7b245d9a570","abstract_canon_sha256":"2d000907476a101831f0f4775792a31aabe6f4913c59ef9d3c62d2d6f26442ac"},"schema_version":"1.0"},"canonical_sha256":"92948100455d397774023a2605a27fd37cf7541a89d4164e9619ae6a3230b993","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:08.255084Z","signature_b64":"BcBuloVKtcaqIHyor8muKlIqeoPTu00t3AC/xAMiaF6tgqOuWXHcqKLdoO6fPyac0LUakCtrESE/zge6Fp5RCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92948100455d397774023a2605a27fd37cf7541a89d4164e9619ae6a3230b993","last_reissued_at":"2026-06-30T02:18:08.254218Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:08.254218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.19679","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNm/5v/mt68Zu2Ai7/osJBCMEUQL7eMgbWZuMQhgMIemTTPqiZaGzJpw6fW8C9j+g7WFiEpU8rCJxoi3s9jjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:14:49.683159Z"},"content_sha256":"221e630af56adab04f5ce883ca81c65e9352c7a5f495592763fdf366b42499c2","schema_version":"1.0","event_id":"sha256:221e630af56adab04f5ce883ca81c65e9352c7a5f495592763fdf366b42499c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SKKICACFLU4XO5ACHITALIT72N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MMControl routes visual and acoustic conditions through bypass branches into a joint audio-video diffusion transformer to enable independent control of identity, voice, pose, and layout.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Canyu Zhao, Chunhua Shen, Hao Chen, Liyang Li, Tianjian Feng, Wen Wang, Zhiyue Zhao","submitted_at":"2026-04-21T16:57:23Z","abstract_excerpt":"Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within a single model. However, existing controllable generation frameworks are typically restricted to video-only control. This restricts comprehensive controllability and often leads to suboptimal cross-modal alignment. To bridge this gap, we present MMControl, which enables users to perform Multi-Modal Control in joint audio-video generation. MMControl introduces a dual-stream conditional injection mechanism. It incorporates both visual and acoust"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MMControl achieves fine-grained, composable control over character identity, voice timbre, body pose, and scene layout in joint audio-video generation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That injecting visual and acoustic conditions through bypass branches into a joint audio-video Diffusion Transformer will maintain high-quality generation and cross-modal alignment without introducing artifacts or requiring extensive retraining.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MMControl adds multi-modal controls for identity, timbre, pose, and layout to unified audio-video diffusion models via dual-stream injection and adjustable guidance scaling.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MMControl routes visual and acoustic conditions through bypass branches into a joint audio-video diffusion transformer to enable independent control of identity, voice, pose, and layout.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1c2f48cd74c2ea52f70955ed9f1ea2a83e9baa61c8e309556b601402f4d043e0"},"source":{"id":"2604.19679","kind":"arxiv","version":3},"verdict":{"id":"2f11548b-ce84-4867-8d03-c56212423dfa","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T02:49:13.862349Z","strongest_claim":"MMControl achieves fine-grained, composable control over character identity, voice timbre, body pose, and scene layout in joint audio-video generation.","one_line_summary":"MMControl adds multi-modal controls for identity, timbre, pose, and layout to unified audio-video diffusion models via dual-stream injection and adjustable guidance scaling.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That injecting visual and acoustic conditions through bypass branches into a joint audio-video Diffusion Transformer will maintain high-quality generation and cross-modal alignment without introducing artifacts or requiring extensive retraining.","pith_extraction_headline":"MMControl routes visual and acoustic conditions through bypass branches into a joint audio-video diffusion transformer to enable independent control of identity, voice, pose, and layout."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.19679/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T16:33:59.611764Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T02:39:56.507296Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2ff625e36d58ea707fa32c864a340162069054a271d3ee229a78521523295b89"},"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":"2f11548b-ce84-4867-8d03-c56212423dfa"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W3lJ4/x9e7NjyHXj0a6hbJ6BGcZ/Pl32e0IbI3AHwlmjSQwDZRNLz7MX4vCsJ3Dv+z6l1fheCX51YoOkfOnDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T12:14:49.683647Z"},"content_sha256":"a53b47dbe2f79c48134d4394a6ee53e2fdfaae1852a57f94e941cef4b20372e3","schema_version":"1.0","event_id":"sha256:a53b47dbe2f79c48134d4394a6ee53e2fdfaae1852a57f94e941cef4b20372e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SKKICACFLU4XO5ACHITALIT72N/bundle.json","state_url":"https://pith.science/pith/SKKICACFLU4XO5ACHITALIT72N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SKKICACFLU4XO5ACHITALIT72N/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":"2026-06-30T12:14:49Z","links":{"resolver":"https://pith.science/pith/SKKICACFLU4XO5ACHITALIT72N","bundle":"https://pith.science/pith/SKKICACFLU4XO5ACHITALIT72N/bundle.json","state":"https://pith.science/pith/SKKICACFLU4XO5ACHITALIT72N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SKKICACFLU4XO5ACHITALIT72N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SKKICACFLU4XO5ACHITALIT72N","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":"2d000907476a101831f0f4775792a31aabe6f4913c59ef9d3c62d2d6f26442ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T16:57:23Z","title_canon_sha256":"69835bb041f7ce804938e1fb7534703948c8edf0ffbc5eca0466f7b245d9a570"},"schema_version":"1.0","source":{"id":"2604.19679","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.19679","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2604.19679v3","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19679","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"SKKICACFLU4X","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"SKKICACFLU4XO5AC","created_at":"2026-06-30T02:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"SKKICACF","created_at":"2026-06-30T02:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:a53b47dbe2f79c48134d4394a6ee53e2fdfaae1852a57f94e941cef4b20372e3","target":"graph","created_at":"2026-06-30T02:18:08Z","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":"MMControl achieves fine-grained, composable control over character identity, voice timbre, body pose, and scene layout in joint audio-video generation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That injecting visual and acoustic conditions through bypass branches into a joint audio-video Diffusion Transformer will maintain high-quality generation and cross-modal alignment without introducing artifacts or requiring extensive retraining."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MMControl adds multi-modal controls for identity, timbre, pose, and layout to unified audio-video diffusion models via dual-stream injection and adjustable guidance scaling."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MMControl routes visual and acoustic conditions through bypass branches into a joint audio-video diffusion transformer to enable independent control of identity, voice, pose, and layout."}],"snapshot_sha256":"1c2f48cd74c2ea52f70955ed9f1ea2a83e9baa61c8e309556b601402f4d043e0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T16:33:59.611764Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T02:39:56.507296Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.19679/integrity.json","findings":[],"snapshot_sha256":"2ff625e36d58ea707fa32c864a340162069054a271d3ee229a78521523295b89","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within a single model. However, existing controllable generation frameworks are typically restricted to video-only control. This restricts comprehensive controllability and often leads to suboptimal cross-modal alignment. To bridge this gap, we present MMControl, which enables users to perform Multi-Modal Control in joint audio-video generation. MMControl introduces a dual-stream conditional injection mechanism. It incorporates both visual and acoust","authors_text":"Canyu Zhao, Chunhua Shen, Hao Chen, Liyang Li, Tianjian Feng, Wen Wang, Zhiyue Zhao","cross_cats":[],"headline":"MMControl routes visual and acoustic conditions through bypass branches into a joint audio-video diffusion transformer to enable independent control of identity, voice, pose, and layout.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T16:57:23Z","title":"MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.19679","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T02:49:13.862349Z","id":"2f11548b-ce84-4867-8d03-c56212423dfa","model_set":{"reader":"grok-4.3"},"one_line_summary":"MMControl adds multi-modal controls for identity, timbre, pose, and layout to unified audio-video diffusion models via dual-stream injection and adjustable guidance scaling.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MMControl routes visual and acoustic conditions through bypass branches into a joint audio-video diffusion transformer to enable independent control of identity, voice, pose, and layout.","strongest_claim":"MMControl achieves fine-grained, composable control over character identity, voice timbre, body pose, and scene layout in joint audio-video generation.","weakest_assumption":"That injecting visual and acoustic conditions through bypass branches into a joint audio-video Diffusion Transformer will maintain high-quality generation and cross-modal alignment without introducing artifacts or requiring extensive retraining."}},"verdict_id":"2f11548b-ce84-4867-8d03-c56212423dfa"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:221e630af56adab04f5ce883ca81c65e9352c7a5f495592763fdf366b42499c2","target":"record","created_at":"2026-06-30T02:18:08Z","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":"2d000907476a101831f0f4775792a31aabe6f4913c59ef9d3c62d2d6f26442ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T16:57:23Z","title_canon_sha256":"69835bb041f7ce804938e1fb7534703948c8edf0ffbc5eca0466f7b245d9a570"},"schema_version":"1.0","source":{"id":"2604.19679","kind":"arxiv","version":3}},"canonical_sha256":"92948100455d397774023a2605a27fd37cf7541a89d4164e9619ae6a3230b993","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92948100455d397774023a2605a27fd37cf7541a89d4164e9619ae6a3230b993","first_computed_at":"2026-06-30T02:18:08.254218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:18:08.254218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BcBuloVKtcaqIHyor8muKlIqeoPTu00t3AC/xAMiaF6tgqOuWXHcqKLdoO6fPyac0LUakCtrESE/zge6Fp5RCQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:18:08.255084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.19679","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:221e630af56adab04f5ce883ca81c65e9352c7a5f495592763fdf366b42499c2","sha256:a53b47dbe2f79c48134d4394a6ee53e2fdfaae1852a57f94e941cef4b20372e3"],"state_sha256":"aff9bbf3d85a1552eeb620e526cb5cd137a4c5997242b2301ed8f391ea29deef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X0QnKUPiJOnpPVPhSSeKhYKY1koqUzgoVbs1c1eEUug00FSG2AHh2jxtPHkR5GWNMBcP/LsajLbP/d10413KDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T12:14:49.685874Z","bundle_sha256":"9c4602a463ba228c9247e4b21e455a392c56395ff50e442b2ea778cda4a14cea"}}