{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S27EYZAZNKRAMKO4A5JC7BJYUC","short_pith_number":"pith:S27EYZAZ","schema_version":"1.0","canonical_sha256":"96be4c64196aa20629dc07522f8538a0896b444582807d50509b71e8179e6d50","source":{"kind":"arxiv","id":"2605.08729","version":2},"attestation_state":"computed","paper":{"title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Unison is a unified framework that harmonizes motion, speech, and sound in human-centric video generation through explicit multimodal strategies.","cross_cats":["cs.GR","cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Chi Zhang, Jiaxu Zhang, Quanyue Song, Shansong Liu, Shihao Cheng, Xiaolei Zhang, Xuelong Li, Zhigang Tu, Zhizhi Guo","submitted_at":"2026-05-09T06:32:54Z","abstract_excerpt":"Motion, speech, and sound effects are fundamental elements of human-centric videos, yet their heterogeneous temporal characteristics make joint generation highly challenging. Existing audio-video generation models often fail to maintain consistent alignment across these modalities, leading to noticeable mismatches between motion, speech, and environmental sounds. We present Unison, a unified framework that explicitly promotes coherence across the motion, speech, and sound modalities. Within the audio stream, Unison employs a semantic-guided harmonization strategy that decouples the generation "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.08729","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T06:32:54Z","cross_cats_sorted":["cs.GR","cs.MM","cs.SD"],"title_canon_sha256":"af5dfab12523065f2896b2d98769310a4a34d52ce90f30816bf012c5d80a961c","abstract_canon_sha256":"e572d6e35917811960648456965f1c83a4278ee12faf52b1503863682d3efaf2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:22.483947Z","signature_b64":"kp6ck6T+bQSj1pvFnvBoWOAjM0BTxgKOLcLW4mQcZViMDhxJBPqCSWUXqowupFkf+r8qDN6ZvKe574uRnujGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96be4c64196aa20629dc07522f8538a0896b444582807d50509b71e8179e6d50","last_reissued_at":"2026-06-30T02:17:22.483285Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:22.483285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Unison is a unified framework that harmonizes motion, speech, and sound in human-centric video generation through explicit multimodal strategies.","cross_cats":["cs.GR","cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Chi Zhang, Jiaxu Zhang, Quanyue Song, Shansong Liu, Shihao Cheng, Xiaolei Zhang, Xuelong Li, Zhigang Tu, Zhizhi Guo","submitted_at":"2026-05-09T06:32:54Z","abstract_excerpt":"Motion, speech, and sound effects are fundamental elements of human-centric videos, yet their heterogeneous temporal characteristics make joint generation highly challenging. Existing audio-video generation models often fail to maintain consistent alignment across these modalities, leading to noticeable mismatches between motion, speech, and environmental sounds. We present Unison, a unified framework that explicitly promotes coherence across the motion, speech, and sound modalities. Within the audio stream, Unison employs a semantic-guided harmonization strategy that decouples the generation "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Unison achieves state-of-the-art performance in both audio perceptual quality and cross-modal synchronization, highlighting the importance of explicit multimodal harmonization in human-centric video generation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed semantic-guided harmonization strategy and bidirectional cross-modal forcing with decoupled denoising schedules will reliably improve coherence without introducing new artifacts or requiring extensive post-hoc tuning on specific datasets.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Unison introduces a unified framework using semantic-guided harmonization and bidirectional cross-modal forcing to generate human-centric videos with improved synchronization between motion, speech, and sound effects.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Unison is a unified framework that harmonizes motion, speech, and sound in human-centric video generation through explicit multimodal strategies.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"54dd8e8557b3b51e7d2c12ac7794564e5e260c77012ee7f1c072f4d935b545dc"},"source":{"id":"2605.08729","kind":"arxiv","version":2},"verdict":{"id":"df696f81-1a0b-48aa-a3b7-da2f9f70853d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T02:23:25.744550Z","strongest_claim":"Unison achieves state-of-the-art performance in both audio perceptual quality and cross-modal synchronization, highlighting the importance of explicit multimodal harmonization in human-centric video generation.","one_line_summary":"Unison introduces a unified framework using semantic-guided harmonization and bidirectional cross-modal forcing to generate human-centric videos with improved synchronization between motion, speech, and sound effects.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed semantic-guided harmonization strategy and bidirectional cross-modal forcing with decoupled denoising schedules will reliably improve coherence without introducing new artifacts or requiring extensive post-hoc tuning on specific datasets.","pith_extraction_headline":"Unison is a unified framework that harmonizes motion, speech, and sound in human-centric video generation through explicit multimodal strategies."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08729/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T09:02:01.946657Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:35:38.357335Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:31:17.607190Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:50:51.413104Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0898b83cb733f80c4cd8792bde22780a797caf2f911c29f126496c569a0ed959"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8235d5616349662ad9114548ef4262d99d05bd2c63ae20dcdc17b9c234d0733f"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.08729","created_at":"2026-06-30T02:17:22.483382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.08729v2","created_at":"2026-06-30T02:17:22.483382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08729","created_at":"2026-06-30T02:17:22.483382+00:00"},{"alias_kind":"pith_short_12","alias_value":"S27EYZAZNKRA","created_at":"2026-06-30T02:17:22.483382+00:00"},{"alias_kind":"pith_short_16","alias_value":"S27EYZAZNKRAMKO4","created_at":"2026-06-30T02:17:22.483382+00:00"},{"alias_kind":"pith_short_8","alias_value":"S27EYZAZ","created_at":"2026-06-30T02:17:22.483382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.00672","citing_title":"DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22905","citing_title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC","json":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC.json","graph_json":"https://pith.science/api/pith-number/S27EYZAZNKRAMKO4A5JC7BJYUC/graph.json","events_json":"https://pith.science/api/pith-number/S27EYZAZNKRAMKO4A5JC7BJYUC/events.json","paper":"https://pith.science/paper/S27EYZAZ"},"agent_actions":{"view_html":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC","download_json":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC.json","view_paper":"https://pith.science/paper/S27EYZAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.08729&json=true","fetch_graph":"https://pith.science/api/pith-number/S27EYZAZNKRAMKO4A5JC7BJYUC/graph.json","fetch_events":"https://pith.science/api/pith-number/S27EYZAZNKRAMKO4A5JC7BJYUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC/action/storage_attestation","attest_author":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC/action/author_attestation","sign_citation":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC/action/citation_signature","submit_replication":"https://pith.science/pith/S27EYZAZNKRAMKO4A5JC7BJYUC/action/replication_record"}},"created_at":"2026-06-30T02:17:22.483382+00:00","updated_at":"2026-06-30T02:17:22.483382+00:00"}