{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S27EYZAZNKRAMKO4A5JC7BJYUC","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":"e572d6e35917811960648456965f1c83a4278ee12faf52b1503863682d3efaf2","cross_cats_sorted":["cs.GR","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T06:32:54Z","title_canon_sha256":"af5dfab12523065f2896b2d98769310a4a34d52ce90f30816bf012c5d80a961c"},"schema_version":"1.0","source":{"id":"2605.08729","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08729","created_at":"2026-06-30T02:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08729v2","created_at":"2026-06-30T02:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08729","created_at":"2026-06-30T02:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"S27EYZAZNKRA","created_at":"2026-06-30T02:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"S27EYZAZNKRAMKO4","created_at":"2026-06-30T02:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"S27EYZAZ","created_at":"2026-06-30T02:17:22Z"}],"graph_snapshots":[{"event_id":"sha256:6d1a765193b0a8f71964bbd2dda4246be3cb0bccdce346676007b8ad718dafd6","target":"graph","created_at":"2026-06-30T02:17:22Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Unison is a unified framework that harmonizes motion, speech, and sound in human-centric video generation through explicit multimodal strategies."}],"snapshot_sha256":"54dd8e8557b3b51e7d2c12ac7794564e5e260c77012ee7f1c072f4d935b545dc"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8235d5616349662ad9114548ef4262d99d05bd2c63ae20dcdc17b9c234d0733f"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.08729/integrity.json","findings":[],"snapshot_sha256":"0898b83cb733f80c4cd8792bde22780a797caf2f911c29f126496c569a0ed959","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Chi Zhang, Jiaxu Zhang, Quanyue Song, Shansong Liu, Shihao Cheng, Xiaolei Zhang, Xuelong Li, Zhigang Tu, Zhizhi Guo","cross_cats":["cs.GR","cs.MM","cs.SD"],"headline":"Unison is a unified framework that harmonizes motion, speech, and sound in human-centric video generation through explicit multimodal strategies.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T06:32:54Z","title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08729","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T02:23:25.744550Z","id":"df696f81-1a0b-48aa-a3b7-da2f9f70853d","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Unison is a unified framework that harmonizes motion, speech, and sound in human-centric video generation through explicit multimodal strategies.","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.","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."}},"verdict_id":"df696f81-1a0b-48aa-a3b7-da2f9f70853d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3936a7acfa92e8b3326b224b84861f5a33b3aa5931339b247641d7978b29d041","target":"record","created_at":"2026-06-30T02:17:22Z","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":"e572d6e35917811960648456965f1c83a4278ee12faf52b1503863682d3efaf2","cross_cats_sorted":["cs.GR","cs.MM","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-09T06:32:54Z","title_canon_sha256":"af5dfab12523065f2896b2d98769310a4a34d52ce90f30816bf012c5d80a961c"},"schema_version":"1.0","source":{"id":"2605.08729","kind":"arxiv","version":2}},"canonical_sha256":"96be4c64196aa20629dc07522f8538a0896b444582807d50509b71e8179e6d50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96be4c64196aa20629dc07522f8538a0896b444582807d50509b71e8179e6d50","first_computed_at":"2026-06-30T02:17:22.483285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:22.483285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kp6ck6T+bQSj1pvFnvBoWOAjM0BTxgKOLcLW4mQcZViMDhxJBPqCSWUXqowupFkf+r8qDN6ZvKe574uRnujGDw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:22.483947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08729","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3936a7acfa92e8b3326b224b84861f5a33b3aa5931339b247641d7978b29d041","sha256:6d1a765193b0a8f71964bbd2dda4246be3cb0bccdce346676007b8ad718dafd6"],"state_sha256":"1885279a7ec1f7377fbaeca6a83f0a131fcd433be4f7fd6e9e5888ff5f3d5d14"}