{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HMUZ6LX53IKA7MHQIQVXLLCYPK","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":"cd13f361d91b2d529300319ff7caf0e38fdc6ae33a32915570542c9f0cd38ef8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-23T17:59:48Z","title_canon_sha256":"8301c8db69b46670429b23fda2c64d61cd2c57940f1f6fda755c543b52c1dbd5"},"schema_version":"1.0","source":{"id":"2603.22282","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.22282","created_at":"2026-06-30T01:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"2603.22282v2","created_at":"2026-06-30T01:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.22282","created_at":"2026-06-30T01:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"HMUZ6LX53IKA","created_at":"2026-06-30T01:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"HMUZ6LX53IKA7MHQ","created_at":"2026-06-30T01:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"HMUZ6LX5","created_at":"2026-06-30T01:17:37Z"}],"graph_snapshots":[{"event_id":"sha256:fb2c028eeed3c9a13f462cee01babe508c39a22bb438a77981bc7652f502a801","target":"graph","created_at":"2026-06-30T01:17:37Z","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/2603.22282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture. Existing unified models handle only restricted modality subsets (e.g., Motion-Text or static Pose-Image) and predominantly rely on discrete tokenization, which introduces quantization errors and disrupts temporal continuity. UniMotion overcomes both limitations through a core principle: treating motion as a first-class continuous modality on equal footing with RGB. A novel Cross-Modal Aligned Motion VAE ","authors_text":"Mengyuan Liu, Shuang Chen, Xinshun Wang, Yang Cong, Ziyi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-23T17:59:48Z","title":"UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.22282","kind":"arxiv","version":2},"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:dbc08a0078d4d44d53586b2b1503e35d13ba9ea0d0702a6b8bafe011046d7959","target":"record","created_at":"2026-06-30T01:17:37Z","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":"cd13f361d91b2d529300319ff7caf0e38fdc6ae33a32915570542c9f0cd38ef8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-23T17:59:48Z","title_canon_sha256":"8301c8db69b46670429b23fda2c64d61cd2c57940f1f6fda755c543b52c1dbd5"},"schema_version":"1.0","source":{"id":"2603.22282","kind":"arxiv","version":2}},"canonical_sha256":"3b299f2efdda140fb0f0442b75ac587a867db9a2a623ea1792353b10407ecdbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b299f2efdda140fb0f0442b75ac587a867db9a2a623ea1792353b10407ecdbc","first_computed_at":"2026-06-30T01:17:37.391730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:37.391730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e+ztuSZoUdrUyy+MThqcAu7tsXqEwsb+vqqFKocVBtRaDFLKsMaPxIcIeR1JEvJvvJeO9WvcLV+YMJkKibjvDw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:37.392341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.22282","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbc08a0078d4d44d53586b2b1503e35d13ba9ea0d0702a6b8bafe011046d7959","sha256:fb2c028eeed3c9a13f462cee01babe508c39a22bb438a77981bc7652f502a801"],"state_sha256":"7add9ce7151ac9e774048fd50fda602ee977c728d78962197eecacf639d64fd2"}