{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HMUZ6LX53IKA7MHQIQVXLLCYPK","short_pith_number":"pith:HMUZ6LX5","schema_version":"1.0","canonical_sha256":"3b299f2efdda140fb0f0442b75ac587a867db9a2a623ea1792353b10407ecdbc","source":{"kind":"arxiv","id":"2603.22282","version":2},"attestation_state":"computed","paper":{"title":"UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mengyuan Liu, Shuang Chen, Xinshun Wang, Yang Cong, Ziyi Wang","submitted_at":"2026-03-23T17:59:48Z","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 "},"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":false},"canonical_record":{"source":{"id":"2603.22282","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-23T17:59:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8301c8db69b46670429b23fda2c64d61cd2c57940f1f6fda755c543b52c1dbd5","abstract_canon_sha256":"cd13f361d91b2d529300319ff7caf0e38fdc6ae33a32915570542c9f0cd38ef8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:37.392341Z","signature_b64":"e+ztuSZoUdrUyy+MThqcAu7tsXqEwsb+vqqFKocVBtRaDFLKsMaPxIcIeR1JEvJvvJeO9WvcLV+YMJkKibjvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b299f2efdda140fb0f0442b75ac587a867db9a2a623ea1792353b10407ecdbc","last_reissued_at":"2026-06-30T01:17:37.391730Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:37.391730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Mengyuan Liu, Shuang Chen, Xinshun Wang, Yang Cong, Ziyi Wang","submitted_at":"2026-03-23T17:59:48Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.22282","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.22282/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.22282","created_at":"2026-06-30T01:17:37.391813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.22282v2","created_at":"2026-06-30T01:17:37.391813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.22282","created_at":"2026-06-30T01:17:37.391813+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMUZ6LX53IKA","created_at":"2026-06-30T01:17:37.391813+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMUZ6LX53IKA7MHQ","created_at":"2026-06-30T01:17:37.391813+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMUZ6LX5","created_at":"2026-06-30T01:17:37.391813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.19578","citing_title":"Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19578","citing_title":"Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK","json":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK.json","graph_json":"https://pith.science/api/pith-number/HMUZ6LX53IKA7MHQIQVXLLCYPK/graph.json","events_json":"https://pith.science/api/pith-number/HMUZ6LX53IKA7MHQIQVXLLCYPK/events.json","paper":"https://pith.science/paper/HMUZ6LX5"},"agent_actions":{"view_html":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK","download_json":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK.json","view_paper":"https://pith.science/paper/HMUZ6LX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.22282&json=true","fetch_graph":"https://pith.science/api/pith-number/HMUZ6LX53IKA7MHQIQVXLLCYPK/graph.json","fetch_events":"https://pith.science/api/pith-number/HMUZ6LX53IKA7MHQIQVXLLCYPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK/action/storage_attestation","attest_author":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK/action/author_attestation","sign_citation":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK/action/citation_signature","submit_replication":"https://pith.science/pith/HMUZ6LX53IKA7MHQIQVXLLCYPK/action/replication_record"}},"created_at":"2026-06-30T01:17:37.391813+00:00","updated_at":"2026-06-30T01:17:37.391813+00:00"}