{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AOWHCTZEK3QHAU6GWFLUAN4KO6","short_pith_number":"pith:AOWHCTZE","schema_version":"1.0","canonical_sha256":"03ac714f2456e07053c6b15740378a778b99403803611d5652ef921f1bf2a832","source":{"kind":"arxiv","id":"2503.06955","version":2},"attestation_state":"computed","paper":{"title":"Motion Anything: Any to Motion Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Wu, Bohan Zhuang, Danning Li, Ian Reid, Richard Hartley, Rui Zhao, Wei Mao, Yiran Wang, Zeyu Zhang, Zirui Song","submitted_at":"2025-03-10T06:04:31Z","abstract_excerpt":"Conditional motion generation has been extensively studied in computer vision, yet two critical challenges remain. First, while masked autoregressive methods have recently outperformed diffusion-based approaches, existing masking models lack a mechanism to prioritize dynamic frames and body parts based on given conditions. Second, existing methods for different conditioning modalities often fail to integrate multiple modalities effectively, limiting control and coherence in generated motion. To address these challenges, we propose Motion Anything, a multimodal motion generation framework that "},"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":"2503.06955","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T06:04:31Z","cross_cats_sorted":[],"title_canon_sha256":"ff9a5dca9601bde40c34f5daff0f08c56bee32c00565d5e27d96c844861047f5","abstract_canon_sha256":"ecde752697525f7606cf3e183eb160eec7cfb5b7f58fdae8c2055f52a4b4ae40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:37.176688Z","signature_b64":"pkBSQ4ebAYn63pJXOuWFhkSTz5GEK01EBij3MYT2T+IEqC0nFTctdOVmlSvChigGw1gYch4JmMXmie+GH6gpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03ac714f2456e07053c6b15740378a778b99403803611d5652ef921f1bf2a832","last_reissued_at":"2026-07-05T10:29:37.176156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:37.176156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion Anything: Any to Motion Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Wu, Bohan Zhuang, Danning Li, Ian Reid, Richard Hartley, Rui Zhao, Wei Mao, Yiran Wang, Zeyu Zhang, Zirui Song","submitted_at":"2025-03-10T06:04:31Z","abstract_excerpt":"Conditional motion generation has been extensively studied in computer vision, yet two critical challenges remain. First, while masked autoregressive methods have recently outperformed diffusion-based approaches, existing masking models lack a mechanism to prioritize dynamic frames and body parts based on given conditions. Second, existing methods for different conditioning modalities often fail to integrate multiple modalities effectively, limiting control and coherence in generated motion. To address these challenges, we propose Motion Anything, a multimodal motion generation framework that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06955","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/2503.06955/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":"2503.06955","created_at":"2026-07-05T10:29:37.176223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06955v2","created_at":"2026-07-05T10:29:37.176223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06955","created_at":"2026-07-05T10:29:37.176223+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOWHCTZEK3QH","created_at":"2026-07-05T10:29:37.176223+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOWHCTZEK3QHAU6G","created_at":"2026-07-05T10:29:37.176223+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOWHCTZE","created_at":"2026-07-05T10:29:37.176223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01518","citing_title":"SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapes","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14935","citing_title":"Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01518","citing_title":"SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapes","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29488","citing_title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14716","citing_title":"AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2506.05952","citing_title":"MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11363","citing_title":"PresentAgent-2: Towards Generalist Multimodal Presentation Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17005","citing_title":"TeMuDance: Contrastive Alignment-Based Textual Control for Music-Driven Dance Generation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17472","citing_title":"UniMesh: Unifying 3D Mesh Understanding and Generation","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6","json":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6.json","graph_json":"https://pith.science/api/pith-number/AOWHCTZEK3QHAU6GWFLUAN4KO6/graph.json","events_json":"https://pith.science/api/pith-number/AOWHCTZEK3QHAU6GWFLUAN4KO6/events.json","paper":"https://pith.science/paper/AOWHCTZE"},"agent_actions":{"view_html":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6","download_json":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6.json","view_paper":"https://pith.science/paper/AOWHCTZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06955&json=true","fetch_graph":"https://pith.science/api/pith-number/AOWHCTZEK3QHAU6GWFLUAN4KO6/graph.json","fetch_events":"https://pith.science/api/pith-number/AOWHCTZEK3QHAU6GWFLUAN4KO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6/action/storage_attestation","attest_author":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6/action/author_attestation","sign_citation":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6/action/citation_signature","submit_replication":"https://pith.science/pith/AOWHCTZEK3QHAU6GWFLUAN4KO6/action/replication_record"}},"created_at":"2026-07-05T10:29:37.176223+00:00","updated_at":"2026-07-05T10:29:37.176223+00:00"}