{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R66A2YKLJSZNXDX3N3WOYSBW7A","short_pith_number":"pith:R66A2YKL","schema_version":"1.0","canonical_sha256":"8fbc0d614b4cb2db8efb6eecec4836f8222a371d85c8b0ba96588ebb853dad5d","source":{"kind":"arxiv","id":"2312.14828","version":1},"attestation_state":"computed","paper":{"title":"Plan, Posture and Go: Towards Open-World Text-to-Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Jinpeng Liu, Wenxun Dai, Xin Tong, Yansong Tang, Yiji Cheng","submitted_at":"2023-12-22T17:02:45Z","abstract_excerpt":"Conventional text-to-motion generation methods are usually trained on limited text-motion pairs, making them hard to generalize to open-world scenarios. Some works use the CLIP model to align the motion space and the text space, aiming to enable motion generation from natural language motion descriptions. However, they are still constrained to generate limited and unrealistic in-place motions. To address these issues, we present a divide-and-conquer framework named PRO-Motion, which consists of three modules as motion planner, posture-diffuser and go-diffuser. The motion planner instructs Larg"},"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":"2312.14828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-22T17:02:45Z","cross_cats_sorted":[],"title_canon_sha256":"f2fd304b268a1f5878b54d7c8f92a1f4b3bf7071a23407213d0430e017c93fb2","abstract_canon_sha256":"2d524d432771b35059568aee38f3f4f382f86fc4b6291012927e699ec4b21259"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:20.401459Z","signature_b64":"ho6pE3o1Dt4ddzOTG7vsdIHmKJZy8YUCSR+oRSZuTY4fiE1l8boiuSjbzH0SzK0BUwGRH2DSGpppQxhTgNdIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fbc0d614b4cb2db8efb6eecec4836f8222a371d85c8b0ba96588ebb853dad5d","last_reissued_at":"2026-07-05T07:27:20.400952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:20.400952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plan, Posture and Go: Towards Open-World Text-to-Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Jinpeng Liu, Wenxun Dai, Xin Tong, Yansong Tang, Yiji Cheng","submitted_at":"2023-12-22T17:02:45Z","abstract_excerpt":"Conventional text-to-motion generation methods are usually trained on limited text-motion pairs, making them hard to generalize to open-world scenarios. Some works use the CLIP model to align the motion space and the text space, aiming to enable motion generation from natural language motion descriptions. However, they are still constrained to generate limited and unrealistic in-place motions. To address these issues, we present a divide-and-conquer framework named PRO-Motion, which consists of three modules as motion planner, posture-diffuser and go-diffuser. The motion planner instructs Larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14828","kind":"arxiv","version":1},"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/2312.14828/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":"2312.14828","created_at":"2026-07-05T07:27:20.401010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14828v1","created_at":"2026-07-05T07:27:20.401010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14828","created_at":"2026-07-05T07:27:20.401010+00:00"},{"alias_kind":"pith_short_12","alias_value":"R66A2YKLJSZN","created_at":"2026-07-05T07:27:20.401010+00:00"},{"alias_kind":"pith_short_16","alias_value":"R66A2YKLJSZNXDX3","created_at":"2026-07-05T07:27:20.401010+00:00"},{"alias_kind":"pith_short_8","alias_value":"R66A2YKL","created_at":"2026-07-05T07:27:20.401010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26981","citing_title":"In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2412.13111","citing_title":"Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17807","citing_title":"Re$^2$MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A","json":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A.json","graph_json":"https://pith.science/api/pith-number/R66A2YKLJSZNXDX3N3WOYSBW7A/graph.json","events_json":"https://pith.science/api/pith-number/R66A2YKLJSZNXDX3N3WOYSBW7A/events.json","paper":"https://pith.science/paper/R66A2YKL"},"agent_actions":{"view_html":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A","download_json":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A.json","view_paper":"https://pith.science/paper/R66A2YKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14828&json=true","fetch_graph":"https://pith.science/api/pith-number/R66A2YKLJSZNXDX3N3WOYSBW7A/graph.json","fetch_events":"https://pith.science/api/pith-number/R66A2YKLJSZNXDX3N3WOYSBW7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A/action/storage_attestation","attest_author":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A/action/author_attestation","sign_citation":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A/action/citation_signature","submit_replication":"https://pith.science/pith/R66A2YKLJSZNXDX3N3WOYSBW7A/action/replication_record"}},"created_at":"2026-07-05T07:27:20.401010+00:00","updated_at":"2026-07-05T07:27:20.401010+00:00"}