{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZNXEPW6XSDATON4RXM7LDCCQWL","short_pith_number":"pith:ZNXEPW6X","schema_version":"1.0","canonical_sha256":"cb6e47dbd790c1373791bb3eb18850b2e66130d0857c210ca8b06324b5cb93b2","source":{"kind":"arxiv","id":"2405.17013","version":3},"attestation_state":"computed","paper":{"title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Qi Wu, Xinhang Liu, Yifan Wang, Yubo Zhao, Yu-Wing Tai","submitted_at":"2024-05-27T09:57:51Z","abstract_excerpt":"While previous approaches to 3D human motion generation have achieved notable success, they often rely on extensive training and are limited to specific tasks. To address these challenges, we introduce Motion-Agent, an efficient conversational framework designed for general human motion generation, editing, and understanding. Motion-Agent employs an open-source pre-trained language model to develop a generative agent, MotionLLM, that bridges the gap between motion and text. This is accomplished by encoding and quantizing motions into discrete tokens that align with the language model's vocabul"},"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":"2405.17013","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T09:57:51Z","cross_cats_sorted":[],"title_canon_sha256":"08825deea70443fbc22efc7be1a12fe720b860bb4555a9eafa01c02aafc3cff0","abstract_canon_sha256":"dca907d0ebf1a345388ceb8f2b0a498bea8934705bc7a0f12b27fc3d19e63dbd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:15.514035Z","signature_b64":"KWOydf8GhaBRisPWNQUmbHHe/eIy95r/n5wn8KK9dpVv5kVzneQ8EOQvW39/vGNKiZXce87zrODHKwemWmncBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb6e47dbd790c1373791bb3eb18850b2e66130d0857c210ca8b06324b5cb93b2","last_reissued_at":"2026-07-05T09:16:15.513518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:15.513518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Keung Tang, Qi Wu, Xinhang Liu, Yifan Wang, Yubo Zhao, Yu-Wing Tai","submitted_at":"2024-05-27T09:57:51Z","abstract_excerpt":"While previous approaches to 3D human motion generation have achieved notable success, they often rely on extensive training and are limited to specific tasks. To address these challenges, we introduce Motion-Agent, an efficient conversational framework designed for general human motion generation, editing, and understanding. Motion-Agent employs an open-source pre-trained language model to develop a generative agent, MotionLLM, that bridges the gap between motion and text. This is accomplished by encoding and quantizing motions into discrete tokens that align with the language model's vocabul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17013","kind":"arxiv","version":3},"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/2405.17013/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":"2405.17013","created_at":"2026-07-05T09:16:15.513598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17013v3","created_at":"2026-07-05T09:16:15.513598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17013","created_at":"2026-07-05T09:16:15.513598+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNXEPW6XSDAT","created_at":"2026-07-05T09:16:15.513598+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNXEPW6XSDATON4R","created_at":"2026-07-05T09:16:15.513598+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNXEPW6X","created_at":"2026-07-05T09:16:15.513598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23061","citing_title":"MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04773","citing_title":"NextMotionQA: Benchmarking and Judging Human Motion Understanding with Vision-Language Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30266","citing_title":"Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28056","citing_title":"CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18956","citing_title":"MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19798","citing_title":"Towards Trust Calibration in Socially Interactive Agents: Investigating Gendered Multimodal Behaviors Generation with LLMs","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10632","citing_title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12370","citing_title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL","json":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL.json","graph_json":"https://pith.science/api/pith-number/ZNXEPW6XSDATON4RXM7LDCCQWL/graph.json","events_json":"https://pith.science/api/pith-number/ZNXEPW6XSDATON4RXM7LDCCQWL/events.json","paper":"https://pith.science/paper/ZNXEPW6X"},"agent_actions":{"view_html":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL","download_json":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL.json","view_paper":"https://pith.science/paper/ZNXEPW6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17013&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNXEPW6XSDATON4RXM7LDCCQWL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNXEPW6XSDATON4RXM7LDCCQWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL/action/storage_attestation","attest_author":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL/action/author_attestation","sign_citation":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL/action/citation_signature","submit_replication":"https://pith.science/pith/ZNXEPW6XSDATON4RXM7LDCCQWL/action/replication_record"}},"created_at":"2026-07-05T09:16:15.513598+00:00","updated_at":"2026-07-05T09:16:15.513598+00:00"}