{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BMFR3ZQINADOCHC7Y67C3X2ELG","short_pith_number":"pith:BMFR3ZQI","schema_version":"1.0","canonical_sha256":"0b0b1de6086806e11c5fc7be2ddf445981384eecd154fe693f3c58427d71058d","source":{"kind":"arxiv","id":"2605.13729","version":1},"attestation_state":"computed","paper":{"title":"Coordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CMC coordinates text and trajectory conditions via two-stage diffusion to generate accurate human motions","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Deli Cai, Haoyang Ma","submitted_at":"2026-05-13T16:09:04Z","abstract_excerpt":"Trajectory-controlled human motion generation aims to synthesize realistic human motions conditioned on both textual descriptions and spatial trajectories. However, existing methods suffer from two critical limitations: first, the conflict between text and trajectory conditions disrupts the denoising process, resulting in compromised motion quality or inaccurate trajectory following; second, the use of redundant motion representations introduces inconsistencies between motion components, leading to instability during trajectory control. To address these challenges, we propose CMC, a decoupled "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:09:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ffc513ec70a965715c626553edbe9916f128d80952cf6f48e29a3690c44b00b7","abstract_canon_sha256":"432a5cc1ad1844833dafbad0849898ebfd24540ea00ac7eeb4e95cbf5565b36b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.574909Z","signature_b64":"auXBHGc7DmuDRoQk2nOvpNpQGObQ1ui1sKtrUTkFeinsUUbjVqHOOw3sC95PckiYWFCPpEZUvkomEEZVWEXHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b0b1de6086806e11c5fc7be2ddf445981384eecd154fe693f3c58427d71058d","last_reissued_at":"2026-05-18T02:44:16.574472Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.574472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CMC coordinates text and trajectory conditions via two-stage diffusion to generate accurate human motions","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changxing Ding, Deli Cai, Haoyang Ma","submitted_at":"2026-05-13T16:09:04Z","abstract_excerpt":"Trajectory-controlled human motion generation aims to synthesize realistic human motions conditioned on both textual descriptions and spatial trajectories. However, existing methods suffer from two critical limitations: first, the conflict between text and trajectory conditions disrupts the denoising process, resulting in compromised motion quality or inaccurate trajectory following; second, the use of redundant motion representations introduces inconsistencies between motion components, leading to instability during trajectory control. To address these challenges, we propose CMC, a decoupled "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on HumanML3D and KIT datasets demonstrate that CMC achieves state-of-the-art performance in control accuracy and motion quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The simplified controlled-joint representation produced by the first-stage trajectory model supplies sufficient partial observations for the second-stage text-conditioned inpainting model to generate consistent, artifact-free full-body motions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CMC decouples trajectory control and text-conditioned motion completion with selective inpainting to achieve state-of-the-art accuracy and quality in multimodal human motion generation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CMC coordinates text and trajectory conditions via two-stage diffusion to generate accurate human motions","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5b45bb0b3988ad8996403aea2d1ecbcf8cbfb461a27fb3b8869b211238b4c3bb"},"source":{"id":"2605.13729","kind":"arxiv","version":1},"verdict":{"id":"55ec01d5-2024-4269-839e-15162a4b6784","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:53:12.336054Z","strongest_claim":"Experiments on HumanML3D and KIT datasets demonstrate that CMC achieves state-of-the-art performance in control accuracy and motion quality.","one_line_summary":"CMC decouples trajectory control and text-conditioned motion completion with selective inpainting to achieve state-of-the-art accuracy and quality in multimodal human motion generation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The simplified controlled-joint representation produced by the first-stage trajectory model supplies sufficient partial observations for the second-stage text-conditioned inpainting model to generate consistent, artifact-free full-body motions.","pith_extraction_headline":"CMC coordinates text and trajectory conditions via two-stage diffusion to generate accurate human motions"},"references":{"count":60,"sample":[{"doi":"","year":2026,"title":"Crowdmogen: Event-driven collective human motion generation.Int","work_id":"f0de9a9c-017d-401a-a14d-47a147682da0","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Executing your commands via motion diffusion in latent space","work_id":"a5254f7b-dfc0-4712-a26d-ea5cb6eef6c8","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Hop: Heterogeneous topology-based multimodal entanglement for co-speech gesture generation","work_id":"8e563704-3e57-4e5a-b747-c40790f756ac","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Interaction transformer for human reaction generation.IEEE Trans","work_id":"ba5740ee-e57e-4166-ad49-60b5b7cc409e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Mofusion: A framework for denoising-diffusion- based motion synthesis","work_id":"93509eac-e67d-4563-a1fc-ab1ee8180664","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"c216d851a680a0b7ce27da01f0b87e9d0bba7e690117fa8daefd94a9eb3348e1","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":"2605.13729","created_at":"2026-05-18T02:44:16.574544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13729v1","created_at":"2026-05-18T02:44:16.574544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13729","created_at":"2026-05-18T02:44:16.574544+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMFR3ZQINADO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMFR3ZQINADOCHC7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMFR3ZQI","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG","json":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG.json","graph_json":"https://pith.science/api/pith-number/BMFR3ZQINADOCHC7Y67C3X2ELG/graph.json","events_json":"https://pith.science/api/pith-number/BMFR3ZQINADOCHC7Y67C3X2ELG/events.json","paper":"https://pith.science/paper/BMFR3ZQI"},"agent_actions":{"view_html":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG","download_json":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG.json","view_paper":"https://pith.science/paper/BMFR3ZQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13729&json=true","fetch_graph":"https://pith.science/api/pith-number/BMFR3ZQINADOCHC7Y67C3X2ELG/graph.json","fetch_events":"https://pith.science/api/pith-number/BMFR3ZQINADOCHC7Y67C3X2ELG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/action/storage_attestation","attest_author":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/action/author_attestation","sign_citation":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/action/citation_signature","submit_replication":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/action/replication_record"}},"created_at":"2026-05-18T02:44:16.574544+00:00","updated_at":"2026-05-18T02:44:16.574544+00:00"}