{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BMFR3ZQINADOCHC7Y67C3X2ELG","short_pith_number":"pith:BMFR3ZQI","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"},"canonical_sha256":"0b0b1de6086806e11c5fc7be2ddf445981384eecd154fe693f3c58427d71058d","source":{"kind":"arxiv","id":"2605.13729","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13729","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13729v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13729","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"BMFR3ZQINADO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BMFR3ZQINADOCHC7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BMFR3ZQI","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BMFR3ZQINADOCHC7Y67C3X2ELG","target":"record","payload":{"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"},"canonical_sha256":"0b0b1de6086806e11c5fc7be2ddf445981384eecd154fe693f3c58427d71058d","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"},"source_kind":"arxiv","source_id":"2605.13729","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jWV7P1nd0VZBGs4IbdHDsIGGAfdFeQ0k1pNkwkzN1ePFsflCdaUFeeQYvwsHzvEstVweqa+CqLRH5vDsAacfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:13:08.879508Z"},"content_sha256":"31dee4e961913f26c02735a3cac45cf55b21f235b7cd029bfadc6a8220c9b73c","schema_version":"1.0","event_id":"sha256:31dee4e961913f26c02735a3cac45cf55b21f235b7cd029bfadc6a8220c9b73c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BMFR3ZQINADOCHC7Y67C3X2ELG","target":"graph","payload":{"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"},"verdict_id":"55ec01d5-2024-4269-839e-15162a4b6784"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wgsVZk20Q/apeXmuyOXDlLI5SPp+OEeNJfIaGmZxLfbtGacr3LCBUP6RpMLLClVE+VmTQXpaGtIlGzKGQPhsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:13:08.880032Z"},"content_sha256":"248d71dbe95c990788d4b3b2e2a4509e514b86d1cac0617eba610e9e36606eff","schema_version":"1.0","event_id":"sha256:248d71dbe95c990788d4b3b2e2a4509e514b86d1cac0617eba610e9e36606eff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/bundle.json","state_url":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T12:13:08Z","links":{"resolver":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG","bundle":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/bundle.json","state":"https://pith.science/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMFR3ZQINADOCHC7Y67C3X2ELG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BMFR3ZQINADOCHC7Y67C3X2ELG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"432a5cc1ad1844833dafbad0849898ebfd24540ea00ac7eeb4e95cbf5565b36b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:09:04Z","title_canon_sha256":"ffc513ec70a965715c626553edbe9916f128d80952cf6f48e29a3690c44b00b7"},"schema_version":"1.0","source":{"id":"2605.13729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13729","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13729v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13729","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"BMFR3ZQINADO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BMFR3ZQINADOCHC7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BMFR3ZQI","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:248d71dbe95c990788d4b3b2e2a4509e514b86d1cac0617eba610e9e36606eff","target":"graph","created_at":"2026-05-18T02:44:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on HumanML3D and KIT datasets demonstrate that CMC achieves state-of-the-art performance in control accuracy and motion quality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CMC coordinates text and trajectory conditions via two-stage diffusion to generate accurate human motions"}],"snapshot_sha256":"5b45bb0b3988ad8996403aea2d1ecbcf8cbfb461a27fb3b8869b211238b4c3bb"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","authors_text":"Changxing Ding, Deli Cai, Haoyang Ma","cross_cats":["cs.AI"],"headline":"CMC coordinates text and trajectory conditions via two-stage diffusion to generate accurate human motions","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:09:04Z","title":"Coordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation"},"references":{"count":60,"internal_anchors":0,"resolved_work":60,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Crowdmogen: Event-driven collective human motion generation.Int","work_id":"f0de9a9c-017d-401a-a14d-47a147682da0","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Executing your commands via motion diffusion in latent space","work_id":"a5254f7b-dfc0-4712-a26d-ea5cb6eef6c8","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Hop: Heterogeneous topology-based multimodal entanglement for co-speech gesture generation","work_id":"8e563704-3e57-4e5a-b747-c40790f756ac","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Interaction transformer for human reaction generation.IEEE Trans","work_id":"ba5740ee-e57e-4166-ad49-60b5b7cc409e","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Mofusion: A framework for denoising-diffusion- based motion synthesis","work_id":"93509eac-e67d-4563-a1fc-ab1ee8180664","year":2023}],"snapshot_sha256":"c216d851a680a0b7ce27da01f0b87e9d0bba7e690117fa8daefd94a9eb3348e1"},"source":{"id":"2605.13729","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:53:12.336054Z","id":"55ec01d5-2024-4269-839e-15162a4b6784","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"CMC coordinates text and trajectory conditions via two-stage diffusion to generate accurate human motions","strongest_claim":"Experiments on HumanML3D and KIT datasets demonstrate that CMC achieves state-of-the-art performance in control accuracy and motion quality.","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."}},"verdict_id":"55ec01d5-2024-4269-839e-15162a4b6784"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:31dee4e961913f26c02735a3cac45cf55b21f235b7cd029bfadc6a8220c9b73c","target":"record","created_at":"2026-05-18T02:44:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"432a5cc1ad1844833dafbad0849898ebfd24540ea00ac7eeb4e95cbf5565b36b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:09:04Z","title_canon_sha256":"ffc513ec70a965715c626553edbe9916f128d80952cf6f48e29a3690c44b00b7"},"schema_version":"1.0","source":{"id":"2605.13729","kind":"arxiv","version":1}},"canonical_sha256":"0b0b1de6086806e11c5fc7be2ddf445981384eecd154fe693f3c58427d71058d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b0b1de6086806e11c5fc7be2ddf445981384eecd154fe693f3c58427d71058d","first_computed_at":"2026-05-18T02:44:16.574472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:16.574472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"auXBHGc7DmuDRoQk2nOvpNpQGObQ1ui1sKtrUTkFeinsUUbjVqHOOw3sC95PckiYWFCPpEZUvkomEEZVWEXHDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:16.574909Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31dee4e961913f26c02735a3cac45cf55b21f235b7cd029bfadc6a8220c9b73c","sha256:248d71dbe95c990788d4b3b2e2a4509e514b86d1cac0617eba610e9e36606eff"],"state_sha256":"b277922617d264f575bd4cf76d526882ed54a4714361b882e54b2871ae1a8977"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQNR9o1bQ/oTiWTaVKjzCzXeomKoXFgPDftXdUlslwMSjrMofKcxqlBZJXxF2r2/kYOGyeqL2CwfNhKppmV9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T12:13:08.882648Z","bundle_sha256":"cd7d3f6ffcc537925fa1702774c2578d1e3a3bc871c7211c36b2435f29d3aa54"}}