{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MYFHID2ST3WJUKHAMDFBXTFPPF","short_pith_number":"pith:MYFHID2S","schema_version":"1.0","canonical_sha256":"660a740f529eec9a28e060ca1bccaf79531c1ff53d37c64501d0da79eb6f8a7f","source":{"kind":"arxiv","id":"2410.03441","version":1},"attestation_state":"computed","paper":{"title":"CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit H. Bermano, Daniele Reda, Guy Tevet, Michiel van de Panne, Setareh Cohan, Sigal Raab, Xue Bin Peng, Zhengyi Luo","submitted_at":"2024-10-04T13:56:48Z","abstract_excerpt":"Motion diffusion models and Reinforcement Learning (RL) based control for physics-based simulations have complementary strengths for human motion generation. The former is capable of generating a wide variety of motions, adhering to intuitive control such as text, while the latter offers physically plausible motion and direct interaction with the environment. In this work, we present a method that combines their respective strengths. CLoSD is a text-driven RL physics-based controller, guided by diffusion generation for various tasks. Our key insight is that motion diffusion can serve as an on-"},"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":"2410.03441","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T13:56:48Z","cross_cats_sorted":[],"title_canon_sha256":"d5af79f097de78601f14cf9423f63872308b06637d3f05e64df5f8f464adb491","abstract_canon_sha256":"52d3fd6506f4ac65581993f6e857ce5715a241a3e5189ae7ce2be8b95b9b2ef9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:01.168670Z","signature_b64":"Yb/6O8CU3ZJq1eRUMs/zvfZBPk9KIF8DcXTvK5GcBaJm+Ya1S83vncGCHQC/RfooFTRWLzH7jQXRuYrFoUUeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"660a740f529eec9a28e060ca1bccaf79531c1ff53d37c64501d0da79eb6f8a7f","last_reissued_at":"2026-07-05T09:16:01.168168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:01.168168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amit H. Bermano, Daniele Reda, Guy Tevet, Michiel van de Panne, Setareh Cohan, Sigal Raab, Xue Bin Peng, Zhengyi Luo","submitted_at":"2024-10-04T13:56:48Z","abstract_excerpt":"Motion diffusion models and Reinforcement Learning (RL) based control for physics-based simulations have complementary strengths for human motion generation. The former is capable of generating a wide variety of motions, adhering to intuitive control such as text, while the latter offers physically plausible motion and direct interaction with the environment. In this work, we present a method that combines their respective strengths. CLoSD is a text-driven RL physics-based controller, guided by diffusion generation for various tasks. Our key insight is that motion diffusion can serve as an on-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03441","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/2410.03441/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":"2410.03441","created_at":"2026-07-05T09:16:01.168229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03441v1","created_at":"2026-07-05T09:16:01.168229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03441","created_at":"2026-07-05T09:16:01.168229+00:00"},{"alias_kind":"pith_short_12","alias_value":"MYFHID2ST3WJ","created_at":"2026-07-05T09:16:01.168229+00:00"},{"alias_kind":"pith_short_16","alias_value":"MYFHID2ST3WJUKHA","created_at":"2026-07-05T09:16:01.168229+00:00"},{"alias_kind":"pith_short_8","alias_value":"MYFHID2S","created_at":"2026-07-05T09:16:01.168229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06438","citing_title":"WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26981","citing_title":"In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22806","citing_title":"Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14731","citing_title":"UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22894","citing_title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29148","citing_title":"GPC: Large-Scale Generative Pretraining for Transferable Motor Control","ref_index":190,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26006","citing_title":"MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22894","citing_title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18780","citing_title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14234","citing_title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14462","citing_title":"Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25164","citing_title":"IAM: Identity-Aware Human Motion and Shape Joint Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20336","citing_title":"Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF","json":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF.json","graph_json":"https://pith.science/api/pith-number/MYFHID2ST3WJUKHAMDFBXTFPPF/graph.json","events_json":"https://pith.science/api/pith-number/MYFHID2ST3WJUKHAMDFBXTFPPF/events.json","paper":"https://pith.science/paper/MYFHID2S"},"agent_actions":{"view_html":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF","download_json":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF.json","view_paper":"https://pith.science/paper/MYFHID2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03441&json=true","fetch_graph":"https://pith.science/api/pith-number/MYFHID2ST3WJUKHAMDFBXTFPPF/graph.json","fetch_events":"https://pith.science/api/pith-number/MYFHID2ST3WJUKHAMDFBXTFPPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF/action/storage_attestation","attest_author":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF/action/author_attestation","sign_citation":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF/action/citation_signature","submit_replication":"https://pith.science/pith/MYFHID2ST3WJUKHAMDFBXTFPPF/action/replication_record"}},"created_at":"2026-07-05T09:16:01.168229+00:00","updated_at":"2026-07-05T09:16:01.168229+00:00"}