{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VW22VT64SNMJD2YTLHKOXBXKOP","short_pith_number":"pith:VW22VT64","schema_version":"1.0","canonical_sha256":"adb5aacfdc935891eb1359d4eb86ea73d3f57a2227e81b2e67ee5bbaded5aee1","source":{"kind":"arxiv","id":"2407.01812","version":3},"attestation_state":"computed","paper":{"title":"Equivariant Diffusion Policy","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Surovik, Dian Wang, Haibo Zhao, Haojie Huang, Jiuguang Wang, Mark Yeatman, Robert Platt, Robin Walters, Stephen Hart, Tarik Kelestemur","submitted_at":"2024-07-01T21:23:26Z","abstract_excerpt":"Recent work has shown diffusion models are an effective approach to learning the multimodal distributions arising from demonstration data in behavior cloning. However, a drawback of this approach is the need to learn a denoising function, which is significantly more complex than learning an explicit policy. In this work, we propose Equivariant Diffusion Policy, a novel diffusion policy learning method that leverages domain symmetries to obtain better sample efficiency and generalization in the denoising function. We theoretically analyze the $\\mathrm{SO}(2)$ symmetry of full 6-DoF control and "},"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":"2407.01812","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-01T21:23:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e95173011a94fc7d9e9fc57695ff4edc22ebefb6994725b9ef542e480567fcc0","abstract_canon_sha256":"298507ff7137c38b65f7a69b4c8fea3db3f95f9a195804c935f1e5010139b0ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:44.994005Z","signature_b64":"FVOBjUNby2S4O+eePiLQ3N+JAfp4Cm5LpCD7KRqTyaQiriflET+YbMXZa5Itpe1MnweGTwSS8Tqdmqk4C62oCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adb5aacfdc935891eb1359d4eb86ea73d3f57a2227e81b2e67ee5bbaded5aee1","last_reissued_at":"2026-07-05T09:20:44.993476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:44.993476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivariant Diffusion Policy","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Surovik, Dian Wang, Haibo Zhao, Haojie Huang, Jiuguang Wang, Mark Yeatman, Robert Platt, Robin Walters, Stephen Hart, Tarik Kelestemur","submitted_at":"2024-07-01T21:23:26Z","abstract_excerpt":"Recent work has shown diffusion models are an effective approach to learning the multimodal distributions arising from demonstration data in behavior cloning. However, a drawback of this approach is the need to learn a denoising function, which is significantly more complex than learning an explicit policy. In this work, we propose Equivariant Diffusion Policy, a novel diffusion policy learning method that leverages domain symmetries to obtain better sample efficiency and generalization in the denoising function. We theoretically analyze the $\\mathrm{SO}(2)$ symmetry of full 6-DoF control and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01812","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/2407.01812/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":"2407.01812","created_at":"2026-07-05T09:20:44.993537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01812v3","created_at":"2026-07-05T09:20:44.993537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01812","created_at":"2026-07-05T09:20:44.993537+00:00"},{"alias_kind":"pith_short_12","alias_value":"VW22VT64SNMJ","created_at":"2026-07-05T09:20:44.993537+00:00"},{"alias_kind":"pith_short_16","alias_value":"VW22VT64SNMJD2YT","created_at":"2026-07-05T09:20:44.993537+00:00"},{"alias_kind":"pith_short_8","alias_value":"VW22VT64","created_at":"2026-07-05T09:20:44.993537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23625","citing_title":"Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21672","citing_title":"Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20135","citing_title":"Frequency-Aware Flow Matching for Continuous and Consistent Robotic Action Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19784","citing_title":"EquiVLA: A General Framework for Rotationally Equivariant Vision-Language-Action Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20648","citing_title":"Jointly Learning Predicates and Actions Enables Zero-Shot Skill Composition","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08547","citing_title":"R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP","json":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP.json","graph_json":"https://pith.science/api/pith-number/VW22VT64SNMJD2YTLHKOXBXKOP/graph.json","events_json":"https://pith.science/api/pith-number/VW22VT64SNMJD2YTLHKOXBXKOP/events.json","paper":"https://pith.science/paper/VW22VT64"},"agent_actions":{"view_html":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP","download_json":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP.json","view_paper":"https://pith.science/paper/VW22VT64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01812&json=true","fetch_graph":"https://pith.science/api/pith-number/VW22VT64SNMJD2YTLHKOXBXKOP/graph.json","fetch_events":"https://pith.science/api/pith-number/VW22VT64SNMJD2YTLHKOXBXKOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP/action/storage_attestation","attest_author":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP/action/author_attestation","sign_citation":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP/action/citation_signature","submit_replication":"https://pith.science/pith/VW22VT64SNMJD2YTLHKOXBXKOP/action/replication_record"}},"created_at":"2026-07-05T09:20:44.993537+00:00","updated_at":"2026-07-05T09:20:44.993537+00:00"}