{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CBMBHBGX55AKSFMVEHCWRVKVS4","short_pith_number":"pith:CBMBHBGX","schema_version":"1.0","canonical_sha256":"10581384d7ef40a9159521c568d55597172ba6bf50e512bdaa3c54441a0f3dc0","source":{"kind":"arxiv","id":"2309.02685","version":3},"attestation_state":"computed","paper":{"title":"Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chaewon Hwang, Hyunseok An, Hyunwoo Ryu, Jiwoo Kim, Jongeun Choi, Joohwan Seo, Junwoo Chang, Roberto Horowitz, Taehan Kim, Yubin Kim","submitted_at":"2023-09-06T03:42:20Z","abstract_excerpt":"Diffusion generative modeling has become a promising approach for learning robotic manipulation tasks from stochastic human demonstrations. In this paper, we present Diffusion-EDFs, a novel SE(3)-equivariant diffusion-based approach for visual robotic manipulation tasks. We show that our proposed method achieves remarkable data efficiency, requiring only 5 to 10 human demonstrations for effective end-to-end training in less than an hour. Furthermore, our benchmark experiments demonstrate that our approach has superior generalizability and robustness compared to state-of-the-art methods. Lastly"},"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":"2309.02685","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-06T03:42:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0ca81ca022acbdade9925e47b7720410c6262dd4fb026518e0c27a7c856409e8","abstract_canon_sha256":"b1cd647a1adffb7716ae972d1e2d0d5c28de591174e0a2c02690d7e9b36960eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:54.767108Z","signature_b64":"l9f9z596WzU8WP9F3udNHbwhFaz37ABD7/8DxhlgX9SdyAqPkpIraTS8iGESEVRjSFh1jDvRly3ooALY6jYoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10581384d7ef40a9159521c568d55597172ba6bf50e512bdaa3c54441a0f3dc0","last_reissued_at":"2026-07-05T07:17:54.766579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:54.766579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chaewon Hwang, Hyunseok An, Hyunwoo Ryu, Jiwoo Kim, Jongeun Choi, Joohwan Seo, Junwoo Chang, Roberto Horowitz, Taehan Kim, Yubin Kim","submitted_at":"2023-09-06T03:42:20Z","abstract_excerpt":"Diffusion generative modeling has become a promising approach for learning robotic manipulation tasks from stochastic human demonstrations. In this paper, we present Diffusion-EDFs, a novel SE(3)-equivariant diffusion-based approach for visual robotic manipulation tasks. We show that our proposed method achieves remarkable data efficiency, requiring only 5 to 10 human demonstrations for effective end-to-end training in less than an hour. Furthermore, our benchmark experiments demonstrate that our approach has superior generalizability and robustness compared to state-of-the-art methods. Lastly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02685","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/2309.02685/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":"2309.02685","created_at":"2026-07-05T07:17:54.766654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02685v3","created_at":"2026-07-05T07:17:54.766654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02685","created_at":"2026-07-05T07:17:54.766654+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBMBHBGX55AK","created_at":"2026-07-05T07:17:54.766654+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBMBHBGX55AKSFMV","created_at":"2026-07-05T07:17:54.766654+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBMBHBGX","created_at":"2026-07-05T07:17:54.766654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.18847","citing_title":"Equivariant Volumetric Grasping","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4","json":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4.json","graph_json":"https://pith.science/api/pith-number/CBMBHBGX55AKSFMVEHCWRVKVS4/graph.json","events_json":"https://pith.science/api/pith-number/CBMBHBGX55AKSFMVEHCWRVKVS4/events.json","paper":"https://pith.science/paper/CBMBHBGX"},"agent_actions":{"view_html":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4","download_json":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4.json","view_paper":"https://pith.science/paper/CBMBHBGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02685&json=true","fetch_graph":"https://pith.science/api/pith-number/CBMBHBGX55AKSFMVEHCWRVKVS4/graph.json","fetch_events":"https://pith.science/api/pith-number/CBMBHBGX55AKSFMVEHCWRVKVS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4/action/storage_attestation","attest_author":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4/action/author_attestation","sign_citation":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4/action/citation_signature","submit_replication":"https://pith.science/pith/CBMBHBGX55AKSFMVEHCWRVKVS4/action/replication_record"}},"created_at":"2026-07-05T07:17:54.766654+00:00","updated_at":"2026-07-05T07:17:54.766654+00:00"}