{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BAFPK6LSTKA42PJ7QE3CG3M3OQ","short_pith_number":"pith:BAFPK6LS","schema_version":"1.0","canonical_sha256":"080af579729a81cd3d3f8136236d9b7427d10101855e328c9ac0c39666b515e2","source":{"kind":"arxiv","id":"2310.16050","version":2},"attestation_state":"computed","paper":{"title":"EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Congyue Deng, Jeannette Bohg, Jimmy Wu, Jingyun Yang, Leonidas Guibas, Rika Antonova","submitted_at":"2023-10-24T17:59:48Z","abstract_excerpt":"If a robot masters folding a kitchen towel, we would expect it to master folding a large beach towel. However, existing policy learning methods that rely on data augmentation still don't guarantee such generalization. Our insight is to add equivariance to both the visual object representation and policy architecture. We propose EquivAct which utilizes SIM(3)-equivariant network structures that guarantee generalization across all possible object translations, 3D rotations, and scales by construction. EquivAct is trained in two phases. We first pre-train a SIM(3)-equivariant visual representatio"},"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":"2310.16050","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-24T17:59:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e6925536145e0a39ce2db570470cafabd9c210e3e6358036f9b0716c8c81968e","abstract_canon_sha256":"87b71a8248d392ab30c3df080cc67f687a0281127551f63ac8251a822bbe7bb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:55.137392Z","signature_b64":"QaXiqIpppQNNvq5kW+qGjukhW8nGdkbRctrT6aBTol8PB3aDlLT7rSKd1+RTnr4dfpQZAHnN7bnqYKpweOHKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"080af579729a81cd3d3f8136236d9b7427d10101855e328c9ac0c39666b515e2","last_reissued_at":"2026-07-05T08:38:55.136887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:55.136887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Congyue Deng, Jeannette Bohg, Jimmy Wu, Jingyun Yang, Leonidas Guibas, Rika Antonova","submitted_at":"2023-10-24T17:59:48Z","abstract_excerpt":"If a robot masters folding a kitchen towel, we would expect it to master folding a large beach towel. However, existing policy learning methods that rely on data augmentation still don't guarantee such generalization. Our insight is to add equivariance to both the visual object representation and policy architecture. We propose EquivAct which utilizes SIM(3)-equivariant network structures that guarantee generalization across all possible object translations, 3D rotations, and scales by construction. EquivAct is trained in two phases. We first pre-train a SIM(3)-equivariant visual representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16050","kind":"arxiv","version":2},"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/2310.16050/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":"2310.16050","created_at":"2026-07-05T08:38:55.136948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16050v2","created_at":"2026-07-05T08:38:55.136948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16050","created_at":"2026-07-05T08:38:55.136948+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAFPK6LSTKA4","created_at":"2026-07-05T08:38:55.136948+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAFPK6LSTKA42PJ7","created_at":"2026-07-05T08:38:55.136948+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAFPK6LS","created_at":"2026-07-05T08:38:55.136948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ","json":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ.json","graph_json":"https://pith.science/api/pith-number/BAFPK6LSTKA42PJ7QE3CG3M3OQ/graph.json","events_json":"https://pith.science/api/pith-number/BAFPK6LSTKA42PJ7QE3CG3M3OQ/events.json","paper":"https://pith.science/paper/BAFPK6LS"},"agent_actions":{"view_html":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ","download_json":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ.json","view_paper":"https://pith.science/paper/BAFPK6LS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16050&json=true","fetch_graph":"https://pith.science/api/pith-number/BAFPK6LSTKA42PJ7QE3CG3M3OQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BAFPK6LSTKA42PJ7QE3CG3M3OQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ/action/storage_attestation","attest_author":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ/action/author_attestation","sign_citation":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ/action/citation_signature","submit_replication":"https://pith.science/pith/BAFPK6LSTKA42PJ7QE3CG3M3OQ/action/replication_record"}},"created_at":"2026-07-05T08:38:55.136948+00:00","updated_at":"2026-07-05T08:38:55.136948+00:00"}