{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CZHWIF4OEPPGDUG66ITTRTAPHM","short_pith_number":"pith:CZHWIF4O","schema_version":"1.0","canonical_sha256":"164f64178e23de61d0def22738cc0f3b1965b1809e611b46ab71f2805357f82f","source":{"kind":"arxiv","id":"2203.04923","version":3},"attestation_state":"computed","paper":{"title":"On-Robot Learning With Equivariant Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dian Wang, Mingxi Jia, Robert Platt, Robin Walters, Xupeng Zhu","submitted_at":"2022-03-09T18:10:47Z","abstract_excerpt":"Recently, equivariant neural network models have been shown to improve sample efficiency for tasks in computer vision and reinforcement learning. This paper explores this idea in the context of on-robot policy learning in which a policy must be learned entirely on a physical robotic system without reference to a model, a simulator, or an offline dataset. We focus on applications of Equivariant SAC to robotic manipulation and explore a number of variations of the algorithm. Ultimately, we demonstrate the ability to learn several non-trivial manipulation tasks completely through on-robot experie"},"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":"2203.04923","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-03-09T18:10:47Z","cross_cats_sorted":[],"title_canon_sha256":"4b453f2373a45f303e140777f7078eefc891b6c1a6a02eaf6bbb85c48209317a","abstract_canon_sha256":"8b9c53f203af15f1903bb9eeacf326cf0ceb60bc0b1b2f9f9d48d6f9432f2ac7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:21.909735Z","signature_b64":"Nva9Gd+18jKGkGUTvAterlec3CNCa+XLNP+n0AYsNqviLBH+hZ8jVH+s0lXXdGjzvYehQZSxGJ73XZp96t0qBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"164f64178e23de61d0def22738cc0f3b1965b1809e611b46ab71f2805357f82f","last_reissued_at":"2026-07-05T05:07:21.909227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:21.909227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On-Robot Learning With Equivariant Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dian Wang, Mingxi Jia, Robert Platt, Robin Walters, Xupeng Zhu","submitted_at":"2022-03-09T18:10:47Z","abstract_excerpt":"Recently, equivariant neural network models have been shown to improve sample efficiency for tasks in computer vision and reinforcement learning. This paper explores this idea in the context of on-robot policy learning in which a policy must be learned entirely on a physical robotic system without reference to a model, a simulator, or an offline dataset. We focus on applications of Equivariant SAC to robotic manipulation and explore a number of variations of the algorithm. Ultimately, we demonstrate the ability to learn several non-trivial manipulation tasks completely through on-robot experie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04923","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/2203.04923/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":"2203.04923","created_at":"2026-07-05T05:07:21.909296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.04923v3","created_at":"2026-07-05T05:07:21.909296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04923","created_at":"2026-07-05T05:07:21.909296+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZHWIF4OEPPG","created_at":"2026-07-05T05:07:21.909296+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZHWIF4OEPPGDUG6","created_at":"2026-07-05T05:07:21.909296+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZHWIF4O","created_at":"2026-07-05T05:07:21.909296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19928","citing_title":"SWAP: Symmetric Equivariant World-Model for Agile Robot Parkour","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM","json":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM.json","graph_json":"https://pith.science/api/pith-number/CZHWIF4OEPPGDUG66ITTRTAPHM/graph.json","events_json":"https://pith.science/api/pith-number/CZHWIF4OEPPGDUG66ITTRTAPHM/events.json","paper":"https://pith.science/paper/CZHWIF4O"},"agent_actions":{"view_html":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM","download_json":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM.json","view_paper":"https://pith.science/paper/CZHWIF4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.04923&json=true","fetch_graph":"https://pith.science/api/pith-number/CZHWIF4OEPPGDUG66ITTRTAPHM/graph.json","fetch_events":"https://pith.science/api/pith-number/CZHWIF4OEPPGDUG66ITTRTAPHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM/action/storage_attestation","attest_author":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM/action/author_attestation","sign_citation":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM/action/citation_signature","submit_replication":"https://pith.science/pith/CZHWIF4OEPPGDUG66ITTRTAPHM/action/replication_record"}},"created_at":"2026-07-05T05:07:21.909296+00:00","updated_at":"2026-07-05T05:07:21.909296+00:00"}