{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QCJZYRJ5AXGFMWAIE3H5IFEVV7","short_pith_number":"pith:QCJZYRJ5","schema_version":"1.0","canonical_sha256":"80939c453d05cc56580826cfd41495afc9e7faf7c1b33832203237f3ea3427c1","source":{"kind":"arxiv","id":"2211.00194","version":1},"attestation_state":"computed","paper":{"title":"SEIL: Simulation-augmented Equivariant Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"David Klee, Dian Wang, Guanang Su, Mingxi Jia, Robert Platt, Robin Walters, Xupeng Zhu","submitted_at":"2022-10-31T23:37:29Z","abstract_excerpt":"In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine learning tasks. However, image-level data augmentation is insufficient for an imitation learning agent to learn good manipulation policies in a reasonable amount of demonstrations. We propose Simulation-augmented Equivariant Imitation Learning (SEIL), a method that combines a novel data augmentation strategy of supplementing expert trajectories with simulated"},"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":"2211.00194","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-10-31T23:37:29Z","cross_cats_sorted":[],"title_canon_sha256":"b070a2340b180d3fda6200ca5ad477e2edb00abe0c6e1113ec66269204af6baf","abstract_canon_sha256":"564ef2507713cd4afcea0529498a2f6fa9e49f2f5038ea026f277877af4fbdc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:19.761411Z","signature_b64":"eE22iMpbIwc0aARYY+y62+NcmSDPp7f7tN5a0Rd5H7uqmetiXqU4Oq9jxai+y12iRfliIAtBVzw4SZC76QpbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80939c453d05cc56580826cfd41495afc9e7faf7c1b33832203237f3ea3427c1","last_reissued_at":"2026-07-05T05:12:19.760939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:19.760939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEIL: Simulation-augmented Equivariant Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"David Klee, Dian Wang, Guanang Su, Mingxi Jia, Robert Platt, Robin Walters, Xupeng Zhu","submitted_at":"2022-10-31T23:37:29Z","abstract_excerpt":"In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine learning tasks. However, image-level data augmentation is insufficient for an imitation learning agent to learn good manipulation policies in a reasonable amount of demonstrations. We propose Simulation-augmented Equivariant Imitation Learning (SEIL), a method that combines a novel data augmentation strategy of supplementing expert trajectories with simulated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00194","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/2211.00194/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":"2211.00194","created_at":"2026-07-05T05:12:19.760996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00194v1","created_at":"2026-07-05T05:12:19.760996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00194","created_at":"2026-07-05T05:12:19.760996+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCJZYRJ5AXGF","created_at":"2026-07-05T05:12:19.760996+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCJZYRJ5AXGFMWAI","created_at":"2026-07-05T05:12:19.760996+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCJZYRJ5","created_at":"2026-07-05T05:12:19.760996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19784","citing_title":"EquiVLA: A General Framework for Rotationally Equivariant Vision-Language-Action Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12228","citing_title":"Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulation","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7","json":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7.json","graph_json":"https://pith.science/api/pith-number/QCJZYRJ5AXGFMWAIE3H5IFEVV7/graph.json","events_json":"https://pith.science/api/pith-number/QCJZYRJ5AXGFMWAIE3H5IFEVV7/events.json","paper":"https://pith.science/paper/QCJZYRJ5"},"agent_actions":{"view_html":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7","download_json":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7.json","view_paper":"https://pith.science/paper/QCJZYRJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00194&json=true","fetch_graph":"https://pith.science/api/pith-number/QCJZYRJ5AXGFMWAIE3H5IFEVV7/graph.json","fetch_events":"https://pith.science/api/pith-number/QCJZYRJ5AXGFMWAIE3H5IFEVV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7/action/storage_attestation","attest_author":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7/action/author_attestation","sign_citation":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7/action/citation_signature","submit_replication":"https://pith.science/pith/QCJZYRJ5AXGFMWAIE3H5IFEVV7/action/replication_record"}},"created_at":"2026-07-05T05:12:19.760996+00:00","updated_at":"2026-07-05T05:12:19.760996+00:00"}