{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ENEYN5WE6RJDDJNVC7IIPRXBVN","short_pith_number":"pith:ENEYN5WE","schema_version":"1.0","canonical_sha256":"234986f6c4f45231a5b517d087c6e1ab4b092aa9a4ff8ac2cc49b8ab3d04b549","source":{"kind":"arxiv","id":"2310.12972","version":2},"attestation_state":"computed","paper":{"title":"CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhay Deshpande, Abhishek Gupta, Liyiming Ke, Siddhartha Srinivasa, Yunchu Zhang","submitted_at":"2023-10-19T17:59:03Z","abstract_excerpt":"We present a new technique to enhance the robustness of imitation learning methods by generating corrective data to account for compounding errors and disturbances. While existing methods rely on interactive expert labeling, additional offline datasets, or domain-specific invariances, our approach requires minimal additional assumptions beyond access to expert data. The key insight is to leverage local continuity in the environment dynamics to generate corrective labels. Our method first constructs a dynamics model from the expert demonstration, encouraging local Lipschitz continuity in the le"},"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":"2310.12972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-19T17:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"71c24a06fe88f922794d360a5650e6d2dcdc652fdfc42cc15677dfdfd8837a8e","abstract_canon_sha256":"c4919d51119430bfeb5a7c16f5e0494bcacf08ba95ed8520295c12a8d8f8a946"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:42.851277Z","signature_b64":"jgjXUlOFfvxSMvV/rzu+TT3N8Wu29cfEZxLBm5WKA7J3CuwuOtlyu0RNEa6b/k92WWSEfqnjMkZWw0Y0Lu0jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"234986f6c4f45231a5b517d087c6e1ab4b092aa9a4ff8ac2cc49b8ab3d04b549","last_reissued_at":"2026-07-05T08:26:42.850810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:42.850810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhay Deshpande, Abhishek Gupta, Liyiming Ke, Siddhartha Srinivasa, Yunchu Zhang","submitted_at":"2023-10-19T17:59:03Z","abstract_excerpt":"We present a new technique to enhance the robustness of imitation learning methods by generating corrective data to account for compounding errors and disturbances. While existing methods rely on interactive expert labeling, additional offline datasets, or domain-specific invariances, our approach requires minimal additional assumptions beyond access to expert data. The key insight is to leverage local continuity in the environment dynamics to generate corrective labels. Our method first constructs a dynamics model from the expert demonstration, encouraging local Lipschitz continuity in the le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12972","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/2310.12972/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":"2310.12972","created_at":"2026-07-05T08:26:42.850862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12972v2","created_at":"2026-07-05T08:26:42.850862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12972","created_at":"2026-07-05T08:26:42.850862+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENEYN5WE6RJD","created_at":"2026-07-05T08:26:42.850862+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENEYN5WE6RJDDJNV","created_at":"2026-07-05T08:26:42.850862+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENEYN5WE","created_at":"2026-07-05T08:26:42.850862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21406","citing_title":"Robot Self-Improvement via Human-Video Dynamics Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19586","citing_title":"One Demo is Worth a Thousand Trajectories: Action-View Augmentation for Visuomotor Policies","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN","json":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN.json","graph_json":"https://pith.science/api/pith-number/ENEYN5WE6RJDDJNVC7IIPRXBVN/graph.json","events_json":"https://pith.science/api/pith-number/ENEYN5WE6RJDDJNVC7IIPRXBVN/events.json","paper":"https://pith.science/paper/ENEYN5WE"},"agent_actions":{"view_html":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN","download_json":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN.json","view_paper":"https://pith.science/paper/ENEYN5WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12972&json=true","fetch_graph":"https://pith.science/api/pith-number/ENEYN5WE6RJDDJNVC7IIPRXBVN/graph.json","fetch_events":"https://pith.science/api/pith-number/ENEYN5WE6RJDDJNVC7IIPRXBVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN/action/storage_attestation","attest_author":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN/action/author_attestation","sign_citation":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN/action/citation_signature","submit_replication":"https://pith.science/pith/ENEYN5WE6RJDDJNVC7IIPRXBVN/action/replication_record"}},"created_at":"2026-07-05T08:26:42.850862+00:00","updated_at":"2026-07-05T08:26:42.850862+00:00"}