{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MHSU4XVPD55AOFXLEPDLYYT2TP","short_pith_number":"pith:MHSU4XVP","schema_version":"1.0","canonical_sha256":"61e54e5eaf1f7a0716eb23c6bc627a9bfc6b61c2e7dd25cf55d748b6e12e8850","source":{"kind":"arxiv","id":"2606.09758","version":1},"attestation_state":"computed","paper":{"title":"Difference-Aware Retrieval Policies for Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Ethan Pronovost, Khimya Khetarpal, Paarth Shah, Quinn Pfeifer, Siddhartha Srinivasa","submitted_at":"2026-06-08T17:18:19Z","abstract_excerpt":"Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment. We show that reusing the training data during inference via a semi-parametric retrieval-based imitation learning approach can alleviate this challenge. We present Difference-Aware Retrieval Policies for Imitation Learning (DARP), a semi-parametric retrieval-based imitation learning approach that addresses this limitation by reparameterizing the imitation learning problem in terms of local neighborhood structure rather than direct stat"},"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":"2606.09758","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-08T17:18:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4734e821703bf1eaea2526c5e1c5cdd8e23f56738a7fe3ac9d65c00071437c54","abstract_canon_sha256":"b5173d05e2579ee706d41fc527e0a629b55ec3afdd6785723629ccb3b747c6a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:08.045155Z","signature_b64":"zfwHjx3TTd+iN3fYb0wxNYsOBYyazCfg22ZrfX+TveA59YETSy5HfYTLyKf1mdAGDLXZTkDkPyY60L37DVbOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e54e5eaf1f7a0716eb23c6bc627a9bfc6b61c2e7dd25cf55d748b6e12e8850","last_reissued_at":"2026-06-09T02:09:08.044353Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:08.044353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Difference-Aware Retrieval Policies for Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Ethan Pronovost, Khimya Khetarpal, Paarth Shah, Quinn Pfeifer, Siddhartha Srinivasa","submitted_at":"2026-06-08T17:18:19Z","abstract_excerpt":"Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment. We show that reusing the training data during inference via a semi-parametric retrieval-based imitation learning approach can alleviate this challenge. We present Difference-Aware Retrieval Policies for Imitation Learning (DARP), a semi-parametric retrieval-based imitation learning approach that addresses this limitation by reparameterizing the imitation learning problem in terms of local neighborhood structure rather than direct stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09758","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/2606.09758/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":"2606.09758","created_at":"2026-06-09T02:09:08.044487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09758v1","created_at":"2026-06-09T02:09:08.044487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09758","created_at":"2026-06-09T02:09:08.044487+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHSU4XVPD55A","created_at":"2026-06-09T02:09:08.044487+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHSU4XVPD55AOFXL","created_at":"2026-06-09T02:09:08.044487+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHSU4XVP","created_at":"2026-06-09T02:09:08.044487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP","json":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP.json","graph_json":"https://pith.science/api/pith-number/MHSU4XVPD55AOFXLEPDLYYT2TP/graph.json","events_json":"https://pith.science/api/pith-number/MHSU4XVPD55AOFXLEPDLYYT2TP/events.json","paper":"https://pith.science/paper/MHSU4XVP"},"agent_actions":{"view_html":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP","download_json":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP.json","view_paper":"https://pith.science/paper/MHSU4XVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09758&json=true","fetch_graph":"https://pith.science/api/pith-number/MHSU4XVPD55AOFXLEPDLYYT2TP/graph.json","fetch_events":"https://pith.science/api/pith-number/MHSU4XVPD55AOFXLEPDLYYT2TP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP/action/storage_attestation","attest_author":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP/action/author_attestation","sign_citation":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP/action/citation_signature","submit_replication":"https://pith.science/pith/MHSU4XVPD55AOFXLEPDLYYT2TP/action/replication_record"}},"created_at":"2026-06-09T02:09:08.044487+00:00","updated_at":"2026-06-09T02:09:08.044487+00:00"}