{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2P53TW64J5YPCSTIIFWEDJ2VX7","short_pith_number":"pith:2P53TW64","schema_version":"1.0","canonical_sha256":"d3fbb9dbdc4f70f14a68416c41a755bfc8af146d29335bbcd17b4e5c80471765","source":{"kind":"arxiv","id":"2210.11435","version":2},"attestation_state":"computed","paper":{"title":"Learning and Retrieval from Prior Data for Skill-based Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Ajay Mandlekar, Soroush Nasiriany, Tian Gao, Yuke Zhu","submitted_at":"2022-10-20T17:34:59Z","abstract_excerpt":"Imitation learning offers a promising path for robots to learn general-purpose behaviors, but traditionally has exhibited limited scalability due to high data supervision requirements and brittle generalization. Inspired by recent advances in multi-task imitation learning, we investigate the use of prior data from previous tasks to facilitate learning novel tasks in a robust, data-efficient manner. To make effective use of the prior data, the robot must internalize knowledge from past experiences and contextualize this knowledge in novel tasks. To that end, we develop a skill-based imitation l"},"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":"2210.11435","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T17:34:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"579c4e1aee9ac08f6e1f9208bd450eb16849db9e48eedb92ee1b740921c281b6","abstract_canon_sha256":"e927ef52ded3589275c5bf36fe4f7d30d92f14cb390c556f20c840ffb56cd404"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:03.464345Z","signature_b64":"RkXipK2VJH2WnoqUJ97PpRs4Nmj1I/zmxERxcP3p1T14wmNlxMhub7a/1gfdLeS54At+vLMILusnay5MN9tyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3fbb9dbdc4f70f14a68416c41a755bfc8af146d29335bbcd17b4e5c80471765","last_reissued_at":"2026-07-05T05:16:03.463897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:03.463897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning and Retrieval from Prior Data for Skill-based Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Ajay Mandlekar, Soroush Nasiriany, Tian Gao, Yuke Zhu","submitted_at":"2022-10-20T17:34:59Z","abstract_excerpt":"Imitation learning offers a promising path for robots to learn general-purpose behaviors, but traditionally has exhibited limited scalability due to high data supervision requirements and brittle generalization. Inspired by recent advances in multi-task imitation learning, we investigate the use of prior data from previous tasks to facilitate learning novel tasks in a robust, data-efficient manner. To make effective use of the prior data, the robot must internalize knowledge from past experiences and contextualize this knowledge in novel tasks. To that end, we develop a skill-based imitation l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11435","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/2210.11435/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":"2210.11435","created_at":"2026-07-05T05:16:03.463945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11435v2","created_at":"2026-07-05T05:16:03.463945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11435","created_at":"2026-07-05T05:16:03.463945+00:00"},{"alias_kind":"pith_short_12","alias_value":"2P53TW64J5YP","created_at":"2026-07-05T05:16:03.463945+00:00"},{"alias_kind":"pith_short_16","alias_value":"2P53TW64J5YPCSTI","created_at":"2026-07-05T05:16:03.463945+00:00"},{"alias_kind":"pith_short_8","alias_value":"2P53TW64","created_at":"2026-07-05T05:16:03.463945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31958","citing_title":"Adapting Generalist Robot Policies with Semantic Reinforcement Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05172","citing_title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13403","citing_title":"RotVLA: Rotational Latent Action for Vision-Language-Action Model","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10094","citing_title":"Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10094","citing_title":"Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05172","citing_title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7","json":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7.json","graph_json":"https://pith.science/api/pith-number/2P53TW64J5YPCSTIIFWEDJ2VX7/graph.json","events_json":"https://pith.science/api/pith-number/2P53TW64J5YPCSTIIFWEDJ2VX7/events.json","paper":"https://pith.science/paper/2P53TW64"},"agent_actions":{"view_html":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7","download_json":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7.json","view_paper":"https://pith.science/paper/2P53TW64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11435&json=true","fetch_graph":"https://pith.science/api/pith-number/2P53TW64J5YPCSTIIFWEDJ2VX7/graph.json","fetch_events":"https://pith.science/api/pith-number/2P53TW64J5YPCSTIIFWEDJ2VX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7/action/storage_attestation","attest_author":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7/action/author_attestation","sign_citation":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7/action/citation_signature","submit_replication":"https://pith.science/pith/2P53TW64J5YPCSTIIFWEDJ2VX7/action/replication_record"}},"created_at":"2026-07-05T05:16:03.463945+00:00","updated_at":"2026-07-05T05:16:03.463945+00:00"}