{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H2FEXZVJ5AHREPNA3RTOYJG7AP","short_pith_number":"pith:H2FEXZVJ","schema_version":"1.0","canonical_sha256":"3e8a4be6a9e80f123da0dc66ec24df03d6b81fa3a8ff0b09d0a2fef1c77cac4e","source":{"kind":"arxiv","id":"2410.08852","version":2},"attestation_state":"computed","paper":{"title":"Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Aaditya Ramdas, Andrea Bajcsy, Henny Admoni, Michelle Zhao, Reid Simmons","submitted_at":"2024-10-11T14:27:56Z","abstract_excerpt":"In interactive imitation learning (IL), uncertainty quantification offers a way for the learner (i.e. robot) to contend with distribution shifts encountered during deployment by actively seeking additional feedback from an expert (i.e. human) online. Prior works use mechanisms like ensemble disagreement or Monte Carlo dropout to quantify when black-box IL policies are uncertain; however, these approaches can lead to overconfident estimates when faced with deployment-time distribution shifts. Instead, we contend that we need uncertainty quantification algorithms that can leverage the expert hum"},"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":"2410.08852","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-11T14:27:56Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"be459e18d4dab0b5eca713f2d14cb7cc61cfe44ee121f88b8e31a8d0a34d41ca","abstract_canon_sha256":"f58553b2b5447acd122ff38f42a522414da0ac2c197c48dc3702c0a7b3f2a5f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:09.798648Z","signature_b64":"Xx6XIHepCx84yiZo4WXsEPiTQkFc62903CVQVwylzBE8XdiZYESz/QPn/A+809YcWZg0fyeIAQBsu5z/O26lBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8a4be6a9e80f123da0dc66ec24df03d6b81fa3a8ff0b09d0a2fef1c77cac4e","last_reissued_at":"2026-07-05T10:56:09.798175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:09.798175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.RO","authors_text":"Aaditya Ramdas, Andrea Bajcsy, Henny Admoni, Michelle Zhao, Reid Simmons","submitted_at":"2024-10-11T14:27:56Z","abstract_excerpt":"In interactive imitation learning (IL), uncertainty quantification offers a way for the learner (i.e. robot) to contend with distribution shifts encountered during deployment by actively seeking additional feedback from an expert (i.e. human) online. Prior works use mechanisms like ensemble disagreement or Monte Carlo dropout to quantify when black-box IL policies are uncertain; however, these approaches can lead to overconfident estimates when faced with deployment-time distribution shifts. Instead, we contend that we need uncertainty quantification algorithms that can leverage the expert hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08852","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/2410.08852/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":"2410.08852","created_at":"2026-07-05T10:56:09.798234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08852v2","created_at":"2026-07-05T10:56:09.798234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08852","created_at":"2026-07-05T10:56:09.798234+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2FEXZVJ5AHR","created_at":"2026-07-05T10:56:09.798234+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2FEXZVJ5AHREPNA","created_at":"2026-07-05T10:56:09.798234+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2FEXZVJ","created_at":"2026-07-05T10:56:09.798234+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23617","citing_title":"RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP","json":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP.json","graph_json":"https://pith.science/api/pith-number/H2FEXZVJ5AHREPNA3RTOYJG7AP/graph.json","events_json":"https://pith.science/api/pith-number/H2FEXZVJ5AHREPNA3RTOYJG7AP/events.json","paper":"https://pith.science/paper/H2FEXZVJ"},"agent_actions":{"view_html":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP","download_json":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP.json","view_paper":"https://pith.science/paper/H2FEXZVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08852&json=true","fetch_graph":"https://pith.science/api/pith-number/H2FEXZVJ5AHREPNA3RTOYJG7AP/graph.json","fetch_events":"https://pith.science/api/pith-number/H2FEXZVJ5AHREPNA3RTOYJG7AP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP/action/storage_attestation","attest_author":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP/action/author_attestation","sign_citation":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP/action/citation_signature","submit_replication":"https://pith.science/pith/H2FEXZVJ5AHREPNA3RTOYJG7AP/action/replication_record"}},"created_at":"2026-07-05T10:56:09.798234+00:00","updated_at":"2026-07-05T10:56:09.798234+00:00"}