{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:II2U22NRVE4PWFWRQV4WPYTOPF","short_pith_number":"pith:II2U22NR","schema_version":"1.0","canonical_sha256":"42354d69b1a938fb16d1857967e26e7949f5d403136816b3d0dd5c31bf1d696d","source":{"kind":"arxiv","id":"2310.17555","version":1},"attestation_state":"computed","paper":{"title":"Interactive Robot Learning from Verbal Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Adith Swaminathan, Alice Chen, Andrey Kolobov, Ching-An Cheng, Huihan Liu, Yuke Zhu","submitted_at":"2023-10-26T16:46:12Z","abstract_excerpt":"The ability to learn and refine behavior after deployment has become ever more important for robots as we design them to operate in unstructured environments like households. In this work, we design a new learning system based on large language model (LLM), OLAF, that allows everyday users to teach a robot using verbal corrections when the robot makes mistakes, e.g., by saying \"Stop what you're doing. You should move closer to the cup.\" A key feature of OLAF is its ability to update the robot's visuomotor neural policy based on the verbal feedback to avoid repeating mistakes in the future. Thi"},"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":"2310.17555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-10-26T16:46:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"931ebb84eb62fd83a7458e43399b3c35c4db8cc637bbd22cdb36b6e3fca0bb54","abstract_canon_sha256":"13c8377106d841f364fe16d70cddf8a502932b2827768ba17c7b9a3441b6b837"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:36.003135Z","signature_b64":"14CeVacrwAgZ95xjpDuKX1x+ly69O4cN5NX2vA4dnlCRtN1F+V2lFRL73Un5IxQMvRc6o/yhxVh+jMVcbQSnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42354d69b1a938fb16d1857967e26e7949f5d403136816b3d0dd5c31bf1d696d","last_reissued_at":"2026-07-05T07:05:36.002654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:36.002654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Robot Learning from Verbal Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Adith Swaminathan, Alice Chen, Andrey Kolobov, Ching-An Cheng, Huihan Liu, Yuke Zhu","submitted_at":"2023-10-26T16:46:12Z","abstract_excerpt":"The ability to learn and refine behavior after deployment has become ever more important for robots as we design them to operate in unstructured environments like households. In this work, we design a new learning system based on large language model (LLM), OLAF, that allows everyday users to teach a robot using verbal corrections when the robot makes mistakes, e.g., by saying \"Stop what you're doing. You should move closer to the cup.\" A key feature of OLAF is its ability to update the robot's visuomotor neural policy based on the verbal feedback to avoid repeating mistakes in the future. Thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17555","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/2310.17555/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":"2310.17555","created_at":"2026-07-05T07:05:36.002716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17555v1","created_at":"2026-07-05T07:05:36.002716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17555","created_at":"2026-07-05T07:05:36.002716+00:00"},{"alias_kind":"pith_short_12","alias_value":"II2U22NRVE4P","created_at":"2026-07-05T07:05:36.002716+00:00"},{"alias_kind":"pith_short_16","alias_value":"II2U22NRVE4PWFWR","created_at":"2026-07-05T07:05:36.002716+00:00"},{"alias_kind":"pith_short_8","alias_value":"II2U22NR","created_at":"2026-07-05T07:05:36.002716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19417","citing_title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF","json":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF.json","graph_json":"https://pith.science/api/pith-number/II2U22NRVE4PWFWRQV4WPYTOPF/graph.json","events_json":"https://pith.science/api/pith-number/II2U22NRVE4PWFWRQV4WPYTOPF/events.json","paper":"https://pith.science/paper/II2U22NR"},"agent_actions":{"view_html":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF","download_json":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF.json","view_paper":"https://pith.science/paper/II2U22NR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17555&json=true","fetch_graph":"https://pith.science/api/pith-number/II2U22NRVE4PWFWRQV4WPYTOPF/graph.json","fetch_events":"https://pith.science/api/pith-number/II2U22NRVE4PWFWRQV4WPYTOPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF/action/storage_attestation","attest_author":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF/action/author_attestation","sign_citation":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF/action/citation_signature","submit_replication":"https://pith.science/pith/II2U22NRVE4PWFWRQV4WPYTOPF/action/replication_record"}},"created_at":"2026-07-05T07:05:36.002716+00:00","updated_at":"2026-07-05T07:05:36.002716+00:00"}