{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7I2HOXTQDW4ZGDD3CLSDZ524BR","short_pith_number":"pith:7I2HOXTQ","schema_version":"1.0","canonical_sha256":"fa34775e701db9930c7b12e43cf75c0c7e3a3b3d559bdadf00e7fd5bc1e64531","source":{"kind":"arxiv","id":"2204.05186","version":1},"attestation_state":"computed","paper":{"title":"Correcting Robot Plans with Natural Language Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Antonio Torralba, Balakumar Sundaralingam, Chris Paxton, Dieter Fox, Jacob Andreas, Pratyusha Sharma, Tucker Hermans, Valts Blukis","submitted_at":"2022-04-11T15:22:43Z","abstract_excerpt":"When humans design cost or goal specifications for robots, they often produce specifications that are ambiguous, underspecified, or beyond planners' ability to solve. In these cases, corrections provide a valuable tool for human-in-the-loop robot control. Corrections might take the form of new goal specifications, new constraints (e.g. to avoid specific objects), or hints for planning algorithms (e.g. to visit specific waypoints). Existing correction methods (e.g. using a joystick or direct manipulation of an end effector) require full teleoperation or real-time interaction. In this paper, we "},"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":"2204.05186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-04-11T15:22:43Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"9d944fe320772a7d2aab93bd756012735b10e8a7f3bb8690652d06ffa4796ad5","abstract_canon_sha256":"edfff3dca4197c4db30e20667e699dd13edd3a96e4bd118f2ee4f1ca6943263c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:18.319788Z","signature_b64":"xawQ1QXv5yLwqYj+f8c9WYJ6+IkBzBbPufAgr+m9l7y9FiKUCWI5wsnOAgmgO7MHcaIo7qSD9HKXTcytzSH5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa34775e701db9930c7b12e43cf75c0c7e3a3b3d559bdadf00e7fd5bc1e64531","last_reissued_at":"2026-07-05T04:13:18.319269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:18.319269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Correcting Robot Plans with Natural Language Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Antonio Torralba, Balakumar Sundaralingam, Chris Paxton, Dieter Fox, Jacob Andreas, Pratyusha Sharma, Tucker Hermans, Valts Blukis","submitted_at":"2022-04-11T15:22:43Z","abstract_excerpt":"When humans design cost or goal specifications for robots, they often produce specifications that are ambiguous, underspecified, or beyond planners' ability to solve. In these cases, corrections provide a valuable tool for human-in-the-loop robot control. Corrections might take the form of new goal specifications, new constraints (e.g. to avoid specific objects), or hints for planning algorithms (e.g. to visit specific waypoints). Existing correction methods (e.g. using a joystick or direct manipulation of an end effector) require full teleoperation or real-time interaction. In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05186","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/2204.05186/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":"2204.05186","created_at":"2026-07-05T04:13:18.319337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05186v1","created_at":"2026-07-05T04:13:18.319337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05186","created_at":"2026-07-05T04:13:18.319337+00:00"},{"alias_kind":"pith_short_12","alias_value":"7I2HOXTQDW4Z","created_at":"2026-07-05T04:13:18.319337+00:00"},{"alias_kind":"pith_short_16","alias_value":"7I2HOXTQDW4ZGDD3","created_at":"2026-07-05T04:13:18.319337+00:00"},{"alias_kind":"pith_short_8","alias_value":"7I2HOXTQ","created_at":"2026-07-05T04:13:18.319337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22319","citing_title":"EmbodiedUS-FS: Fast Slow Intelligence for Ultrasound Robotics","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18189","citing_title":"Beyond Failure Recovery: An Engagement-Aware Human-in-the-loop Framework for Robotic Systems","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08495","citing_title":"EgoPriMo: Egocentric Motion Generation for Interactive Humanoid Control","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32027","citing_title":"Freeform Preference Learning for Robotic Manipulation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2403.01823","citing_title":"RT-H: Action Hierarchies Using Language","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2209.07753","citing_title":"Code as Policies: Language Model Programs for Embodied Control","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2211.09527","citing_title":"Ignore Previous Prompt: Attack Techniques For Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07395","citing_title":"A Physical Agentic Loop for Language-Guided Grasping with Execution-State Monitoring","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR","json":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR.json","graph_json":"https://pith.science/api/pith-number/7I2HOXTQDW4ZGDD3CLSDZ524BR/graph.json","events_json":"https://pith.science/api/pith-number/7I2HOXTQDW4ZGDD3CLSDZ524BR/events.json","paper":"https://pith.science/paper/7I2HOXTQ"},"agent_actions":{"view_html":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR","download_json":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR.json","view_paper":"https://pith.science/paper/7I2HOXTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05186&json=true","fetch_graph":"https://pith.science/api/pith-number/7I2HOXTQDW4ZGDD3CLSDZ524BR/graph.json","fetch_events":"https://pith.science/api/pith-number/7I2HOXTQDW4ZGDD3CLSDZ524BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR/action/storage_attestation","attest_author":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR/action/author_attestation","sign_citation":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR/action/citation_signature","submit_replication":"https://pith.science/pith/7I2HOXTQDW4ZGDD3CLSDZ524BR/action/replication_record"}},"created_at":"2026-07-05T04:13:18.319337+00:00","updated_at":"2026-07-05T04:13:18.319337+00:00"}