{"paper":{"title":"Distill: Uncovering the True Intent behind Human-Robot Communication","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Distill refines initial robot task specifications by removing steps, generalizing meanings, and relaxing order constraints to better match users' true intent.","cross_cats":["cs.HC"],"primary_cat":"cs.RO","authors_text":"David Porfirio, Ting Li","submitted_at":"2026-05-14T02:05:49Z","abstract_excerpt":"As robots become increasingly integrated into everyday environments, intuitive communication paradigms such as natural language and end-user programming have become indispensable for specifying autonomous robot behavior. However, these mechanisms are ineffective at fully capturing user intent: natural language is imprecise and ambiguous, whereas end-user programming can be overly specific. As a result, understanding what users truly mean when they interact with robots remains a central challenge for human-AI communication systems. To address this issue, we propose the Distill approach for huma"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We implemented Distill on a web interface and, through a crowdsourcing study, demonstrated its ability to elicit and refine user intent from initial task specifications.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three operations of removing steps, generalizing meanings, and relaxing ordering constraints accurately uncover and preserve the user's true underlying intent without introducing distortions or requiring additional user feedback.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Distill refines user task specifications for robots by pruning unnecessary steps, generalizing meanings, and relaxing order constraints, as demonstrated in a crowdsourcing study on a web interface.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Distill refines initial robot task specifications by removing steps, generalizing meanings, and relaxing order constraints to better match users' true intent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3c7e1f57c4896afed24b232d24bc06a74cd82a3d4a23bfb2cfd5f2e943b9247b"},"source":{"id":"2605.14262","kind":"arxiv","version":1},"verdict":{"id":"a25cc9a5-1ff3-4f5b-afed-08cfcd02f491","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:42:54.220080Z","strongest_claim":"We implemented Distill on a web interface and, through a crowdsourcing study, demonstrated its ability to elicit and refine user intent from initial task specifications.","one_line_summary":"Distill refines user task specifications for robots by pruning unnecessary steps, generalizing meanings, and relaxing order constraints, as demonstrated in a crowdsourcing study on a web interface.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three operations of removing steps, generalizing meanings, and relaxing ordering constraints accurately uncover and preserve the user's true underlying intent without introducing distortions or requiring additional user feedback.","pith_extraction_headline":"Distill refines initial robot task specifications by removing steps, generalizing meanings, and relaxing order constraints to better match users' true intent."},"references":{"count":66,"sample":[{"doi":"","year":2026,"title":"[n. d.]. LimeZu. https://limezu.itch.io/. Accessed: 2026-04-25","work_id":"1d9e6538-69c2-45b5-8947-d87ad8c7a9fb","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/3466819","year":2021,"title":"Gopika Ajaykumar, Maureen Steele, and Chien-Ming Huang. 2021. A survey on end-user robot programming.ACM Computing Surveys (CSUR)54, 8 (2021), 1–36. doi:10.1145/3466819","work_id":"d85ffb44-f447-40d9-b11a-364497a021d4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/icra.2015.7139973","year":2015,"title":"Sonya Alexandrova, Zachary Tatlock, and Maya Cakmak. 2015. RoboFlow: A flow-based visual programming language for mobile manipulation tasks. In2015 IEEE international conference on robotics and automa","work_id":"dca3e8d2-891d-4166-b78d-967482f901f0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/3290605.3300233","year":2019,"title":"Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz","work_id":"2734701f-773b-4092-8c0a-a34d39c6e99c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Virginia Braun and Victoria Clarke. 2021. Thematic analysis: A practical guide. (2021)","work_id":"8e7fb43f-18c7-4243-abfb-26ba4021a665","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":66,"snapshot_sha256":"224b5d05de26d16a966047a0fa0b0b6f41e518db712f6afd5e73e9ab038708e3","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c951fc5b2aa3e100b49e2157167b8c27913e507a6bc42678790c507b11966eeb"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}