{"id":"W2963106920","doi":"10.1177/0278364920910802","title":"Improving user specifications for robot behavior through active preference learning: Framework and evaluation","year":2020,"lang":"en","type":"article","venue":"The International Journal of Robotics Research","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Task (project management); Robot; Process (computing); Preference; Preference elicitation; Preference learning; Task analysis; Active learning (machine learning)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009851101,0.00008096398,0.0001096478,0.0001003568,0.0001602032,0.0001905091,0.0004425841,0.00006017249,0.00008044257],"category_scores_gemma":[0.001663038,0.00006483069,0.00005307925,0.0001659494,0.00006060081,0.0002809206,0.00007430749,0.0009000444,0.000009885395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001349855,"about_ca_system_score_gemma":0.00008125814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006428451,"about_ca_topic_score_gemma":0.000002690899,"domain_scores_codex":[0.9983693,0.0001379349,0.000292254,0.0001070416,0.000934609,0.0001588978],"domain_scores_gemma":[0.9975371,0.0007905471,0.0001214156,0.00008495073,0.001392757,0.00007318139],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005280117,0.00001777531,0.0006698495,0.000011213,0.00007250727,0.000001851351,0.002152164,0.9734004,0.005086922,0.004887185,0.0003269262,0.01332041],"study_design_scores_gemma":[0.0005507497,0.0001646694,0.007937955,0.00006616792,0.00005564665,0.00002352404,0.002061775,0.9819922,0.001933207,0.002121137,0.002975572,0.0001174009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05906988,0.0003623616,0.9304451,0.008637839,0.0004801828,0.0005124626,0.000002054478,0.00003600601,0.0004540961],"genre_scores_gemma":[0.9778736,0.0001693647,0.02122384,0.00005071795,0.000563965,0.00002142522,0.000006450333,0.00002285504,0.00006774103],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9188038,"threshold_uncertainty_score":0.3910295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4275317402355947,"score_gpt":0.4292571667206051,"score_spread":0.001725426485010395,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}