{"id":"W2026305448","doi":"10.1109/fuzz-ieee.2012.6251313","title":"A qualitative evaluation criterion for human-robot interaction system in achieving collective tasks","year":2012,"lang":"en","type":"article","venue":"","topic":"Human-Automation Interaction and Safety","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Robot; Computer science; Fuzzy logic; Human–computer interaction; Human–robot interaction; Automation; Task (project management); Artificial intelligence; Task analysis; Knowledge base; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002370066,0.0001467654,0.0002143959,0.000374137,0.0002041509,0.00004546889,0.00007186681,0.0001179804,0.004090863],"category_scores_gemma":[0.0001992245,0.000142746,0.00009294061,0.0002185547,0.00002181081,0.0005647277,0.00001607035,0.0001719127,0.0003843396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001085763,"about_ca_system_score_gemma":0.00003310902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002517677,"about_ca_topic_score_gemma":0.0002201673,"domain_scores_codex":[0.9976305,0.001075878,0.0005486323,0.0002529951,0.0002076223,0.0002843541],"domain_scores_gemma":[0.9986621,0.0005616911,0.0002395261,0.000177787,0.0002937451,0.00006516758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.001022464,0.001043676,0.002571511,0.000185993,0.0002762361,0.000001168846,0.7381107,0.0001599096,0.01086124,0.2121722,0.01588311,0.01771186],"study_design_scores_gemma":[0.007670497,0.0006760845,0.2005457,0.0004680439,0.000165074,0.00006940777,0.7550771,0.0173993,0.001582759,0.001160511,0.01431431,0.0008711559],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6494561,0.00008496986,0.07466808,0.0003985206,0.005014862,0.002560444,0.00002330104,0.0003045103,0.2674892],"genre_scores_gemma":[0.9923861,2.875804e-7,0.0005567506,0.0001529798,0.0002469069,0.001172729,0.00007304731,0.00002102267,0.005390172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.34293,"threshold_uncertainty_score":0.9968196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2396459984465314,"score_gpt":0.5623415808577311,"score_spread":0.3226955824111997,"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."}}