{"id":"W2899850214","doi":"10.1109/roman.2018.8525546","title":"Assessing User Specifications for Robot Task Planning","year":2018,"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; Supervisor; Task (project management); Computer science; Human–computer interaction; Variety (cybernetics); Task analysis; Human–robot interaction; Quality (philosophy); Artificial intelligence; Engineering; Systems 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01252928,0.0007251256,0.0003729341,0.001381424,0.0005250581,0.002154337,0.0008180895,0.001007361,0.001474781],"category_scores_gemma":[0.110505,0.0003804688,0.0004760889,0.000552207,0.0006255261,0.001416271,0.001349464,0.0007186979,0.0005869942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009458155,"about_ca_system_score_gemma":0.0008036438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002701677,"about_ca_topic_score_gemma":0.003916977,"domain_scores_codex":[0.9899351,0.005325697,0.001178568,0.0006062571,0.002661596,0.0002928159],"domain_scores_gemma":[0.8282022,0.1248097,0.01560265,0.010993,0.01781459,0.002577834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002310349,0.001460532,0.7338681,0.000500052,0.0001824759,0.0004121204,0.02818661,0.01242857,0.01595691,0.00139754,0.002305941,0.2009909],"study_design_scores_gemma":[0.0002356097,0.006979895,0.7353099,0.0003545971,0.0002720772,0.00186308,0.02695146,0.1852327,0.02869375,0.003164937,0.01044757,0.0004943282],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9804033,0.00007106993,0.0172081,0.00006489481,0.000005485836,0.0001455225,0.0001119564,0.0004058911,0.001583873],"genre_scores_gemma":[0.9851967,0.00003459368,0.01386782,0.00003072647,0.000002436848,0.0001170496,0.0003143247,0.00004710639,0.0003892585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01252928,"threshold_uncertainty_score":0.06626189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2414312944350762,"score_gpt":0.4891213810304627,"score_spread":0.2476900865953865,"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."}}