{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001376024,0.00006563286,0.0000743877,0.00008322417,0.000239582,0.0001047499,0.00008897635,0.00005427247,0.01908893],"category_scores_gemma":[0.00004122486,0.00006009724,0.0000464057,0.0000788115,0.00004179103,0.0002166027,0.000009225316,0.00006285188,0.002717058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002396307,"about_ca_system_score_gemma":0.0000132494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000112074,"about_ca_topic_score_gemma":0.000008159587,"domain_scores_codex":[0.999368,0.00003421216,0.0002085744,0.0001831582,0.00005903707,0.0001470501],"domain_scores_gemma":[0.9993703,0.0001655217,0.00007196613,0.0002248445,0.0001235795,0.00004382207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005549707,0.0001901443,0.004584062,0.000006699987,0.00009586903,0.00000162405,0.006061143,0.00002959923,0.004664555,0.3486314,0.6230434,0.01263604],"study_design_scores_gemma":[0.0004415527,0.00004704822,0.1115858,0.00001187098,0.00001011662,0.00001033344,0.004426451,0.001034694,0.0004567343,0.0005321943,0.8813119,0.0001312867],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01589139,0.000007921753,0.49128,0.001217136,0.001601279,0.0001519195,0.000004163989,0.0002070712,0.4896391],"genre_scores_gemma":[0.9308807,1.9073e-7,0.01186804,0.0009495989,0.0006761264,0.00005737819,0.00002370316,0.00001432379,0.05553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9149892,"threshold_uncertainty_score":0.9980595,"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."}}