{"id":"W2941455863","doi":"10.1145/3290605.3300750","title":"Automation Accuracy Is Good, but High Controllability May Be Better","year":2019,"lang":"en","type":"article","venue":"","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Controllability; Automation; Task (project management); Computer science; Preference; Control (management); Human–computer interaction; Constant (computer programming); Artificial intelligence; Machine learning; Engineering; Statistics; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004179054,0.0001528995,0.0002132591,0.00005792191,0.0001037027,0.0003353411,0.0004698917,0.00008677816,0.0004339307],"category_scores_gemma":[0.00006551411,0.0001265775,0.00008607007,0.0002002981,0.00002991839,0.000592901,0.0001673686,0.0001264303,0.0007419091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005280261,"about_ca_system_score_gemma":0.00005263253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002886876,"about_ca_topic_score_gemma":0.000007626167,"domain_scores_codex":[0.9985461,0.00008587119,0.0002719437,0.0004854414,0.0003051997,0.0003054608],"domain_scores_gemma":[0.9983879,0.000297433,0.0001030478,0.001018376,0.000110848,0.00008234489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006370995,0.0005173516,0.1834623,0.0002860386,0.0002349164,0.00003723722,0.005750627,0.001212692,0.09957837,0.1987079,0.07010259,0.4400463],"study_design_scores_gemma":[0.004507472,0.0003631636,0.1698677,0.0001041672,0.00004320248,0.00005712345,0.0002884208,0.6040862,0.1274951,0.01133928,0.0802615,0.001586733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8798031,0.00001367876,0.09882671,0.01152476,0.0005416585,0.0002686664,0.000002820876,0.0004535467,0.008565058],"genre_scores_gemma":[0.9765197,8.840631e-7,0.01421954,0.005626611,0.000074486,0.000006905261,0.000002725246,0.000008775544,0.003540373],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6028735,"threshold_uncertainty_score":0.9535989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01007860506918046,"score_gpt":0.2347848522197949,"score_spread":0.2247062471506145,"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."}}