{"id":"W2954574984","doi":"10.1109/msr.2019.00052","title":"What do Developers Know About Machine Learning: A Study of ML Discussions on StackOverflow","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Machine learning; Artificial intelligence; Topic model; Software; Focus (optics); Data science","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":[0.0003178231,0.0001490581,0.0001956778,0.0002099727,0.00006187263,0.0002203567,0.0008330421,0.00004084735,0.0001881662],"category_scores_gemma":[0.0002885513,0.00009635675,0.00004436155,0.000555519,0.0000157711,0.0005145111,0.0003674564,0.0002476937,0.0003141018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007372633,"about_ca_system_score_gemma":0.00007847427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007399016,"about_ca_topic_score_gemma":0.00003562289,"domain_scores_codex":[0.9984595,0.00009212668,0.0001851374,0.0004103018,0.0005536995,0.00029922],"domain_scores_gemma":[0.9984581,0.0005690085,0.00003674794,0.0007375946,0.00008513907,0.0001133921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000784147,0.002169787,0.5368278,0.00007535546,0.0002061757,0.00005896992,0.02235643,0.06033878,0.0008371559,0.006420866,0.0008603518,0.3697699],"study_design_scores_gemma":[0.004931308,0.007843189,0.7080221,0.0006225088,0.00001433085,0.00001254909,0.007141078,0.2254309,0.002573563,0.0001029104,0.04207428,0.001231306],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873143,0.0001805211,0.01036789,0.0002541188,0.0006137582,0.0004669486,7.369276e-7,0.0002817636,0.0005199823],"genre_scores_gemma":[0.9879397,0.0001158003,0.002296458,0.00002023167,0.00001557201,0.00001556138,0.000001101557,0.0000170554,0.009578511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3685386,"threshold_uncertainty_score":0.4037248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01397952711583728,"score_gpt":0.2750782205586064,"score_spread":0.2610986934427691,"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."}}