{"id":"W4213251046","doi":"10.1145/3495256","title":"Automating data science","year":2022,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automation; Computer science; Data science; Process (computing); 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":[0.0183979,0.001375184,0.001417145,0.00418617,0.002129245,0.009467416,0.002890837,0.002202283,0.008517413],"category_scores_gemma":[0.06693328,0.0009639715,0.001573446,0.004352965,0.003911599,0.008950635,0.009235241,0.005257155,0.007256963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002108906,"about_ca_system_score_gemma":0.00905579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004771679,"about_ca_topic_score_gemma":0.00499671,"domain_scores_codex":[0.9775919,0.009127556,0.001502252,0.003188531,0.007411163,0.001178497],"domain_scores_gemma":[0.9057258,0.03748675,0.003057593,0.04178948,0.01032861,0.001611728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003515193,0.0004171872,0.006933731,0.001390352,0.000176127,0.0002732228,0.002058655,0.02061725,0.01620689,0.148311,0.03736528,0.7658988],"study_design_scores_gemma":[0.0001022923,0.0001367869,0.003110881,0.0004467237,0.00008176321,0.0004250212,0.0007965166,0.1051487,0.01928672,0.555741,0.314593,0.0001306749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02321894,0.002371906,0.9233021,0.01091932,0.0006228132,0.0005282658,0.0007210663,0.009739377,0.02857615],"genre_scores_gemma":[0.177296,0.003095433,0.804827,0.002662487,0.0006454652,0.0004314471,0.002626386,0.001056304,0.007359541],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0183979,"threshold_uncertainty_score":0.09729862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1379017813942821,"score_gpt":0.36646717004846,"score_spread":0.2285653886541779,"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."}}