{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001651895,0.00003335527,0.00004487362,0.00006298884,0.001476893,0.00005853013,0.1904048,0.00000510056,0.000007342245],"category_scores_gemma":[0.009991313,0.00002695573,0.00001503892,0.001027464,0.0002463659,0.000512274,0.2709393,0.0002018225,0.000006374524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003318257,"about_ca_system_score_gemma":0.0001758603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005386673,"about_ca_topic_score_gemma":0.000004773993,"domain_scores_codex":[0.9990855,0.0002188122,0.0001423443,0.0001822287,0.0002880346,0.00008308883],"domain_scores_gemma":[0.9029406,0.0002183017,0.0001695502,0.09660567,0.00004881553,0.00001702922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001685919,0.0003166092,0.01289908,0.00001537485,0.00001516456,1.883382e-7,0.001740868,0.0009088492,0.0168263,0.803418,0.02387996,0.1399779],"study_design_scores_gemma":[0.0001296094,0.00002006088,0.09832636,0.00001317224,0.000008334517,0.00002479651,0.0002040271,0.7721984,0.0004258066,0.03747001,0.09105801,0.0001214092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06179291,0.002366374,0.03367817,0.8496032,0.001154758,0.0007653855,0.0001818664,0.0008220273,0.04963525],"genre_scores_gemma":[0.71895,0.00001226606,0.2808343,0.0001220452,0.000003261902,0.00001028138,0.00002071749,0.000001854493,0.00004529119],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.8494812,"threshold_uncertainty_score":0.999823,"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."}}