{"id":"W2806149066","doi":"10.1609/aaai.v32i1.11369","title":"Dataset Evolver: An Interactive Feature Engineering Notebook","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature engineering; Feature (linguistics); Computer science; Construct (python library); Artificial intelligence; Reinforcement learning; Science and engineering; Machine learning; Human–computer interaction; Software engineering; Engineering; Deep learning; Programming language","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":[0.0004019875,0.0001907571,0.0001680247,0.0001221535,0.0001855291,0.0003287895,0.002257829,0.00008081178,0.00006529215],"category_scores_gemma":[0.0004920113,0.0001440125,0.00004888028,0.0004183262,0.0001705465,0.0009603527,0.0003985036,0.0003935131,0.000189305],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000388774,"about_ca_system_score_gemma":0.00005857133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004763179,"about_ca_topic_score_gemma":0.00001404605,"domain_scores_codex":[0.9985774,0.00001852646,0.0002787441,0.0005170006,0.000351412,0.0002569593],"domain_scores_gemma":[0.9985489,0.00006868922,0.000272571,0.000534762,0.000479875,0.00009524565],"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":[0.00008615603,0.0001238139,0.000178053,0.00002980313,0.00001897645,4.784997e-7,0.002107185,0.00003299753,0.09274387,0.7883474,0.003562625,0.1127687],"study_design_scores_gemma":[0.0000313302,0.0004540919,0.0007957151,0.0001888992,0.00001269694,0.000008989622,0.0002745637,0.5362067,0.4375041,0.01588965,0.00831449,0.0003187557],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2061723,0.00007100871,0.7130998,0.03289757,0.004669081,0.002196654,0.0006628459,0.001238867,0.03899186],"genre_scores_gemma":[0.9892685,0.000006596666,0.01008691,0.0002470355,0.0001733579,0.00001279506,0.00002412841,0.00001072948,0.000169932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7830962,"threshold_uncertainty_score":0.5872658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05272340630652117,"score_gpt":0.3101749047573195,"score_spread":0.2574514984507983,"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."}}