{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001599254,0.001820615,0.0009649534,0.001922527,0.0005157875,0.001833024,0.003141153,0.001041609,0.0668027],"category_scores_gemma":[0.007503085,0.0009028543,0.001206852,0.001377445,0.0003016568,0.002790895,0.002815641,0.002229743,0.02024213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007704848,"about_ca_system_score_gemma":0.0008901305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002563311,"about_ca_topic_score_gemma":0.005391702,"domain_scores_codex":[0.9994144,0.0001107999,0.0000451234,0.0001507284,0.0002238617,0.00005506608],"domain_scores_gemma":[0.9963368,0.002277921,0.0001126849,0.0005749597,0.000344799,0.0003528323],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00090302,0.0001587189,0.001390629,0.0006903138,0.0001054756,0.0004188354,0.0002698396,0.003684172,0.005685416,0.002978343,0.8830213,0.100694],"study_design_scores_gemma":[0.001104205,0.0001777682,0.005501332,0.0002469418,0.00005962716,0.0005820106,0.0001932193,0.06447227,0.02134309,0.01645757,0.8896072,0.0002547988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.01119001,0.0006883385,0.1942804,0.001098433,0.0004720196,0.0006872988,0.1942934,0.576269,0.021021],"genre_scores_gemma":[0.07392999,0.0008574973,0.4054143,0.002146085,0.000273344,0.003649572,0.360046,0.125424,0.02825929],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.0668027,"threshold_uncertainty_score":0.2234773,"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."}}