{"id":"W3112714882","doi":"","title":"ProvBuild: Improving Data Scientist Efficiency with Provenance (An Extended Abstract)","year":2020,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Debugging; Computer science; Scripting language; Workflow; Programming language; Programmer; Algorithmic program debugging; Process (computing); Overhead (engineering); Software engineering; Database","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01316958,0.001164572,0.000691415,0.001673561,0.001691477,0.005117211,0.003636572,0.001250631,0.008082254],"category_scores_gemma":[0.05775872,0.001284661,0.001204318,0.001791792,0.002625035,0.008769508,0.007330919,0.003406562,0.002678639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001162165,"about_ca_system_score_gemma":0.003678687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003455582,"about_ca_topic_score_gemma":0.004610183,"domain_scores_codex":[0.9916481,0.003024159,0.000634948,0.001438229,0.002921334,0.0003332999],"domain_scores_gemma":[0.9602661,0.01825723,0.001738213,0.0144929,0.004090974,0.001154513],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002886395,0.001602,0.03301482,0.00240906,0.0003168096,0.002085298,0.0107056,0.05163941,0.05674633,0.07494349,0.1890226,0.5746283],"study_design_scores_gemma":[0.001082317,0.0006830155,0.008349814,0.0005921608,0.0002523737,0.001381926,0.0009577031,0.410218,0.1757117,0.1253491,0.2748581,0.000563734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03583053,0.0005671728,0.7578239,0.002515322,0.0004984307,0.0007214422,0.004091222,0.1900862,0.007865807],"genre_scores_gemma":[0.2168362,0.0004741312,0.7448817,0.0008114925,0.0001689119,0.00048077,0.008116195,0.02427814,0.003952435],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9868304,"threshold_uncertainty_score":0.06964827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1812090060713548,"score_gpt":0.3712430813406168,"score_spread":0.1900340752692621,"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."}}