{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001478522,0.0002064016,0.0001891016,0.0002359791,0.0001409148,0.001499544,0.004123436,0.00003490847,0.000301944],"category_scores_gemma":[0.004878343,0.0001582891,0.00003395256,0.0006251676,0.00007242544,0.001165894,0.0008947399,0.0002354,0.0002038643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004746843,"about_ca_system_score_gemma":0.0001444748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002046494,"about_ca_topic_score_gemma":0.000008866911,"domain_scores_codex":[0.9957601,0.00002114873,0.0004752185,0.001430539,0.002002851,0.0003101085],"domain_scores_gemma":[0.9975027,0.000217264,0.0002177854,0.001416388,0.0004221711,0.00022365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003995187,0.0008530809,0.006477227,0.0001263769,0.0001566061,0.00038432,0.003050552,0.1364999,0.007243911,0.1075042,0.01869851,0.7186058],"study_design_scores_gemma":[0.0004027166,0.0001786808,0.007595021,0.00008668999,0.000007336163,0.000008929626,0.0002779154,0.9707122,0.0003318849,0.0002300107,0.01982187,0.0003467686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1045342,0.0000187798,0.8880583,0.001700171,0.002030733,0.0003787965,0.0002810774,0.0005100518,0.002487925],"genre_scores_gemma":[0.9703881,0.00000102269,0.02866411,0.0002532763,0.0001934398,0.00001057761,0.0001134726,0.00001724156,0.0003588297],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8658538,"threshold_uncertainty_score":0.999537,"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."}}