{"id":"W2953003320","doi":"10.48550/arxiv.1812.10176","title":"A Variability-Aware Design Approach to the Data Analysis Modeling Process","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Software Engineering Methodologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Flexibility (engineering); Automation; Process (computing); Data science; Software; Systems engineering; Software engineering; Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01387646,0.0009742921,0.0006641621,0.001849322,0.0009340998,0.003832229,0.00293805,0.001724647,0.001903982],"category_scores_gemma":[0.01930233,0.001120539,0.002563787,0.001304255,0.002641438,0.002794571,0.003457128,0.003947887,0.0005662239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001812755,"about_ca_system_score_gemma":0.004647533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00166936,"about_ca_topic_score_gemma":0.002213924,"domain_scores_codex":[0.9894782,0.004577934,0.0008013621,0.001544726,0.003191458,0.0004062479],"domain_scores_gemma":[0.9885232,0.005208668,0.001087729,0.002736503,0.002095496,0.0003484672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001838389,0.0001724523,0.003032883,0.0006498129,0.0002540756,0.0005119484,0.001982442,0.2297783,0.01900614,0.5931816,0.001677547,0.149569],"study_design_scores_gemma":[0.00006823556,0.0002427684,0.0005735441,0.0002070777,0.0001700473,0.0003549492,0.0002205963,0.73332,0.01226137,0.2185119,0.03400742,0.00006206653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00102153,0.00002724146,0.9982377,0.00009812816,0.00000645103,0.0000659323,0.00001681393,0.000100117,0.0004261072],"genre_scores_gemma":[0.04880824,0.00009524725,0.9499526,0.00008785698,0.00002179714,0.0003577588,0.00008575053,0.00007549206,0.0005152284],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01387646,"threshold_uncertainty_score":0.07338667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3436730915888954,"score_gpt":0.2658874829567656,"score_spread":0.07778560863212985,"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."}}