{"id":"W4297040452","doi":"10.48550/arxiv.1812.10176","title":"A Variability-Aware Design Approach to the Data Analysis Modeling\\n Process","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Software System Performance and Reliability","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); Software; Data science; Software engineering; Systems engineering; Data modeling; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00336882,0.0004273743,0.0006037977,0.0003714732,0.0004126671,0.0002818599,0.01105172,0.0003711532,0.0000112428],"category_scores_gemma":[0.0002009323,0.0003279676,0.0002717183,0.003313525,0.0001339797,0.0006423866,0.007193763,0.0006194639,0.0001020879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002112659,"about_ca_system_score_gemma":0.000605328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002601433,"about_ca_topic_score_gemma":0.00002781526,"domain_scores_codex":[0.9953668,0.0006314131,0.000390126,0.002852995,0.0002605674,0.0004980646],"domain_scores_gemma":[0.9899076,0.0002074318,0.0002426601,0.008821393,0.0005885234,0.0002323775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002516444,0.0001414193,0.003721484,0.0001542904,0.0004340876,0.000005828539,0.0007906687,0.9929451,1.157876e-7,0.001224117,0.0004041546,0.0001535935],"study_design_scores_gemma":[0.0001246148,0.00003199392,0.0002379491,0.00003784823,0.0005107726,0.000002103842,0.0001080459,0.9883522,0.000003430328,0.01007804,0.00009335379,0.0004196267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03182771,0.00001883728,0.9654823,0.0001348683,0.000450254,0.001027461,0.00005230973,0.0003636823,0.0006426027],"genre_scores_gemma":[0.9831778,0.00001870421,0.01624931,0.0001183529,0.0001719101,0.000009602586,0.00007790578,0.00001679724,0.0001596388],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9513501,"threshold_uncertainty_score":0.9999172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1753042015782082,"score_gpt":0.2296931253182083,"score_spread":0.05438892374000012,"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."}}