{"id":"W2138601625","doi":"10.5430/air.v4n2p45","title":"Automated selection of a software effort estimation model based on accuracy and uncertainty","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Machine learning; Software; Selection (genetic algorithm); Estimation; Data mining; Process (computing); Model selection; Bayesian probability; Artificial intelligence; Software development; Engineering; Systems engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003179348,0.0001323071,0.0001667553,0.0006426874,0.000153705,0.0001897892,0.0006600253,0.0001049334,0.000007917416],"category_scores_gemma":[0.01008086,0.0001257202,0.00003506658,0.001752064,0.0001787909,0.0003973981,0.0002196938,0.0004163139,0.00006869051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000229935,"about_ca_system_score_gemma":0.000670718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002602435,"about_ca_topic_score_gemma":0.00002186541,"domain_scores_codex":[0.9971606,0.0001720295,0.00033389,0.0004528177,0.001363819,0.0005169031],"domain_scores_gemma":[0.9959023,0.002253043,0.00005268241,0.0004912304,0.00104501,0.0002557576],"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":[0.0000605655,0.0001024538,0.0007451967,0.00003672669,0.000005474538,0.000004000083,0.0004046362,0.8762951,0.0006440276,0.007682489,0.0002695028,0.1137498],"study_design_scores_gemma":[0.00004065749,0.0003485724,0.0003101445,0.00005254132,0.000001275322,0.000002839429,0.00004146825,0.9506994,0.03227253,0.01611055,0.00001187422,0.0001081512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1402777,0.00001834614,0.8583958,0.0003521948,0.00006651918,0.0003370029,0.000002414741,0.0004986926,0.00005134472],"genre_scores_gemma":[0.9236242,0.000004578777,0.07624211,0.00001627355,0.00002284746,0.00005170822,0.000004275943,0.00001411474,0.00001990759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7833465,"threshold_uncertainty_score":0.9982576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1494272806277806,"score_gpt":0.4149915128714236,"score_spread":0.265564232243643,"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."}}