{"id":"W6959096943","doi":"10.7287/peerj.preprints.1260v2","title":"Comments on \"Researcher bias: The use of machine learning in software defect prediction\"","year":2016,"lang":"en","type":"article","venue":"","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; McGill University","funders":"","keywords":"Metric (unit); Reuse; Construct (python library); Group (periodic table); Software; Selection (genetic algorithm); Association (psychology); Predictive modelling","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":[0.04238548,0.001984483,0.001444664,0.002226459,0.005496915,0.005681022,0.006880662,0.0338748,0.006597287],"category_scores_gemma":[0.2191753,0.00124746,0.002180828,0.002854776,0.007375646,0.007089115,0.004167067,0.0373008,0.005775623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005255255,"about_ca_system_score_gemma":0.008082938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01681167,"about_ca_topic_score_gemma":0.01313122,"domain_scores_codex":[0.9651784,0.01409695,0.003983674,0.003735088,0.01154272,0.001463122],"domain_scores_gemma":[0.7222981,0.1919492,0.01286623,0.00693124,0.05961545,0.006339885],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004295031,0.00001745474,0.0007945047,0.0001073763,0.00002028221,0.0002747602,0.0006880795,0.0001504563,0.0001702036,0.001625998,0.9915624,0.004545495],"study_design_scores_gemma":[0.0001027833,0.0001324715,0.00378427,0.001286756,0.00008398475,0.001141596,0.004667115,0.001411007,0.001383491,0.007768147,0.9779443,0.0002939626],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0005634803,0.0008138471,0.0006333809,0.9774277,0.01958641,0.00002111462,0.0001659236,0.00009337403,0.0006948392],"genre_scores_gemma":[0.0051375,0.0008905774,0.000831496,0.9700033,0.02082093,0.0000753766,0.00006552362,0.00009747585,0.002077801],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.9576145,"threshold_uncertainty_score":0.2241585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0737485079944002,"score_gpt":0.273899385897897,"score_spread":0.2001508779034968,"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."}}