{"id":"W4309896433","doi":"10.1007/s10664-022-10242-2","title":"Automatic prediction of rejected edits in Stack Overflow","year":2022,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Global Institute for Water Security, University of Saskatchewan","keywords":"Computer science; Quality (philosophy); World Wide Web; Information retrieval; Software; Precision and recall; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0005308778,0.0001708403,0.0002583559,0.0004828691,0.00006468678,0.00003291663,0.0008038834,0.00006208589,0.0001059807],"category_scores_gemma":[0.002535901,0.0001959205,0.00007279623,0.001980188,0.00001466988,0.0002801796,0.0006408123,0.0005727971,0.000008423865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004028335,"about_ca_system_score_gemma":0.0001135243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002095574,"about_ca_topic_score_gemma":7.276503e-7,"domain_scores_codex":[0.9978791,0.00006855006,0.0004067474,0.0003801479,0.0008138999,0.000451486],"domain_scores_gemma":[0.9980262,0.001200067,0.00005289932,0.0005474543,0.00005394492,0.0001194348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007500546,0.0002067422,0.5424304,0.0002159133,0.00003644719,0.00009473741,0.001118509,0.4466149,0.0006540384,0.0001192285,0.003880177,0.004621421],"study_design_scores_gemma":[0.0003774985,0.0001416057,0.5606921,0.00004001678,0.000002393824,0.00002206347,0.00000815824,0.4359402,0.0003762241,0.00004788888,0.002180462,0.000171417],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6489607,0.0001512316,0.3486711,0.00009534373,0.0008044802,0.0001954544,0.00001850692,0.001096228,0.000006903554],"genre_scores_gemma":[0.9647613,0.000002940575,0.03493489,0.00002906788,0.00007862505,0.000115728,0.00001088127,0.00003210907,0.00003445067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3158006,"threshold_uncertainty_score":0.7989405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0211596723309598,"score_gpt":0.2590476734414302,"score_spread":0.2378880011104704,"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."}}