{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001643898,0.0006226621,0.000496853,0.004689138,0.0006253858,0.001238819,0.001059022,0.001207742,0.00173312],"category_scores_gemma":[0.0247712,0.0002534754,0.0004367052,0.001532883,0.0002859497,0.001181649,0.0006852291,0.001060241,0.0009816389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003589106,"about_ca_system_score_gemma":0.0009512057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004825873,"about_ca_topic_score_gemma":0.007856971,"domain_scores_codex":[0.997964,0.0003234923,0.0002081606,0.0004908502,0.0008201687,0.0001933602],"domain_scores_gemma":[0.9576629,0.02379234,0.007413517,0.002305509,0.006974291,0.00185153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002138922,0.0007142964,0.8409462,0.0003532986,0.0002672246,0.001317933,0.0005153657,0.01021805,0.0178003,0.0007240933,0.007562227,0.1174421],"study_design_scores_gemma":[0.0001053536,0.0006823094,0.5439807,0.0001052074,0.0003282363,0.001797747,0.0005054016,0.4222466,0.024708,0.00156569,0.003850363,0.0001244174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911809,0.0002302666,0.004805504,0.00007143606,0.00006948076,0.0000288652,0.001651606,0.001240678,0.0007212933],"genre_scores_gemma":[0.9900726,0.00006509769,0.005627234,0.00002876075,0.00005563498,0.00001360335,0.003254035,0.000114926,0.0007681609],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004825873,"threshold_uncertainty_score":0.009595513,"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."}}