{"id":"W2955851367","doi":"10.1109/msr.2019.00074","title":"Can Issues Reported at Stack Overflow Questions be Reproduced? An Exploratory Study","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Code (set theory); Code review; Compiler; Exploratory research; Programming language; Stack (abstract data type); Source code; Sample (material); Software; Data science; Software development; Static program analysis","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":[],"consensus_categories":[],"category_scores_codex":[0.0009347728,0.0001538924,0.0001796356,0.0001583496,0.00009999923,0.0001636648,0.0008035928,0.00004610522,0.0001918192],"category_scores_gemma":[0.0006796065,0.0001423969,0.00003300672,0.0005509805,0.00002152493,0.0006398553,0.0005778136,0.0001784764,0.0002194769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001731375,"about_ca_system_score_gemma":0.0001398568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004030552,"about_ca_topic_score_gemma":0.0005348748,"domain_scores_codex":[0.997704,0.0001234717,0.0002609258,0.0009029707,0.0006545426,0.0003540883],"domain_scores_gemma":[0.9962797,0.0001656213,0.0000493258,0.003097263,0.000216006,0.0001920664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001981531,0.001260041,0.9385051,0.00004465017,0.0001545375,0.000414389,0.0200824,0.002780784,0.009297002,0.003466612,0.02087867,0.003095972],"study_design_scores_gemma":[0.001819866,0.003135866,0.9070947,0.00006379995,0.00002663343,0.0001208469,0.002856147,0.0308914,0.02812009,0.0007200078,0.02340931,0.001741351],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99304,0.00006254046,0.003281537,0.001011801,0.0005337743,0.0005535912,0.000001982964,0.001222085,0.0002927062],"genre_scores_gemma":[0.9827,0.00000518863,0.006168151,0.00008493235,0.00007678122,0.00004889921,0.000005203108,0.00002339167,0.01088742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03141044,"threshold_uncertainty_score":0.5806776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05047758650881961,"score_gpt":0.3264721570450574,"score_spread":0.2759945705362378,"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."}}