{"id":"W4400722606","doi":"10.1016/j.jss.2024.112158","title":"Reproducibility of issues reported in stack overflow questions: Challenges, impact & estimation","year":2024,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Reproducibility; Stack (abstract data type); Estimation; Computer science; Reliability engineering; Statistics; Mathematics; Engineering; Systems engineering; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3234411,0.001116396,0.002085308,0.006721245,0.003973068,0.009095921,0.005897048,0.006278548,0.005371404],"category_scores_gemma":[0.8083922,0.001438905,0.002362347,0.006514646,0.007718815,0.01044896,0.008469528,0.005666954,0.002502017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003548703,"about_ca_system_score_gemma":0.006374772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006092527,"about_ca_topic_score_gemma":0.004520518,"domain_scores_codex":[0.5087479,0.3023932,0.05098995,0.043243,0.08862689,0.005999072],"domain_scores_gemma":[0.07564873,0.6695179,0.05785773,0.1190176,0.07526114,0.002696933],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001561321,0.0009662018,0.6861367,0.003351312,0.002476184,0.0008566117,0.02143258,0.006830553,0.004631013,0.04390793,0.03536463,0.192485],"study_design_scores_gemma":[0.0006106793,0.00121061,0.5228115,0.004003999,0.001838895,0.002508275,0.02109814,0.09464877,0.02438486,0.1982173,0.1279037,0.0007633353],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5065213,0.006270309,0.379524,0.03517579,0.00477387,0.00528819,0.01254043,0.00278615,0.04711994],"genre_scores_gemma":[0.9343953,0.0004489525,0.05230384,0.002884689,0.001401403,0.001871499,0.003653765,0.0005003267,0.002540379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.676559,"threshold_uncertainty_score":0.8343176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04380599402015875,"score_gpt":0.3244064420340398,"score_spread":0.2806004480138811,"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."}}