{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06842841,0.0007117633,0.000660761,0.004729498,0.001413082,0.00270133,0.001621068,0.001833869,0.001435481],"category_scores_gemma":[0.3810375,0.0007446841,0.0008394427,0.002634826,0.002752535,0.003689071,0.003408573,0.001678098,0.0004729274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00114265,"about_ca_system_score_gemma":0.001053675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005697582,"about_ca_topic_score_gemma":0.0007755916,"domain_scores_codex":[0.9234185,0.05273058,0.007113254,0.004613916,0.01032794,0.001795843],"domain_scores_gemma":[0.3853987,0.5133287,0.05825957,0.01845705,0.02267666,0.001879165],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006714481,0.001397876,0.5446426,0.00112472,0.000288341,0.002238647,0.3986792,0.000458125,0.005941588,0.0009595412,0.001314311,0.04228367],"study_design_scores_gemma":[0.0001194099,0.005244932,0.6708032,0.001264449,0.000309903,0.004808476,0.2774076,0.004337868,0.01319311,0.002021151,0.02019818,0.0002915846],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958724,0.0001210757,0.002617617,0.0001839425,0.000009302289,0.0003016899,0.0001437354,0.00003338166,0.0007168461],"genre_scores_gemma":[0.9954829,0.0001334495,0.002940288,0.0001777787,0.00002771166,0.0006127564,0.0002420293,0.00004435064,0.0003386848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9315716,"threshold_uncertainty_score":0.3618883,"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."}}