{"id":"W4411993048","doi":"10.1016/j.jss.2025.112541","title":"LLMs and Stack Overflow discussions: Reliability, impact, and challenges","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Stack (abstract data type); Reliability (semiconductor); Computer science; Reliability engineering; Political science; Computer security; Engineering; Operating system; Physics","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":[0.0005227289,0.00008114451,0.0002894043,0.0001071576,0.00009368142,0.00004004782,0.0000244604,0.00008703425,0.000005611768],"category_scores_gemma":[0.0005342877,0.00004755351,0.00003799635,0.00006080754,0.00005855832,0.0001260008,0.00002227498,0.0001667808,4.861648e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004992975,"about_ca_system_score_gemma":0.0001384034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002203267,"about_ca_topic_score_gemma":0.00001765206,"domain_scores_codex":[0.9992014,0.00004884749,0.0004064319,0.000108321,0.0001260739,0.0001089436],"domain_scores_gemma":[0.9991257,0.0002296428,0.0001367009,0.0001078313,0.0002332773,0.0001668121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003008077,0.0001531229,0.5905493,0.003815032,0.0001203771,0.00002899556,0.005614802,0.00001727079,0.0001000717,0.0005580473,0.003192485,0.3955497],"study_design_scores_gemma":[0.000654852,0.002798747,0.8819373,0.01023781,0.0003383973,0.001661955,0.04782848,0.0005557011,0.0001759374,0.009067843,0.04441714,0.0003258607],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9068592,0.08419451,0.0002239828,0.008006159,0.0004921837,0.0001372991,0.000003558732,0.000008194242,0.00007493688],"genre_scores_gemma":[0.9687757,0.03035166,0.0002184769,0.00007216636,0.0002205852,0.00000271436,6.733142e-7,0.000005148947,0.0003527985],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3952238,"threshold_uncertainty_score":0.1939176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1051350801235757,"score_gpt":0.406944567029956,"score_spread":0.3018094869063803,"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."}}