{"id":"W2954476116","doi":"10.1109/msr.2019.00046","title":"Can Duplicate Questions on Stack Overflow Benefit the Software Development Community?","year":2019,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Heuristics; Reputation; Information retrieval; Similarity (geometry); Stack (abstract data type); World Wide Web; Data science; Data mining; Artificial intelligence; 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":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004868295,0.0001269339,0.00009873571,0.00008700188,0.0003092189,0.0001708267,0.00169902,0.00004248518,0.00006920963],"category_scores_gemma":[0.000245518,0.00008775114,0.00003159564,0.0003665403,0.00002529427,0.0001257056,0.000583332,0.000482433,0.0008986056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001555988,"about_ca_system_score_gemma":0.0001326063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003207504,"about_ca_topic_score_gemma":0.0001562352,"domain_scores_codex":[0.9988503,0.00006250916,0.0001376162,0.0002109916,0.0004090674,0.000329472],"domain_scores_gemma":[0.9969913,0.00132991,0.00002278493,0.001465752,0.00009450335,0.0000957236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002642587,0.0008502769,0.2243208,0.0001939433,0.0002585634,0.00002156014,0.01413721,0.06157652,0.0006856332,0.3450151,0.01696683,0.3359472],"study_design_scores_gemma":[0.0005659983,0.0002755646,0.9261019,0.0001362752,0.000003615388,0.00001791923,0.0001070575,0.0122258,0.004904829,0.003758187,0.05124234,0.0006605064],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7598544,0.00004497218,0.2323381,0.004197408,0.0004090442,0.0005382888,0.000004937352,0.001179653,0.001433207],"genre_scores_gemma":[0.9606952,0.000004702626,0.03390666,0.0005672958,0.00001709417,0.00004968309,0.000004965073,0.00001576103,0.004738657],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7017812,"threshold_uncertainty_score":0.9998793,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02334161124921441,"score_gpt":0.2581692911669891,"score_spread":0.2348276799177747,"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."}}