{"id":"W2180526599","doi":"10.1109/pacrim.2015.7334812","title":"Sociolinguistics and programming","year":2015,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"University of Lethbridge","keywords":"Computer science; C4.5 algorithm; Naive Bayes classifier; Decision tree; Artificial intelligence; Natural language processing; Machine learning; Coding (social sciences); Random forest; Implementation; Programming language; Support vector machine","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":[0.0003194897,0.00003290883,0.00003725232,0.0000150285,0.00004144872,0.00007455892,0.0001146943,0.00002374169,0.000001847044],"category_scores_gemma":[0.0001558613,0.00002737977,0.000007375513,0.00007148217,0.00001821619,0.00006506089,0.00009191388,0.00004545947,0.00002635083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009159737,"about_ca_system_score_gemma":0.00003436972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005160531,"about_ca_topic_score_gemma":7.572467e-7,"domain_scores_codex":[0.9996555,0.00001786556,0.00005602304,0.00009526868,0.00007700881,0.0000982672],"domain_scores_gemma":[0.9997069,0.00002178593,0.00001445192,0.00009053009,0.00006324534,0.0001030565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[5.615191e-7,0.000005618375,0.002115507,0.000002471353,0.000001717201,0.000003664829,0.0009397372,0.000002007372,0.000006051212,0.932451,0.0004861703,0.06398547],"study_design_scores_gemma":[0.0009907783,0.0002111216,0.001811851,0.00001828548,0.000009227197,0.00008040005,0.0009268909,0.2310542,0.002556229,0.2249821,0.5367512,0.0006076724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002865398,0.0001071811,0.9878759,0.00078967,0.0001913956,0.00003658491,1.131037e-7,0.0001793935,0.007954313],"genre_scores_gemma":[0.7507288,0.000001323777,0.2486241,0.0002157002,0.00004566686,0.000001336836,4.660423e-7,0.000001355658,0.0003812676],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7478634,"threshold_uncertainty_score":0.1116515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08692363511330098,"score_gpt":0.3121883468085785,"score_spread":0.2252647116952775,"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."}}