{"id":"W4404785115","doi":"10.1007/s40593-024-00441-x","title":"Predicting Tags for Learner Questions on Stack Overflow","year":2024,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence in Education","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Stack (abstract data type); Computer science; Educational technology; Multimedia; Mathematics education; Programming language; Mathematics","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":[0.0006481454,0.00008475266,0.00009249501,0.0005261169,0.00003723221,0.0003690652,0.0006612812,0.00004897604,0.00002249033],"category_scores_gemma":[0.0005395931,0.00007996924,0.00008928192,0.0002202913,0.00002091142,0.000775416,0.00003765426,0.0002449364,0.0000269562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002938385,"about_ca_system_score_gemma":0.0005620926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005327086,"about_ca_topic_score_gemma":0.00003295947,"domain_scores_codex":[0.9986435,0.00003857385,0.0005992655,0.000199762,0.0003909094,0.0001279685],"domain_scores_gemma":[0.9988256,0.0003318371,0.0001530267,0.0001366228,0.0005021578,0.00005081857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002102429,0.000166352,0.0003279181,0.000008080148,0.00001939595,0.00000688419,0.001688743,0.02085882,0.0004582201,0.3482383,0.0002398296,0.6279665],"study_design_scores_gemma":[0.00002474828,0.0001397767,0.0002724159,0.0005434689,0.000006177506,0.00005342214,0.0005728288,0.7487727,0.004384426,0.2401221,0.004996564,0.000111435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1124139,0.0002301451,0.8693304,0.00618627,0.0113707,0.0001151656,0.000002918927,0.00003089746,0.0003195626],"genre_scores_gemma":[0.9638649,0.00005705867,0.03422403,0.0002140885,0.001499462,0.00001383813,0.000002191368,0.000008348446,0.0001161142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.851451,"threshold_uncertainty_score":0.3558904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05232476163451524,"score_gpt":0.3840827449888329,"score_spread":0.3317579833543177,"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."}}