{"id":"W4389206342","doi":"10.22215/etd/2023-15821","title":"Evaluating the Effectiveness of Comparison Activities in a Programming Tutor","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"TUTOR; Computer science; Test (biology); Mathematics education; Significant difference; Artificial intelligence; Machine learning; Programming language; Psychology; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.00587923,0.0002030416,0.0004021908,0.0002442625,0.0001509096,0.0002133771,0.0008232352,0.0001388313,0.000001754177],"category_scores_gemma":[0.0007148701,0.0001467829,0.0001151299,0.000663618,0.00002925605,0.0001483899,0.00009494786,0.000724036,0.000006987978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006433501,"about_ca_system_score_gemma":0.0001601265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001124739,"about_ca_topic_score_gemma":0.0004804531,"domain_scores_codex":[0.997007,0.001410301,0.000380339,0.0004132589,0.0004789131,0.0003102081],"domain_scores_gemma":[0.9964527,0.002726521,0.00030723,0.0004326275,0.00005598936,0.00002490166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006116161,0.00007030742,0.00187087,0.0006482119,0.00003335801,0.000002202383,0.01374521,0.001313627,0.0003428672,0.004511221,0.000006031689,0.9773949],"study_design_scores_gemma":[0.004030075,0.004801929,0.5170643,0.02021147,0.0002991701,0.00001846627,0.08292948,0.3339463,0.0158375,0.003552275,0.01358126,0.003727785],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9744425,0.0003967638,0.0211345,0.00002814133,0.001372587,0.0009782836,4.323134e-7,0.0006488665,0.0009979609],"genre_scores_gemma":[0.9733024,0.000002243573,0.02454898,0.000002768623,0.00003418242,0.0002359686,0.00004365148,0.00002972914,0.001800101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9736671,"threshold_uncertainty_score":0.5985631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06193665027651755,"score_gpt":0.4068142584345004,"score_spread":0.3448776081579828,"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."}}