{"id":"W3171228652","doi":"10.18162/ritpu-2021-v18n2-03","title":"Challenges, Multiple Attempts, and Trump Cards: A Practice Report of Student’s Exposure to an Automated Correction System for a Programming Challenges Activity","year":2021,"lang":"en","type":"article","venue":"Revue internationale des technologies en pédagogie universitaire","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Medical education; Programming language; Mathematics education; Psychology; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006248559,0.0001824639,0.0002815529,0.0002809627,0.0002152303,0.0001076782,0.0006771485,0.0001883037,1.89984e-7],"category_scores_gemma":[0.002000689,0.0002044914,0.0000851628,0.0002725678,0.00007043852,0.0008669982,0.0005478185,0.000247272,8.015435e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004080077,"about_ca_system_score_gemma":0.00009649717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006557065,"about_ca_topic_score_gemma":0.0002725942,"domain_scores_codex":[0.998388,0.0001793257,0.0002413072,0.0006834541,0.0002571079,0.0002508407],"domain_scores_gemma":[0.997838,0.0006436154,0.0003091153,0.0006013145,0.0005526522,0.00005525583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003017614,0.0001985738,0.001381192,0.0003195217,0.0001595641,0.0004061871,0.007643533,0.0004153393,0.0002655447,0.002151289,0.0000177358,0.9870113],"study_design_scores_gemma":[0.002528454,0.003910664,0.04125474,0.003445736,0.0002565648,0.008410889,0.5421701,0.03833519,0.006398503,0.00007594305,0.351821,0.001392249],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8323199,0.005933646,0.1413775,0.01094709,0.0008975425,0.0009453938,0.00001048255,0.007219314,0.0003491035],"genre_scores_gemma":[0.8803819,0.0005319733,0.1184757,0.000003361341,0.00002704606,0.00004939964,0.000009044369,0.00001557711,0.0005059525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9856191,"threshold_uncertainty_score":0.8338919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05945509478269099,"score_gpt":0.32610471147996,"score_spread":0.266649616697269,"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."}}