{"id":"W4385761401","doi":"10.4204/eptcs.382.2","title":"Computer Aided Design and Grading for an Electronic Functional Programming Exam","year":2023,"lang":"en","type":"article","venue":"Electronic Proceedings in Theoretical Computer Science","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Grading (engineering); Computer science; Automation; Constructive; Programming language; Mathematical proof; Software engineering; Process (computing); Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006518508,0.0005749585,0.0003477366,0.001540947,0.0005823036,0.002807196,0.001358411,0.0009842335,0.0253733],"category_scores_gemma":[0.02906667,0.00040074,0.0005019291,0.0007424806,0.0004463762,0.0009750903,0.000907407,0.0008953926,0.005878906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008808358,"about_ca_system_score_gemma":0.00141953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001022262,"about_ca_topic_score_gemma":0.001431126,"domain_scores_codex":[0.9951862,0.001545221,0.0004728905,0.0005493107,0.002015455,0.0002309172],"domain_scores_gemma":[0.9799121,0.006828022,0.0009390863,0.00326223,0.008478964,0.0005795488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005284574,0.0005123162,0.00497786,0.0002870297,0.00002577578,0.0004897115,0.000770045,0.01826751,0.04445618,0.01699422,0.02152162,0.8911693],"study_design_scores_gemma":[0.0007013816,0.003604398,0.02982716,0.0003987223,0.0001273987,0.002269045,0.001074362,0.4064998,0.1775405,0.02098023,0.35664,0.0003370633],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07007376,0.0001617491,0.8923865,0.0006426646,0.0004485897,0.001651018,0.0004652684,0.009338814,0.02483166],"genre_scores_gemma":[0.2705726,0.0001052521,0.7070286,0.0001704336,0.00007541769,0.0007347569,0.0008556472,0.0009607836,0.01949655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0253733,"threshold_uncertainty_score":0.0848822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02026439381970135,"score_gpt":0.2680378493480965,"score_spread":0.2477734555283952,"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."}}