{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008041804,0.0003437886,0.0003267125,0.0007324682,0.0009627659,0.001341724,0.001737983,0.0001153558,0.000001839954],"category_scores_gemma":[0.0002139456,0.0003241778,0.00007435186,0.002795941,0.0008720757,0.001562641,0.0006404851,0.0008533919,0.000009010889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003498784,"about_ca_system_score_gemma":0.000404637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003904003,"about_ca_topic_score_gemma":0.000001338035,"domain_scores_codex":[0.9948322,0.00009811714,0.0004073556,0.001559595,0.0006791319,0.002423558],"domain_scores_gemma":[0.9985557,0.0005113748,0.0001268466,0.0003154145,0.0001953175,0.0002953233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002380989,0.00005060324,0.0001481197,0.00001932514,0.000006834191,0.000001748939,0.001180911,0.0007844564,0.000301008,0.7320691,0.00003624827,0.2653778],"study_design_scores_gemma":[0.0005911716,0.001833149,0.0008701507,0.0000561975,0.000006987411,0.0001022849,0.00003657076,0.8799144,0.0004330219,0.11397,0.001772537,0.0004135141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08313739,0.00007198716,0.9140998,0.0006502991,0.0002905036,0.0006899331,1.472806e-7,0.001036314,0.00002364071],"genre_scores_gemma":[0.7198076,0.000009692283,0.2796615,0.0001516435,0.0002127961,0.0001237718,0.000001913694,0.00002341855,0.000007698265],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8791299,"threshold_uncertainty_score":0.999921,"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."}}