{"id":"W2964516878","doi":"10.1145/3341719","title":"Teaching the art of functional programming using automated grading (experience report)","year":2019,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Correctness; Computer science; Functional programming; Grading (engineering); Programming language; Computer programming; Code (set theory); Multimedia; Software engineering; Mathematics education; Psychology","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":[0.002277232,0.0003200107,0.000385569,0.0001953873,0.0005693387,0.0003801264,0.003417533,0.000114819,0.000005364097],"category_scores_gemma":[0.002472705,0.0002002505,0.0002759713,0.0008150418,0.0002150261,0.0005785871,0.001329445,0.0008323529,0.000007146039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008213564,"about_ca_system_score_gemma":0.00006645935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001932268,"about_ca_topic_score_gemma":0.000001399307,"domain_scores_codex":[0.9970422,0.00007809509,0.0006707799,0.0006542819,0.0009574561,0.0005972108],"domain_scores_gemma":[0.9970503,0.0003140484,0.001110294,0.001202333,0.0002445303,0.00007842034],"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":[0.000100871,0.0007658122,0.1613122,0.0009526706,0.0003616467,0.00002812302,0.05041437,0.001538463,0.07726771,0.04627415,0.001234754,0.6597492],"study_design_scores_gemma":[0.006101843,0.003924399,0.07892855,0.01210156,0.0007912734,0.006512546,0.07935281,0.1733817,0.1449494,0.004185749,0.4834813,0.006288867],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928586,0.0002123975,0.00242441,0.001613827,0.0005401711,0.0008038384,6.823331e-7,0.001045458,0.0005005571],"genre_scores_gemma":[0.8557154,9.749872e-7,0.1434503,0.00007450095,0.00008995915,0.00004088816,0.000001724151,0.00003315218,0.000593023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6534603,"threshold_uncertainty_score":0.8165981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02009138487233451,"score_gpt":0.2914121183470974,"score_spread":0.2713207334747629,"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."}}