{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004460553,0.0007093408,0.0002516475,0.001080748,0.0007483211,0.002656672,0.001101738,0.0007622219,0.01513955],"category_scores_gemma":[0.01411466,0.0003609431,0.000454736,0.0007094131,0.0009178258,0.002700294,0.001829711,0.001826783,0.006564414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008212821,"about_ca_system_score_gemma":0.001351575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001485137,"about_ca_topic_score_gemma":0.00320556,"domain_scores_codex":[0.9972568,0.0008102626,0.0001745433,0.0004002837,0.001091693,0.0002664992],"domain_scores_gemma":[0.9909644,0.002608516,0.0006309373,0.001536791,0.002873489,0.001385839],"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":[0.0001316435,0.001466483,0.008907548,0.0001840439,0.00001824889,0.0003061751,0.005595677,0.002651316,0.01852786,0.008022125,0.0636636,0.8905252],"study_design_scores_gemma":[0.0002254162,0.003502355,0.04141881,0.0005336683,0.00008200703,0.005167755,0.005755637,0.02830553,0.121027,0.03441506,0.7592198,0.0003468535],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3137884,0.0007566948,0.5374075,0.004261536,0.0008678549,0.0008369483,0.001188347,0.0154553,0.1254374],"genre_scores_gemma":[0.5984907,0.000815012,0.3188888,0.0007365429,0.0002273503,0.0003426959,0.001269671,0.002136815,0.07709245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01513955,"threshold_uncertainty_score":0.05064684,"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."}}