{"id":"W3033974021","doi":"10.1145/3342529","title":"Learn-OCaml Extensions and Repository for Article Teaching the Art of Functional Programming using Automated Grading (Experience Report)","year":2019,"lang":"en","type":"dataset","venue":"Artifact Digital Object Group","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Grading (engineering); Computer science; Programming language; Functional programming; Software engineering; Mathematics education; Engineering; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.0003588225,0.0001955311,0.0002331021,0.0001131337,0.0004553209,0.000362535,0.0003961975,0.0001258295,0.000002002349],"category_scores_gemma":[0.000312231,0.0001503946,0.00009923499,0.0001812988,0.000169811,0.0008380646,0.0002866854,0.00032738,0.00000752456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006247743,"about_ca_system_score_gemma":0.0001523541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002205135,"about_ca_topic_score_gemma":0.000002971529,"domain_scores_codex":[0.9984452,0.00004370777,0.0004499752,0.0004968069,0.0002868932,0.0002774732],"domain_scores_gemma":[0.9982976,0.0004558497,0.0004072037,0.00069626,0.00008784174,0.00005525041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006632583,0.001886645,0.008200403,0.0003822421,0.0005026328,0.0002160976,0.001404443,0.0008579766,0.01109032,0.01087546,0.9423799,0.02213753],"study_design_scores_gemma":[0.000784742,0.0009766534,0.01336712,0.0007889164,0.0001929949,0.00430767,0.001812588,0.1030945,0.003222509,0.00378569,0.8662359,0.001430758],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7002349,0.0005214135,0.1825428,0.002131838,0.006104239,0.004056654,0.1023769,0.001634982,0.0003961882],"genre_scores_gemma":[0.916093,0.000003695114,0.009000978,0.0001073252,0.0001194932,0.0001232258,0.07431685,0.00001888942,0.0002165581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.215858,"threshold_uncertainty_score":0.6132912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02939641665517751,"score_gpt":0.3139160516332025,"score_spread":0.284519634978025,"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."}}