{"id":"W3135167302","doi":"10.1145/3408877.3439579","title":"Data Collection for the Learn-OCaml Programming Platform","year":2021,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Programming language; Correctness; Compiler; Context (archaeology); Code (set theory); Data type; Software engineering","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":[0.0008538046,0.00007944883,0.00007922301,0.0000278604,0.0006946037,0.0006213717,0.001023947,0.00003910736,0.00001008349],"category_scores_gemma":[0.0005221757,0.00005442023,0.00004464724,0.0003848337,0.00002131039,0.0004142573,0.0004804738,0.0002087142,0.00001363911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002194931,"about_ca_system_score_gemma":0.0001147543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007835568,"about_ca_topic_score_gemma":0.0001239241,"domain_scores_codex":[0.9990283,0.00003847374,0.0001278363,0.0003816052,0.0001636611,0.0002601581],"domain_scores_gemma":[0.9983459,0.0005300698,0.00004817034,0.0009685133,0.00006746523,0.00003989425],"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":[0.000002329555,0.00002706509,0.0001102543,0.000006601862,0.00001947498,0.000002278085,0.0005020151,0.00007125016,0.00001531074,0.01279164,0.004441775,0.98201],"study_design_scores_gemma":[0.0001634982,0.00004306397,0.0001760009,0.00000981947,0.000008569651,0.00003403452,0.0003440055,0.14171,0.0001107457,0.0001193748,0.8571967,0.0000841138],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000292866,0.0002796564,0.9939644,0.003839774,0.0004711666,0.0001968507,8.335953e-7,0.0003995096,0.0005549334],"genre_scores_gemma":[0.09586171,0.00001399544,0.8904163,0.0003677658,0.0001947578,0.00006402226,0.00004614425,0.00001500635,0.01302029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9819259,"threshold_uncertainty_score":0.5991901,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0931146594574479,"score_gpt":0.3205356898603982,"score_spread":0.2274210304029503,"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."}}