{"id":"W6910432838","doi":"10.48448/e783-r608","title":"CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Course","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Question answering; Snippet; Construct (python library); Code (set theory); Annotation; Benchmark (surveying); Source code; Class (philosophy)","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"],"consensus_categories":[],"category_scores_codex":[0.006134699,0.0005286395,0.0005327528,0.001957752,0.0005687778,0.0003920938,0.00160569,0.0001824284,0.0006855477],"category_scores_gemma":[0.001107934,0.0005825584,0.00005559832,0.002307516,0.00125838,0.000621607,0.0003293671,0.0006818633,0.00007338154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001458776,"about_ca_system_score_gemma":0.002278309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008382572,"about_ca_topic_score_gemma":0.01563679,"domain_scores_codex":[0.9948161,0.0002512771,0.0006036354,0.001850511,0.00132604,0.001152389],"domain_scores_gemma":[0.9973854,0.00015126,0.0006609329,0.001351308,0.0001739031,0.0002772401],"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":[0.0004659024,0.00512231,0.0258449,0.001483904,0.0001153688,0.0002458929,0.000814866,0.02805935,0.02440163,0.003711487,0.667236,0.2424984],"study_design_scores_gemma":[0.001443947,0.0004447053,0.0003781519,0.0003726744,0.00009728189,0.0000133564,0.0006328775,0.148596,0.0001416625,0.0000573673,0.8467286,0.001093386],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.04616123,0.01045599,0.2244482,0.00705426,0.03300219,0.08111399,0.5215133,0.028209,0.04804185],"genre_scores_gemma":[0.1041434,0.00001448812,0.6733295,0.001063357,0.005599566,0.003508725,0.1914966,0.006219253,0.01462511],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4488813,"threshold_uncertainty_score":0.9996626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04229468153165272,"score_gpt":0.371406589637136,"score_spread":0.3291119081054833,"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."}}