{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001506631,0.002015078,0.0006697563,0.003618282,0.001339067,0.001170989,0.002537846,0.002919819,0.01374986],"category_scores_gemma":[0.009455886,0.0004058083,0.001108241,0.002867257,0.0005689657,0.00211394,0.002312388,0.00212847,0.0164075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001765706,"about_ca_system_score_gemma":0.00247457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02899324,"about_ca_topic_score_gemma":0.05852346,"domain_scores_codex":[0.9978278,0.0005318051,0.0002350944,0.0006543589,0.0005393269,0.0002116351],"domain_scores_gemma":[0.9956056,0.001640926,0.0002125966,0.0007240011,0.001285144,0.000531662],"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":[0.0006434689,0.001352066,0.01199906,0.001826539,0.00009182596,0.0004771514,0.00111573,0.00360724,0.005794228,0.002293316,0.8891121,0.08168726],"study_design_scores_gemma":[0.0005910889,0.0005967686,0.05461627,0.0003880373,0.00007891929,0.0007154533,0.002006538,0.04218777,0.01356653,0.005411377,0.8796515,0.0001897642],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.07975327,0.001375527,0.01129985,0.001738124,0.0004521664,0.001233989,0.8710671,0.01761202,0.01546795],"genre_scores_gemma":[0.02554106,0.0001446321,0.01305389,0.0003056954,0.00004753812,0.0007535077,0.9553384,0.0003164371,0.004498809],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02899324,"threshold_uncertainty_score":0.05764896,"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."}}