{"id":"W4392564669","doi":"10.1145/3626252.3630909","title":"Prompt Problems: A New Programming Exercise for the Generative AI Era","year":2024,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Ulla Tuomisen Säätiö","keywords":"Generative grammar; Computer science; Artificial intelligence; Programming language","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":[0.002789247,0.001385886,0.0006188939,0.0008944247,0.0006715239,0.00215775,0.002347502,0.002110152,0.01047455],"category_scores_gemma":[0.01854977,0.0005610778,0.0006592869,0.0005574772,0.00179066,0.005155674,0.003865862,0.003389413,0.00262937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005601547,"about_ca_system_score_gemma":0.00120076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003260324,"about_ca_topic_score_gemma":0.0008085904,"domain_scores_codex":[0.9976208,0.001155858,0.0001238366,0.0004280146,0.0005618479,0.0001097118],"domain_scores_gemma":[0.9880044,0.009108056,0.0004050411,0.001312287,0.0004719964,0.0006983059],"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":[0.001040233,0.00196876,0.004777477,0.001372631,0.00004488589,0.001347886,0.01057565,0.01354827,0.05622508,0.04723031,0.07396439,0.7879043],"study_design_scores_gemma":[0.0006692949,0.002744344,0.006150197,0.0008860528,0.0000808062,0.005791714,0.002528793,0.1190573,0.05246146,0.1317798,0.6775432,0.000307058],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05322806,0.0002872028,0.8914012,0.002598637,0.000379562,0.000640824,0.0006173498,0.0339151,0.01693198],"genre_scores_gemma":[0.0953778,0.00026361,0.8883348,0.0008269949,0.00008752397,0.0007018752,0.0008805326,0.003010336,0.01051666],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01047455,"threshold_uncertainty_score":0.03504092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02639252194379686,"score_gpt":0.2911855269503672,"score_spread":0.2647930050065703,"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."}}