{"id":"W4403334275","doi":"10.1145/3654777.3676357","title":"CoLadder: Manipulating Code Generation via Multi-Level Blocks","year":2024,"lang":"en","type":"article","venue":"","topic":"E-Learning and Knowledge Management","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Code (set theory); Code generation; Programming language; Parallel computing; Operating system","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":[0.0002795762,0.00009977599,0.00007492876,0.00009389724,0.0001433734,0.0004518512,0.0003053569,0.0000365586,0.00008114978],"category_scores_gemma":[0.00001616911,0.00008733252,0.00004187534,0.0002544522,0.00001396861,0.000213615,0.0002453195,0.0001125149,0.000493572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003921304,"about_ca_system_score_gemma":0.000021088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004104789,"about_ca_topic_score_gemma":0.0001930866,"domain_scores_codex":[0.9990975,0.0000381169,0.0001617267,0.0003613032,0.0001572744,0.0001840481],"domain_scores_gemma":[0.9995883,0.00003410799,0.00002074046,0.0002682787,0.00004066466,0.0000478908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.1414e-7,0.0001085197,0.0005387674,0.00008565623,0.00008111344,0.00008129407,0.001745933,0.005290787,0.005898577,0.1701331,0.03814389,0.7778915],"study_design_scores_gemma":[0.00009013136,0.00002417118,0.0003218619,0.00002102568,0.000005650251,0.000006163001,0.00002641019,0.9809979,0.001080618,0.0001140732,0.01718688,0.0001251194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001557235,0.0002298747,0.9772171,0.0008022226,0.0008153358,0.0001012049,4.985711e-7,0.0006194033,0.01865708],"genre_scores_gemma":[0.7718511,0.000004905775,0.1875546,0.0002121814,0.0001970729,0.000013106,0.000004188023,0.00001031497,0.04015258],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9757071,"threshold_uncertainty_score":0.6344034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09725723618703863,"score_gpt":0.2967556515266978,"score_spread":0.1994984153396591,"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."}}