{"id":"W4396833177","doi":"10.1145/3613904.3642773","title":"CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs","year":2024,"lang":"en","type":"article","venue":"","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":206,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Code (set theory); Software deployment; Transparency (behavior); Thematic analysis; Class (philosophy); Multimedia; Software engineering; Mathematics education; Programming language; Qualitative research; Psychology; Artificial intelligence","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":[0.0007356828,0.0001303904,0.000175384,0.0001642234,0.00007645394,0.0004684961,0.0003449299,0.00003435505,0.000007281676],"category_scores_gemma":[0.00002272167,0.00009839699,0.00005125844,0.0004043033,0.00004207422,0.0002275083,0.0001139386,0.0001368085,0.00000295317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003970095,"about_ca_system_score_gemma":0.0002857684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004778982,"about_ca_topic_score_gemma":0.00002855118,"domain_scores_codex":[0.998645,0.00009136824,0.0002267554,0.0003204989,0.0004910672,0.0002253311],"domain_scores_gemma":[0.9993474,0.0001387932,0.0000692817,0.0002790144,0.00005507227,0.0001104516],"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":[0.00001195589,0.001010315,0.1146837,0.0004270166,0.0001526946,0.00003933594,0.004446233,0.001324413,0.001541945,0.02320805,0.0001680186,0.8529863],"study_design_scores_gemma":[0.0002669885,0.0007980219,0.005097889,0.0002458598,0.00004494085,0.000007795781,0.002182442,0.9877087,0.001030835,0.0003683754,0.002048111,0.0002000331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9317874,0.0007719063,0.06363203,0.002858485,0.0002765084,0.0001603539,0.000001610946,0.0003334422,0.0001782681],"genre_scores_gemma":[0.8925533,0.000007627928,0.1070301,0.00009839541,0.00005694596,0.00001125866,0.000002321019,0.00001054439,0.0002295356],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9863843,"threshold_uncertainty_score":0.4517719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03321512878270768,"score_gpt":0.3645469566558219,"score_spread":0.3313318278731143,"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."}}