{"id":"W4387869001","doi":"10.1145/3630009","title":"The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Snippet; Artificial intelligence; Code (set theory); Code generation; Machine learning; Artificial neural network; Construct (python library); Set (abstract data type); Programming language; Natural language processing","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003093974,0.0001623971,0.0001775583,0.0001133985,0.00098078,0.0001844319,0.0005770446,0.00008452837,0.000001180219],"category_scores_gemma":[0.007085171,0.00009063233,0.00007242699,0.0004059228,0.0001361683,0.00009402546,0.00004893035,0.0005322013,0.000002152582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001875563,"about_ca_system_score_gemma":0.00002346645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002494867,"about_ca_topic_score_gemma":0.00001091458,"domain_scores_codex":[0.9985721,0.0004040075,0.0001823812,0.0003158757,0.0001595517,0.000366144],"domain_scores_gemma":[0.9700059,0.02928983,0.00003345676,0.0005505874,0.00005253809,0.0000677213],"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":[0.00008102532,0.00001218616,0.00027227,0.0000555452,0.0001588625,0.00000521852,0.002132267,0.433626,0.001625769,0.006453176,0.0002361658,0.5553415],"study_design_scores_gemma":[0.0007295101,0.0001060805,0.001471828,0.0000101555,0.00002763213,0.00008168417,0.00004341153,0.9784437,0.0008498167,0.0007515137,0.01733273,0.00015196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007885613,0.001059316,0.9813102,0.008152857,0.0007229608,0.0003068426,0.000006597801,0.0005548663,6.753113e-7],"genre_scores_gemma":[0.4078822,0.001311241,0.5884432,0.0003679638,0.00030088,0.0007014197,0.00001280354,0.00008448571,0.000895864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5551895,"threshold_uncertainty_score":0.8482123,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1099002619407233,"score_gpt":0.3378867384012966,"score_spread":0.2279864764605732,"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."}}