{"id":"W4402897200","doi":"10.1109/qrs62785.2024.00033","title":"Weaknesses in LLM-Generated Code for Embedded Systems Networking","year":2024,"lang":"en","type":"article","venue":"","topic":"Embedded Systems Design Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Code (set theory); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001603587,0.0001822454,0.0002652692,0.0002743898,0.0000487311,0.0008439781,0.0006778906,0.0001156531,0.000003139594],"category_scores_gemma":[0.00003355725,0.0001546781,0.00006631271,0.0008719262,0.00001465065,0.0005726364,0.0001171921,0.0001328258,0.00002462848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001246613,"about_ca_system_score_gemma":0.0001428279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001102358,"about_ca_topic_score_gemma":0.0001709901,"domain_scores_codex":[0.9982224,0.0002239204,0.0004448895,0.0005368339,0.0002041029,0.0003679031],"domain_scores_gemma":[0.9988512,0.0004734583,0.000051126,0.0004772964,0.00008890668,0.00005804036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006033865,0.0000559064,0.00009489105,0.0005003417,0.00004154973,0.00008705277,0.001244896,0.002407392,0.01198555,0.9244438,0.04929634,0.009836244],"study_design_scores_gemma":[0.0001216147,0.0000680191,0.000006368346,0.0004913677,0.000003658294,0.00003972908,0.00005414755,0.9436583,0.007531993,0.003963265,0.04381075,0.0002507989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006468716,0.00269738,0.985123,0.0003075418,0.002044473,0.0008025197,0.000004404843,0.002164633,0.006209131],"genre_scores_gemma":[0.9445449,0.00003719534,0.05228112,0.0001806834,0.0003214981,0.0004882579,0.000005706748,0.00003432555,0.00210633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.943898,"threshold_uncertainty_score":0.81385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04146562305789299,"score_gpt":0.3035065337521313,"score_spread":0.2620409106942383,"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."}}