{"id":"W4406892457","doi":"10.1109/fllm63129.2024.10852461","title":"Comparative Analysis of Loop-Free Function Evaluation Using ChatGPT and Copilot with C Bounded Model Checking","year":2024,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Bounded function; Loop (graph theory); Function (biology); Model checking; Computer science; Control theory (sociology); Mathematical optimization; Algorithm; Mathematics; Artificial intelligence; Mathematical analysis; Control (management); Combinatorics","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":[0.007242751,0.000779114,0.0006577997,0.00178912,0.0004640235,0.001101763,0.001982107,0.0007751512,0.001713114],"category_scores_gemma":[0.04511604,0.0004111371,0.0009196808,0.0009895595,0.001715078,0.001694785,0.001202725,0.00127225,0.0002918897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00213094,"about_ca_system_score_gemma":0.003364931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0101287,"about_ca_topic_score_gemma":0.008171178,"domain_scores_codex":[0.991714,0.002840774,0.000461811,0.00062026,0.003621265,0.0007419777],"domain_scores_gemma":[0.9282434,0.0540356,0.00305415,0.008151754,0.006039537,0.0004755182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002033002,0.0003121295,0.01848131,0.0009184182,0.0002069795,0.0004302053,0.0006543845,0.8024982,0.01798549,0.03399109,0.003020364,0.1194685],"study_design_scores_gemma":[0.00004698665,0.0003876369,0.002072211,0.00006288713,0.0000554595,0.00009402461,0.00007321443,0.9677367,0.02416298,0.003923647,0.001358048,0.00002623344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6808564,0.001014892,0.2939951,0.0004797619,0.000092876,0.0002148715,0.0005117342,0.01202288,0.01081148],"genre_scores_gemma":[0.9147422,0.0001642583,0.08269536,0.0001021199,0.000009826555,0.0001094067,0.0004926185,0.0007510093,0.0009331676],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0101287,"threshold_uncertainty_score":0.03830379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06673743189225984,"score_gpt":0.3420002828752244,"score_spread":0.2752628509829645,"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."}}