{"id":"W7117165756","doi":"10.1145/3756681.3756985","title":"Large Language Models as Robust Data Generators in Software Analytics: Are We There Yet?","year":2025,"lang":"","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Adversarial system; Robustness (evolution); Software quality; Software; Data quality; Data modeling; Source code; Software metric; Context (archaeology)","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":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.001707554,0.0006953368,0.0008516699,0.0007198834,0.0004718767,0.0008070681,0.006727991,0.0004581876,0.0009271564],"category_scores_gemma":[0.001034624,0.0006819573,0.0001565015,0.002914009,0.0001332353,0.002463135,0.00865666,0.001471282,0.0001506636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003021424,"about_ca_system_score_gemma":0.0009233727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009250443,"about_ca_topic_score_gemma":0.002807315,"domain_scores_codex":[0.9941025,0.000639089,0.0009930653,0.002221217,0.0007962727,0.001247818],"domain_scores_gemma":[0.9939129,0.0004889254,0.0003946173,0.004787731,0.0001849944,0.0002308056],"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":[0.00002517704,0.0002566365,0.008534944,0.0001709714,0.0001454986,0.0004710213,0.002907217,0.908251,0.000005790984,0.05266085,0.004681476,0.02188941],"study_design_scores_gemma":[0.001196764,0.00003072411,0.0003468935,0.0006278593,0.00007756823,0.000006235688,0.004531782,0.9848861,0.00004796157,0.005677263,0.001902167,0.0006687554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005784457,0.006259781,0.9744935,0.003983052,0.001628424,0.0004715707,0.0001095581,0.0003424976,0.006927173],"genre_scores_gemma":[0.8333923,0.0007682354,0.1504482,0.002597771,0.0003314296,0.0000164844,0.0001125001,0.000084902,0.01224826],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8276078,"threshold_uncertainty_score":0.9999861,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04894563841330968,"score_gpt":0.3169293484392279,"score_spread":0.2679837100259183,"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."}}