{"id":"W4412153876","doi":"10.1007/978-3-031-97623-0_3","title":"Hiding in Plain Sight: On the Robustness of AI-Generated Code Detection","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Robustness (evolution); Sight; Code (set theory); Artificial intelligence; Computer vision; Programming language; Optics","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"],"consensus_categories":[],"category_scores_codex":[0.001188548,0.0003923557,0.0004162371,0.00118005,0.0002679944,0.0002813667,0.002088105,0.0003272831,0.00001005254],"category_scores_gemma":[0.0001661246,0.0003002871,0.000102583,0.001530311,0.0003049956,0.000296212,0.0005097127,0.001117071,0.000008085268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003456482,"about_ca_system_score_gemma":0.000429891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005578485,"about_ca_topic_score_gemma":0.0005975174,"domain_scores_codex":[0.9971051,0.0001017708,0.0005274297,0.001070427,0.0007250447,0.0004701832],"domain_scores_gemma":[0.9978541,0.0006150253,0.0002459696,0.001013831,0.0002056713,0.00006537375],"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":[0.00002330016,0.00003670332,0.00001819272,0.0000447518,0.00001195833,0.00003814136,0.0003644903,0.4253623,0.003842154,0.0146629,0.00002406974,0.555571],"study_design_scores_gemma":[0.0002002611,0.0001726847,0.0000444138,0.0006404409,0.000004661587,0.00001792867,3.261279e-7,0.867834,0.1140886,0.01618505,0.0004703225,0.0003412453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002065876,0.000098043,0.9926703,0.001079387,0.002109561,0.0004154398,0.000003522819,0.0001010155,0.001456852],"genre_scores_gemma":[0.9686102,0.00002920909,0.02954186,0.0009992985,0.0002891115,0.00002141854,0.000002761608,0.00002507453,0.0004810427],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9665443,"threshold_uncertainty_score":0.9999449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01563596583748072,"score_gpt":0.2303640308463903,"score_spread":0.2147280650089096,"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."}}