{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003322052,0.00115234,0.001102378,0.001763205,0.0007610335,0.002462993,0.002509221,0.002293789,0.00319949],"category_scores_gemma":[0.0383798,0.0006318499,0.0007490373,0.001238075,0.003618847,0.004729053,0.003077837,0.002484606,0.0009908057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001309285,"about_ca_system_score_gemma":0.0007654527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00269398,"about_ca_topic_score_gemma":0.001235426,"domain_scores_codex":[0.9956415,0.001348672,0.0001369144,0.0007106525,0.001617262,0.0005449676],"domain_scores_gemma":[0.9507819,0.0383412,0.002309653,0.005623732,0.00251435,0.0004291538],"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":[0.002274374,0.0002188812,0.003714811,0.0004450819,0.0002650722,0.0005020165,0.000695609,0.4163831,0.0439963,0.1450871,0.009075576,0.3773421],"study_design_scores_gemma":[0.00001524444,0.0000928544,0.0006425739,0.00002953011,0.00003539881,0.0001922224,0.00005537113,0.9270073,0.01445082,0.05656881,0.000873174,0.00003664044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1381612,0.002505148,0.8380523,0.00130356,0.0002968156,0.00008550279,0.0003157988,0.002352794,0.01692689],"genre_scores_gemma":[0.9195574,0.0007050467,0.07315389,0.0002545154,0.000312379,0.00003937485,0.0002750847,0.0003404686,0.005361722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003322052,"threshold_uncertainty_score":0.01756889,"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."}}