{"id":"W4401032320","doi":"10.1007/978-3-031-66064-1_3","title":"Pierce: A Testing Tool for Neural Network Verification Solvers","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Computer science; Artificial neural network; Programming language; Software engineering; Artificial intelligence","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":[0.001450596,0.0005719208,0.0004971765,0.0005082108,0.0005000379,0.000999463,0.003195159,0.0003383848,0.000008039174],"category_scores_gemma":[0.0004958216,0.0005563296,0.000177664,0.001032652,0.0004352871,0.0007244436,0.001450189,0.001216066,0.00003880808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004101453,"about_ca_system_score_gemma":0.0005045199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001303839,"about_ca_topic_score_gemma":0.0000117951,"domain_scores_codex":[0.9957587,0.0000313228,0.0005880611,0.001920612,0.0008116132,0.0008897518],"domain_scores_gemma":[0.996487,0.001516855,0.00032527,0.001261635,0.0002874566,0.0001217494],"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":[0.000004492922,0.000004189911,0.00003728876,0.00005581438,0.000007810567,0.0000243918,0.0002493041,0.6465754,0.00003350071,0.03204231,0.00003910383,0.3209264],"study_design_scores_gemma":[0.0001527746,0.0001117756,0.00005930048,0.0003726325,0.00001566117,0.00003811488,1.048851e-7,0.8312061,0.00002775424,0.1656511,0.001846306,0.0005183014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006162756,0.0003571083,0.9903973,0.0008284235,0.005271234,0.0006880495,0.000003910706,0.0004684765,0.00192385],"genre_scores_gemma":[0.06346667,0.00000697401,0.9324598,0.0009215215,0.002307668,0.00003642925,0.00001030463,0.00007759994,0.0007129753],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3204081,"threshold_uncertainty_score":0.9996888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02549068661471008,"score_gpt":0.2695432457109795,"score_spread":0.2440525590962694,"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."}}