{"id":"W4399601886","doi":"10.1145/3672457","title":"<i>GIST</i> : Generated Inputs Sets Transferability in Deep Learning","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Scratch; Test set; GiST; Testability; Test (biology); Set (abstract data type); Artificial intelligence; Property (philosophy); Artificial neural network; Machine learning; Transfer of learning; Data mining; Reliability engineering; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.001257961,0.0002158835,0.0002973863,0.0003674011,0.000116139,0.00007916122,0.0003682734,0.000184779,0.00001742845],"category_scores_gemma":[0.001002545,0.0002221402,0.00007346048,0.0006935068,0.00003915224,0.0002652207,0.00002105428,0.001104523,0.000006898376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007139752,"about_ca_system_score_gemma":0.00004023812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004123545,"about_ca_topic_score_gemma":0.00001907588,"domain_scores_codex":[0.9981737,0.0005189678,0.0002672937,0.0005796716,0.0001239432,0.0003364366],"domain_scores_gemma":[0.9967943,0.002689452,0.00001621791,0.0003821684,0.00002704357,0.00009086318],"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":[0.000009907412,0.00001707465,0.000172914,0.00007740519,0.0000287553,0.00004304486,0.001407339,0.7082142,0.0007948376,0.000695565,0.000001275009,0.2885377],"study_design_scores_gemma":[0.0005327291,0.0002066395,0.002430211,0.0001246514,0.00003568353,0.0001780403,0.0000375814,0.9872193,0.002827532,0.001512832,0.004384219,0.0005105318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03212128,0.0005659097,0.964747,0.0004717308,0.0009844042,0.0001021035,0.000001732152,0.0009976539,0.000008236391],"genre_scores_gemma":[0.4218237,0.00008032699,0.577918,0.00006475033,0.0000260786,0.00002607718,0.000002103397,0.00002117869,0.00003778141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3897025,"threshold_uncertainty_score":0.9058613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04779516566455851,"score_gpt":0.3112324647310983,"score_spread":0.2634372990665398,"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."}}