{"id":"W4416017187","doi":"10.1145/3746252.3761626","title":"Datasets for Supervised Adversarial Attacks on Neural Rankers","year":2025,"lang":"","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo; University of Toronto","funders":"","keywords":"Adversarial system; Artificial neural network; Key (lock); Feature (linguistics); Supervised learning","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":[0.00120465,0.0007583768,0.0007862656,0.000521771,0.001071751,0.0007303988,0.003388597,0.0004038789,0.00040503],"category_scores_gemma":[0.001405759,0.000757947,0.0004802913,0.001235164,0.0002686581,0.001175721,0.001551588,0.0009471042,0.0001477391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002586741,"about_ca_system_score_gemma":0.0005942794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000170147,"about_ca_topic_score_gemma":0.00003878994,"domain_scores_codex":[0.9946322,0.000485501,0.0009646888,0.001929684,0.0007067253,0.001281214],"domain_scores_gemma":[0.9952692,0.001828877,0.0002529493,0.002166966,0.0002023285,0.0002797248],"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":[0.002955052,0.0005166882,0.0007546465,0.0003558451,0.0004894882,0.00006101744,0.0007886202,0.3466702,0.0002880282,0.2030564,0.1493189,0.2947451],"study_design_scores_gemma":[0.007798065,0.0004748531,0.0005332474,0.0001471083,0.0001532602,0.000003144769,0.0001162675,0.9379341,0.0003244199,0.001007866,0.05082002,0.0006876172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00131767,0.0001388787,0.9597691,0.01209692,0.01433888,0.001803113,0.0002698065,0.0003317962,0.009933854],"genre_scores_gemma":[0.8719372,0.00003768957,0.1055327,0.01240967,0.001693604,0.0001487246,0.0006445348,0.00009707447,0.007498831],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8706195,"threshold_uncertainty_score":0.9994872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02193130906810358,"score_gpt":0.3210918387249055,"score_spread":0.299160529656802,"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."}}