{"id":"W2899082763","doi":"10.18653/v1/w18-5119","title":"Decipherment for Adversarial Offensive Language Detection","year":2018,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Decipherment; Offensive; Computer science; Adversarial system; Filter (signal processing); Plaintext; Artificial intelligence; Task (project management); Ciphertext; Computer security; Encryption; Natural language processing; Computer vision; Engineering; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001218594,0.00006681109,0.00005988655,0.00004446961,0.0001438987,0.00006391523,0.0001829659,0.00004434341,0.00004995878],"category_scores_gemma":[0.00004260943,0.00005826863,0.00006359991,0.0001243352,0.00002202946,0.0001392784,0.000049579,0.00003298566,0.0001896567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003838181,"about_ca_system_score_gemma":0.0000206626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009634587,"about_ca_topic_score_gemma":0.0001681133,"domain_scores_codex":[0.9993932,0.00001639484,0.00008866064,0.0002178688,0.0001075878,0.0001763328],"domain_scores_gemma":[0.9995538,0.00002945058,0.0000318212,0.000226027,0.0001080401,0.00005086765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009417978,0.00004468003,0.000008842569,0.000007175625,0.00004038416,0.000005251517,0.001558176,0.000007474707,0.1269962,0.007697018,0.004622351,0.8589183],"study_design_scores_gemma":[0.0008929355,0.0008693045,0.0002695696,0.000006053204,0.000009641892,0.00002046628,0.0001804819,0.02544281,0.9233323,0.001912064,0.04687219,0.0001921174],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05700544,0.000007573899,0.9341619,0.000155732,0.001456877,0.0002184071,6.90807e-7,0.0002355348,0.006757841],"genre_scores_gemma":[0.9549564,8.762183e-7,0.04201147,0.0004284824,0.0005872273,0.00002548544,8.787e-7,0.0000056619,0.001983485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.897951,"threshold_uncertainty_score":0.2437716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007391968568682176,"score_gpt":0.2447051758545074,"score_spread":0.2373132072858252,"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."}}