{"id":"W4389520247","doi":"10.18653/v1/2023.findings-emnlp.663","title":"Towards Detecting Contextual Real-Time Toxicity for In-Game Chat","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research; McGill University; Ubisoft (Canada)","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Flagging; Metadata; Social media; Scalability; Transferability; World Wide Web; Online chat; Multimedia; The Internet; Machine learning; Operating system","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":[0.0004970382,0.0001290712,0.0001858128,0.0002643869,0.00007514354,0.00006718387,0.0004920347,0.00007904529,0.00001809983],"category_scores_gemma":[0.0002946599,0.0001257727,0.00006932403,0.0007986815,0.00002503906,0.0004898538,0.0002801726,0.0001016388,0.00008962224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009767312,"about_ca_system_score_gemma":0.00003939496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009450233,"about_ca_topic_score_gemma":0.00006573952,"domain_scores_codex":[0.9987706,0.00003246271,0.0002459061,0.0004114332,0.0001665465,0.0003730493],"domain_scores_gemma":[0.9991726,0.000236494,0.00006825278,0.0003763646,0.00008333332,0.00006301548],"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":[0.00004035536,0.00005334432,0.0001245049,0.00004351034,0.00001410158,0.00003313875,0.001275666,0.0002221157,0.2012523,0.03663009,0.001692897,0.7586179],"study_design_scores_gemma":[0.0005266129,0.0003468353,0.001308739,0.00002902012,0.000001772428,0.00001606313,0.0001177407,0.109362,0.853,0.03196807,0.002945851,0.0003772707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05936938,0.000003391188,0.9330269,0.0003622667,0.0001643938,0.0004230185,0.000002669607,0.003462032,0.003185972],"genre_scores_gemma":[0.8505772,0.00002031994,0.1469539,0.0002383863,0.00006476249,0.000204606,0.000001728057,0.00002021927,0.001918849],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7912078,"threshold_uncertainty_score":0.512886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02604361725977513,"score_gpt":0.3008491043650964,"score_spread":0.2748054871053213,"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."}}