{"id":"W4411895413","doi":"10.2139/ssrn.5332683","title":"Ppo-Cis: A Deep Reinforcement Learning Framework for Real-Time Toxicity Detection in Social Media","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Concordia University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001127004,0.001185376,0.001224693,0.00074414,0.0003648018,0.0008591097,0.00284002,0.001605866,0.003924939],"category_scores_gemma":[0.003191811,0.0005799071,0.000600456,0.0004121397,0.000551514,0.001218731,0.001614639,0.002674218,0.001113475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008020228,"about_ca_system_score_gemma":0.001554032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00737401,"about_ca_topic_score_gemma":0.01166533,"domain_scores_codex":[0.9996025,0.00007394064,0.0000157741,0.0001281362,0.0001079423,0.00007179644],"domain_scores_gemma":[0.9988765,0.000505664,0.0001107392,0.0001159842,0.0002610183,0.0001300918],"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":[0.000438201,0.0005101836,0.004111827,0.0001859486,0.0001659878,0.0001918346,0.00006498689,0.678048,0.006715604,0.006013545,0.01167771,0.2918762],"study_design_scores_gemma":[0.00000505873,0.00002009011,0.00007818481,0.000002320601,0.000003642652,0.000007529999,0.000001628222,0.9981536,0.0005299714,0.0009670086,0.000228022,0.000002911752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02388407,0.0004881257,0.9629347,0.0003140105,0.0001883907,0.0001414397,0.0004621759,0.009176818,0.00241025],"genre_scores_gemma":[0.6852007,0.0003045317,0.3003085,0.0005190619,0.0001687514,0.0003599859,0.001080213,0.0006348635,0.01142344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00737401,"threshold_uncertainty_score":0.01466221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01062135680049155,"score_gpt":0.2843653166184001,"score_spread":0.2737439598179086,"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."}}