{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002710317,0.0004182011,0.0005617373,0.0007241508,0.0005488638,0.0002316354,0.001311127,0.0006922014,0.000008959091],"category_scores_gemma":[0.0008738579,0.0004680867,0.0003584193,0.0005724494,0.00004287549,0.0003744518,0.000791807,0.007775879,0.000006057557],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005031193,"about_ca_system_score_gemma":0.002358021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004576067,"about_ca_topic_score_gemma":0.0007607485,"domain_scores_codex":[0.9954319,0.0002639317,0.0008067826,0.0007257336,0.0005035197,0.002268105],"domain_scores_gemma":[0.9979531,0.0004576404,0.0008029044,0.0004184335,0.0002807321,0.00008725355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003283966,0.0000961937,0.00001424881,0.0001276663,0.0002491694,0.000009420125,0.00249585,0.02835058,0.001647001,0.3278857,0.00004263702,0.6387532],"study_design_scores_gemma":[0.0004087445,0.0003677492,0.00002816958,0.0002009735,0.00002843618,0.00005623632,0.0002197056,0.04979172,0.006107735,0.9419799,0.0003658295,0.0004447804],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002525095,0.0003130515,0.9945691,0.0003239019,0.0007467952,0.0006312585,0.000001523065,0.0005840494,0.0003052216],"genre_scores_gemma":[0.8899403,0.005362345,0.1017217,0.0001206436,0.001407334,0.0004996178,0.00001454444,0.00006277484,0.0008707777],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8928474,"threshold_uncertainty_score":0.9997771,"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."}}