{"id":"W4392004492","doi":"10.5430/wjel.v14n2p502","title":"Evaluating AI-Generated Emails: A Comparative Efficiency Analysis","year":2024,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04940285,0.001063257,0.001569429,0.008464379,0.000812194,0.005036984,0.001971356,0.001661412,0.002942116],"category_scores_gemma":[0.4106957,0.0004968859,0.001063968,0.005397961,0.001011259,0.004817149,0.002807673,0.0008638193,0.001731802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002341949,"about_ca_system_score_gemma":0.001012015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001076997,"about_ca_topic_score_gemma":0.001130842,"domain_scores_codex":[0.8733699,0.09472384,0.0103867,0.00375478,0.0165253,0.001239521],"domain_scores_gemma":[0.2526177,0.6884145,0.01266158,0.01795983,0.02710513,0.001241286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.008424442,0.002462775,0.04560973,0.002935055,0.0009026421,0.0005183948,0.01028497,0.02885784,0.01725399,0.003318457,0.003033417,0.8763983],"study_design_scores_gemma":[0.002161331,0.02557856,0.3637902,0.001553014,0.002966238,0.002913369,0.02536675,0.4279262,0.104761,0.01343619,0.02857031,0.0009767874],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9188351,0.001755115,0.06085268,0.0004762188,0.00009270708,0.001044392,0.0005707377,0.002455515,0.01391761],"genre_scores_gemma":[0.9379097,0.0005868652,0.05699889,0.0001123306,0.00008018403,0.0005995923,0.0008468608,0.0007271658,0.00213838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04940285,"threshold_uncertainty_score":0.2612703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2380251381738855,"score_gpt":0.4968091037490571,"score_spread":0.2587839655751717,"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."}}