{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005172853,0.0001440081,0.0004363302,0.002574467,0.0001097096,0.001062085,0.0006108722,0.00002923177,0.002575363],"category_scores_gemma":[0.001631852,0.00009545374,0.0004463638,0.006138576,0.00004726294,0.001172343,0.00007246042,0.0003338404,0.0001395418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006653411,"about_ca_system_score_gemma":0.00009474516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008112349,"about_ca_topic_score_gemma":0.0001047551,"domain_scores_codex":[0.9965156,0.0002309665,0.001097977,0.0002020196,0.001745343,0.0002080365],"domain_scores_gemma":[0.9971941,0.0005933985,0.0004059914,0.000248352,0.001435239,0.0001229832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003050145,0.0004695022,0.01556434,0.00006476946,0.003341717,0.001006923,0.4865052,0.1061329,0.004858721,0.008901571,0.2344882,0.1383612],"study_design_scores_gemma":[0.002451794,0.0007000998,0.02203877,0.0004206026,0.004582562,0.00003146708,0.1727271,0.5313202,0.003576528,0.0009512371,0.2599502,0.001249442],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9782566,0.002561919,0.00342873,0.0002449217,0.001304984,0.0000999469,0.000016971,0.00005215532,0.01403379],"genre_scores_gemma":[0.9919341,0.000005407299,0.001105482,0.0002432766,0.0005050304,0.000002234417,0.000007378831,0.000006190365,0.0061909],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4251873,"threshold_uncertainty_score":0.9999749,"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."}}