{"id":"W7039174724","doi":"","title":"Linguistic Markers of AI-Generated Text: A Comparative Analysis of Machine-Identified and Human-Inferred Predictors","year":2025,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Insect behavior and control techniques","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perplexity; Lexical diversity; Lexical choice; Quality (philosophy); Computational linguistics; Word lists by frequency; Generative grammar; Ask price; Diversity (politics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009118597,0.00005789154,0.0003198165,0.0001114101,0.0001045656,0.0000598829,0.0001347345,0.00006904322,0.000002991436],"category_scores_gemma":[0.0002223748,0.00002268425,0.0001976948,0.0005582915,0.0000150074,0.0001898868,0.00001676232,0.00007137212,8.945802e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008267583,"about_ca_system_score_gemma":0.00001772076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002489137,"about_ca_topic_score_gemma":0.000114032,"domain_scores_codex":[0.9987882,0.0001006029,0.0007754389,0.00003153649,0.0002422516,0.00006197355],"domain_scores_gemma":[0.9970274,0.0001900345,0.001684486,0.00003202686,0.001050308,0.00001574428],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000384016,0.0001158455,0.8617432,0.0001252881,0.00303349,8.885896e-8,0.002869454,0.001079955,0.1130594,0.01314783,0.003316281,0.001125191],"study_design_scores_gemma":[0.0004468439,0.0001725007,0.9854271,0.00008781854,0.0009490837,5.859586e-7,0.0006206761,0.004529413,0.004149752,0.00009854526,0.003454658,0.00006300326],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977272,0.00004392122,0.0001180923,0.00007908217,0.0002638575,0.0002863026,0.0001676962,0.000007994176,0.001305909],"genre_scores_gemma":[0.9996631,0.000003193678,0.000007444969,0.00002531039,0.00002002179,0.000006798815,0.00003419512,1.991242e-7,0.0002397555],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1236839,"threshold_uncertainty_score":0.09250368,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0148876258615229,"score_gpt":0.2786338573205616,"score_spread":0.2637462314590387,"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."}}