{"id":"W6910466605","doi":"10.48448/cbzh-1251","title":"Automatic Detection of Machine Generated Text: A Critical Survey","year":2020,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generative grammar; Natural language; Product (mathematics); Detector; Work (physics); Language model","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001905696,0.0004375197,0.0006586848,0.001250664,0.0001678565,0.0001240496,0.001007812,0.0002694336,0.003077153],"category_scores_gemma":[0.004310353,0.0003962084,0.00007480592,0.004220681,0.002438781,0.0001722551,0.0002642619,0.0004534909,0.002543753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002360942,"about_ca_system_score_gemma":0.0009268208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003694337,"about_ca_topic_score_gemma":0.008880507,"domain_scores_codex":[0.9960545,0.0003663118,0.000613795,0.0009335009,0.001421494,0.0006103481],"domain_scores_gemma":[0.9979431,0.0002628392,0.0003947165,0.0006954405,0.000346884,0.0003570253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009687919,0.001066844,0.001330765,0.001007509,0.0002237781,0.00008735547,0.0003006564,0.0001976556,0.7902658,0.00223962,0.144066,0.05911717],"study_design_scores_gemma":[0.0006454057,0.000380168,0.003391468,0.0002821767,0.0001185281,0.00004208552,0.00002786964,0.9669826,0.01418569,0.0002028107,0.01288232,0.0008588635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03668352,0.009116895,0.1963041,0.002652196,0.01501362,0.01002416,0.02377897,0.02077235,0.6856542],"genre_scores_gemma":[0.9640899,0.00001502628,0.01887853,0.0001948097,0.0002858891,0.00002224065,0.0002947803,0.001118877,0.0150999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.966785,"threshold_uncertainty_score":0.999849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03524143377624262,"score_gpt":0.3210387684624098,"score_spread":0.2857973346861672,"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."}}