{"id":"W4399371019","doi":"10.3138/jsp-2023-0079","title":"A Rapid Investigation of Artificial Intelligence Generated Content Footprints in Scholarly Publications","year":2024,"lang":"en","type":"article","venue":"Journal of Scholarly Publishing","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Content (measure theory); Computer science; Information retrieval; Data science; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003318715,0.0001149665,0.0002026265,0.0005559225,0.00005283791,0.006010108,0.0005734541,0.0003230516,0.00001898846],"category_scores_gemma":[0.008317075,0.00009682243,0.000116613,0.0007778664,0.0001394744,0.00150967,0.0001237463,0.00103317,0.000002572217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005605461,"about_ca_system_score_gemma":0.0005061852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003705648,"about_ca_topic_score_gemma":0.00002635638,"domain_scores_codex":[0.9980873,0.0001778917,0.0008633687,0.0002289094,0.000447671,0.0001948239],"domain_scores_gemma":[0.9979612,0.0000744385,0.0003131403,0.0001989617,0.001297111,0.000155178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006592322,0.00007089892,0.01174572,0.00004721405,0.0001103686,0.00001554431,0.0004371353,0.00003119141,0.7155743,0.003678005,0.002258798,0.2659649],"study_design_scores_gemma":[0.001015019,0.002142925,0.1390316,0.001660838,0.0001421089,0.0004436538,0.005651197,0.002052499,0.7177556,0.01982887,0.1094515,0.0008242531],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9695902,0.007849967,0.01265681,0.008924719,0.0005880754,0.00008391795,0.000009129015,0.00001715839,0.0002800245],"genre_scores_gemma":[0.9892955,0.0003140973,0.009654671,0.0002418121,0.0003662566,0.000005045135,0.00002239526,0.00001344942,0.00008674931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2651407,"threshold_uncertainty_score":0.9956917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.129285737070927,"score_gpt":0.3083854016389009,"score_spread":0.1790996645679739,"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."}}