{"id":"W4411237045","doi":"10.1001/jamanetworkopen.2025.15160","title":"Citation Contamination by Paper Mill Articles in Systematic Reviews of the Life Sciences","year":2025,"lang":"en","type":"article","venue":"JAMA Network Open","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Citation; Mill; Contamination; Environmental science; History; Library science; Biology; Computer science; Archaeology; Ecology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch","research_integrity","bibliometrics"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch","bibliometrics","research_integrity"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2581261,0.001330348,0.003540765,0.0298491,0.003114284,0.00830628,0.003332609,0.003695413,0.007365118],"category_scores_gemma":[0.7471794,0.001659155,0.003989854,0.0460213,0.005119052,0.008129368,0.006925885,0.002521227,0.001984438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004964308,"about_ca_system_score_gemma":0.01229762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003410592,"about_ca_topic_score_gemma":0.006010819,"domain_scores_codex":[0.3363691,0.3432018,0.2206968,0.0219618,0.07538576,0.002384839],"domain_scores_gemma":[0.09548005,0.6120023,0.2275671,0.03120138,0.03199339,0.001755925],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001562125,0.0001823683,0.5468762,0.1241542,0.01668343,0.001084403,0.01197143,0.001429464,0.001421108,0.009206058,0.02856106,0.2568681],"study_design_scores_gemma":[0.0009357287,0.001088697,0.4547529,0.319256,0.02189872,0.006349667,0.009889449,0.007307376,0.005771742,0.04708341,0.124918,0.0007482453],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1914089,0.6100659,0.0687465,0.06911588,0.01302586,0.01089423,0.01678267,0.0007500607,0.01921],"genre_scores_gemma":[0.7589965,0.1218115,0.07245627,0.01656628,0.006751291,0.01327683,0.006025604,0.0005106667,0.003605096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9963046,"threshold_uncertainty_score":0.9148626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04692872264228141,"score_gpt":0.3433375674288132,"score_spread":0.2964088447865317,"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."}}