{"id":"W4405967087","doi":"10.1101/2024.12.26.24319521","title":"Citation Contamination of Systematic Review Literature in the Life Sciences by Paper Mills","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Academic Writing and Publishing","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Contamination; Citation; Environmental science; Library science; Computer science; Biology; 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":"evaluation","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":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004086751,0.0001336336,0.0003795707,0.0001308859,0.000089733,0.0004852043,0.0004778249,0.0001124805,0.0000705705],"category_scores_gemma":[0.001755862,0.0000748682,0.00009063842,0.0001287258,0.0001253441,0.0001967505,0.00009050913,0.0007149884,0.00001091511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001437213,"about_ca_system_score_gemma":0.00005694179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000610736,"about_ca_topic_score_gemma":0.00003510474,"domain_scores_codex":[0.9982643,0.0004267979,0.0005732651,0.000216849,0.0004109544,0.000107868],"domain_scores_gemma":[0.99891,0.0004292937,0.0003110948,0.0001822835,0.000150489,0.00001687848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[9.116056e-7,0.00002175183,0.0001095843,0.7138844,0.0000345997,0.00000295845,0.0971186,0.000003112061,0.00001709197,0.109956,0.07876916,0.00008180772],"study_design_scores_gemma":[0.00008800736,0.00003669818,0.0001318222,0.948462,0.0004663429,0.000004291333,0.01306988,0.0002596602,0.000009303702,0.02030581,0.01684533,0.000320829],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.05563072,0.8924693,0.000004858493,0.01576533,0.001002214,0.001392267,0.0001634583,0.00005376645,0.03351812],"genre_scores_gemma":[0.9848313,0.009814827,0.000009523048,0.003259558,0.000376281,0.0001705377,0.0001088556,0.00001155831,0.001417544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9292006,"threshold_uncertainty_score":0.4678836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04335486111841079,"score_gpt":0.27953419382027,"score_spread":0.2361793327018592,"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."}}