{"id":"W4413902283","doi":"10.3389/frai.2025.1644098","title":"AI for scientific integrity: detecting ethical breaches, errors, and misconduct in manuscripts","year":2025,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Innovation Saskatchewan","keywords":"Scientific misconduct; Misconduct; Scientific integrity; Research integrity; Engineering ethics; Psychology; Computer security; Criminology; Political science; Law; Computer science; Engineering; Medicine; Pathology; Alternative medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.08561972,0.001399262,0.001346892,0.01239192,0.003952222,0.01731722,0.004798281,0.005179035,0.005317973],"category_scores_gemma":[0.4234526,0.0008728614,0.001426216,0.006139777,0.006877655,0.01583255,0.009287733,0.004048181,0.004578669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003603978,"about_ca_system_score_gemma":0.008590613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001349986,"about_ca_topic_score_gemma":0.001103405,"domain_scores_codex":[0.8859453,0.05320833,0.01292365,0.00994085,0.03595884,0.002023018],"domain_scores_gemma":[0.4418305,0.3114041,0.09006382,0.07960829,0.07067289,0.006420354],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008000265,0.0002702236,0.0658143,0.003066908,0.0005288442,0.001201501,0.009445433,0.01104522,0.01022667,0.1224766,0.03837683,0.7367474],"study_design_scores_gemma":[0.0001616674,0.0007958343,0.02359867,0.003572503,0.0005700979,0.004878788,0.005640048,0.2236194,0.07204138,0.4606721,0.2038702,0.0005793281],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07982005,0.01128368,0.806339,0.03678763,0.004090855,0.002480521,0.002419262,0.01361106,0.04316796],"genre_scores_gemma":[0.5894178,0.00393349,0.3872461,0.004584204,0.002045299,0.0008403949,0.002073535,0.0009709235,0.008888292],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.994821,"threshold_uncertainty_score":0.4528058,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2207587080626437,"score_gpt":0.4430035054144811,"score_spread":0.2222447973518374,"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."}}