{"id":"W7084067906","doi":"10.6084/m9.figshare.c.8052947.v1","title":"A large language model-based tool for identifying relationships to industry in research on the carcinogenicity of benzene, cobalt, and aspartame","year":2025,"lang":"en","type":"other","venue":"Figshare","topic":"Carcinogens and Genotoxicity Assessment","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Occupational Cancer Research Centre; University of Toronto","funders":"","keywords":"Inference; Pharmaceutical industry; Aside; Quality (philosophy); Causal inference; Human studies","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03115387,0.003117927,0.001823031,0.01737168,0.001150519,0.004019043,0.002288874,0.002190037,0.02003615],"category_scores_gemma":[0.1562793,0.001515049,0.008165871,0.007898387,0.0006589646,0.003810172,0.005207221,0.001851295,0.002758809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003052874,"about_ca_system_score_gemma":0.006399284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004494038,"about_ca_topic_score_gemma":0.01203403,"domain_scores_codex":[0.9838111,0.009255557,0.003040562,0.002261158,0.001411074,0.0002204558],"domain_scores_gemma":[0.7208968,0.2611169,0.009077664,0.004364415,0.003748396,0.0007957989],"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":[0.005756221,0.0007094294,0.1109663,0.06942067,0.01936193,0.003988193,0.004182382,0.0992935,0.009216839,0.03050993,0.1573641,0.4892305],"study_design_scores_gemma":[0.002995698,0.000925256,0.02236834,0.00581545,0.0136522,0.001942983,0.0008404963,0.6779065,0.009886396,0.09924612,0.1639337,0.0004869915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04162507,0.007937072,0.6721402,0.005040601,0.0003440748,0.003918319,0.1848989,0.07788199,0.006213867],"genre_scores_gemma":[0.2094498,0.001932757,0.6942557,0.001331651,0.0002459719,0.01055166,0.07872622,0.002198854,0.001307322],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9688461,"threshold_uncertainty_score":0.1647594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1767751440954841,"score_gpt":0.4122972393515684,"score_spread":0.2355220952560844,"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."}}