{"id":"W7084140570","doi":"10.6084/m9.figshare.30204920.v1","title":"Additional file 2 of 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":"article","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":"Aspartame; Quality (philosophy); Identification (biology); Class (philosophy)","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002073011,0.001872232,0.00107565,0.002968033,0.000736749,0.001755957,0.002059338,0.001868155,0.7072228],"category_scores_gemma":[0.01852196,0.0007805947,0.001683242,0.002444656,0.0002917581,0.001969759,0.001675951,0.001248432,0.1404426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001241828,"about_ca_system_score_gemma":0.001780546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007663202,"about_ca_topic_score_gemma":0.0159934,"domain_scores_codex":[0.9992861,0.000178591,0.0001322388,0.0001877775,0.0001466685,0.0000686297],"domain_scores_gemma":[0.9797847,0.01758418,0.0005570879,0.000650727,0.00107271,0.0003506246],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000406254,0.0001153011,0.003799226,0.003342997,0.0001042299,0.0002319658,0.000143212,0.002017828,0.0004219022,0.002405037,0.9737162,0.01329574],"study_design_scores_gemma":[0.002088349,0.0001727611,0.01165932,0.001533053,0.0002871743,0.0005419716,0.0003684628,0.01173798,0.002500589,0.02394113,0.9449951,0.0001740444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.0002743502,0.00002518252,0.002304326,0.0001160864,0.00002670495,0.00006111243,0.9925747,0.00336989,0.001247612],"genre_scores_gemma":[0.007687171,0.0001045544,0.01839257,0.0004506179,0.0000535136,0.001063746,0.9637926,0.003364634,0.005090547],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.997927,"threshold_uncertainty_score":0.4176112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1416298451601406,"score_gpt":0.398109226742987,"score_spread":0.2564793815828463,"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."}}