{"id":"W7104443750","doi":"10.5281/zenodo.17559036","title":"An LLM-based Toolbox for Automated Text Mining on the Uses of Chemicals","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"European Commission","keywords":"Toolbox; Software; Automation; Expert system; Visualization","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":[],"consensus_categories":[],"category_scores_codex":[0.001904938,0.001959326,0.0009356478,0.005542726,0.000663476,0.002675589,0.001416985,0.001069587,0.02607009],"category_scores_gemma":[0.007213752,0.0007052019,0.001854317,0.002734453,0.0003946229,0.002943409,0.002702588,0.001533223,0.01933403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008615875,"about_ca_system_score_gemma":0.001616465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002270564,"about_ca_topic_score_gemma":0.004355871,"domain_scores_codex":[0.9987117,0.0002486195,0.0002759235,0.0003621178,0.000340319,0.00006128557],"domain_scores_gemma":[0.9965466,0.00189231,0.0003098741,0.0005376495,0.0005091422,0.0002044776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006748646,0.0004064382,0.005297222,0.003419155,0.0003771376,0.0007672123,0.0007541133,0.007671092,0.03194175,0.01259385,0.1669103,0.7691869],"study_design_scores_gemma":[0.0003203309,0.0002653851,0.008192095,0.0009492004,0.0002849976,0.001488028,0.0007321574,0.4411405,0.06851006,0.05830088,0.4196309,0.0001855595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005055319,0.0003680688,0.6655753,0.000517533,0.0001230227,0.0004754871,0.0497086,0.2746227,0.003553972],"genre_scores_gemma":[0.03642603,0.0004481132,0.8687901,0.0003640054,0.00006295849,0.000848206,0.08238331,0.005819437,0.004857767],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02607009,"threshold_uncertainty_score":0.08721316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03712296480879256,"score_gpt":0.3008059306487143,"score_spread":0.2636829658399217,"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."}}