{"id":"W4385947706","doi":"10.48550/arxiv.2308.00389","title":"Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canada First Research Excellence Fund; University of Toronto; European Commission; Canadian Institute for Advanced Research","keywords":"Pipeline (software); Convolutional neural network; Artificial intelligence; Computer science; Machine learning; Set (abstract data type); Artificial neural network; Automation; Data set; Data collection; Training set; Data mining; Statistics; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0167615,0.001926647,0.002556575,0.03437206,0.001573893,0.004465469,0.003469607,0.001602759,0.01231909],"category_scores_gemma":[0.08469821,0.001083942,0.002315581,0.01826564,0.00114821,0.005262765,0.003989926,0.001899589,0.01516074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001808833,"about_ca_system_score_gemma":0.01479331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003940796,"about_ca_topic_score_gemma":0.008755617,"domain_scores_codex":[0.9910965,0.002138162,0.001742899,0.001917853,0.002828,0.0002766085],"domain_scores_gemma":[0.9224055,0.0395461,0.006846352,0.009328691,0.02077517,0.001098124],"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":[0.000644289,0.0003942119,0.01597881,0.0250893,0.0005544375,0.001319383,0.001149566,0.01037762,0.03007161,0.01609865,0.2102503,0.6880719],"study_design_scores_gemma":[0.0004868135,0.0006846292,0.01694577,0.003699498,0.0008566395,0.000947389,0.001588471,0.09278326,0.06762718,0.08266378,0.7311399,0.0005766869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03421228,0.01724219,0.4618407,0.00577379,0.001621306,0.006262861,0.4092791,0.04419903,0.0195686],"genre_scores_gemma":[0.0722388,0.005031412,0.6616909,0.000621783,0.0006600257,0.00577143,0.2477312,0.001781276,0.004473252],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03437206,"threshold_uncertainty_score":0.08864433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3709789710801434,"score_gpt":0.2956307195027804,"score_spread":0.07534825157736302,"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."}}