{"id":"W4392350883","doi":"10.1088/2632-2153/ad2f52","title":"Autonomous data extraction from peer reviewed literature for training machine learning models of oxidation potentials","year":2024,"lang":"en","type":"article","venue":"Machine Learning Science and Technology","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Canada First Research Excellence Fund; University of Toronto; European Commission","keywords":"Computer science; Training (meteorology); Data extraction; Peer review; Extraction (chemistry); Artificial intelligence; Machine learning; MEDLINE; Chemistry; Geography","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007776765,0.000326666,0.000553748,0.0009035841,0.0008352182,0.0008276883,0.001528473,0.0002469789,0.0002015385],"category_scores_gemma":[0.005977567,0.0002767906,0.00005182717,0.001924985,0.0009479991,0.002042068,0.0007663773,0.0008311371,0.00002838524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007515521,"about_ca_system_score_gemma":0.0002995766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003382993,"about_ca_topic_score_gemma":0.0000293159,"domain_scores_codex":[0.9960741,0.0002280587,0.0006882098,0.001513488,0.000864752,0.0006314209],"domain_scores_gemma":[0.9977355,0.0004049745,0.0004209979,0.0007649845,0.0005674938,0.000106071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002458347,0.00002153923,0.0004020102,0.0001706803,0.000009585012,0.0000102897,0.0009819003,0.005237392,0.9372402,0.005173741,0.00005322439,0.0506749],"study_design_scores_gemma":[0.0002885686,0.0002590229,0.0001465494,0.0004495491,0.00006658786,0.00009987946,0.0002002788,0.9176621,0.04911268,0.00927129,0.02208616,0.0003573088],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8551005,0.01243811,0.1214704,0.00637985,0.001619691,0.0008018009,0.0003075099,0.001488083,0.0003941351],"genre_scores_gemma":[0.9553175,0.0003656254,0.04315124,0.00005283627,0.0001368428,0.00004077863,0.0003234976,0.00004094475,0.0005707338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9124247,"threshold_uncertainty_score":0.9999684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0426779243544447,"score_gpt":0.3172604992317604,"score_spread":0.2745825748773157,"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."}}