{"id":"W4402712669","doi":"10.34847/nkl.cf30u38e","title":"FAIRer transcriptions: HTR- United and the possibility of a common for training data","year":2024,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Training (meteorology); Computer science; Natural language processing; Geography; Meteorology","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.01901644,0.001589199,0.001604202,0.003508508,0.003527581,0.006462115,0.003241724,0.004156514,0.2942071],"category_scores_gemma":[0.1246635,0.001765232,0.001474441,0.005209655,0.002353722,0.01136376,0.007657822,0.005560685,0.1496238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00317148,"about_ca_system_score_gemma":0.005995736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01269815,"about_ca_topic_score_gemma":0.01403679,"domain_scores_codex":[0.9758288,0.00976851,0.00288931,0.005311776,0.004193992,0.002007541],"domain_scores_gemma":[0.8632154,0.04586685,0.003100036,0.06084407,0.02418925,0.002784399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001804889,0.0001384156,0.002639728,0.0005129596,0.0000565462,0.0003582565,0.003306717,0.001434889,0.006272341,0.02784109,0.8406868,0.1149475],"study_design_scores_gemma":[0.000347275,0.0001507173,0.00372903,0.000492478,0.0000446445,0.0003258382,0.002641042,0.01299425,0.01737158,0.03373402,0.9279159,0.0002532556],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.0245624,0.0004358444,0.3049075,0.02239223,0.02036532,0.001951177,0.3520938,0.1393946,0.1338971],"genre_scores_gemma":[0.1867521,0.0002376082,0.2656762,0.005812685,0.004177232,0.001976541,0.3174494,0.07838066,0.1395377],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9967583,"threshold_uncertainty_score":0.9842208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04217539025975647,"score_gpt":0.2956712044573642,"score_spread":0.2534958141976077,"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."}}