{"id":"W4389810683","doi":"","title":"CATMuS-Medieval: Consistent Approaches to Transcribing ManuScripts: A generalized set of guidelines and models for Latin scripts from Middle Ages (8th--16th century)","year":2024,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto; Université de Montréal","funders":"","keywords":"Computer science; Art; Natural language processing; History; Classics","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":[0.004462326,0.0008714952,0.0006397509,0.002423683,0.001493708,0.004720775,0.002621874,0.001250881,0.006093347],"category_scores_gemma":[0.01378204,0.001121662,0.0014609,0.001860689,0.00198588,0.00404712,0.002562051,0.001815734,0.002483349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002193041,"about_ca_system_score_gemma":0.004351733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01809176,"about_ca_topic_score_gemma":0.04164919,"domain_scores_codex":[0.9957957,0.002122206,0.000431837,0.0009634555,0.0005309473,0.0001557549],"domain_scores_gemma":[0.9929489,0.002954305,0.0004638873,0.001615498,0.001837564,0.0001798289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006894728,0.0002689233,0.01908367,0.0009547825,0.000237934,0.0005508321,0.01450545,0.09017633,0.01000954,0.2514635,0.02533842,0.5867211],"study_design_scores_gemma":[0.00009771279,0.000161697,0.007701426,0.0005658427,0.000162459,0.0004725075,0.005116228,0.6260875,0.01397209,0.2512456,0.09428166,0.0001352956],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03265939,0.0005372679,0.94926,0.0007028859,0.0000564422,0.0004007533,0.004100267,0.003636522,0.008646403],"genre_scores_gemma":[0.2781386,0.0003627408,0.705053,0.0002240566,0.00004219497,0.0007005145,0.009659298,0.001253327,0.004566351],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01809176,"threshold_uncertainty_score":0.03597295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.170512534241524,"score_gpt":0.2781819695454389,"score_spread":0.1076694353039149,"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."}}