{"id":"W4391767333","doi":"10.1007/978-3-031-70543-4_11","title":"CATMuS Medieval: A Multilingual Large-Scale Cross-Century Dataset in Latin Script for Handwritten Text Recognition and Beyond","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs; University of Toronto; Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Scale (ratio); Artificial intelligence; Speech recognition; Linguistics; Geography; Cartography; Philosophy","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001894285,0.0006666366,0.0006903824,0.001409796,0.0002595646,0.001280215,0.001801403,0.000561633,0.00002760213],"category_scores_gemma":[0.0002302444,0.0006397248,0.0001320102,0.0006695082,0.0007499844,0.001004682,0.001513262,0.001071487,0.00006497995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000271958,"about_ca_system_score_gemma":0.0003868768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005274299,"about_ca_topic_score_gemma":0.0008172487,"domain_scores_codex":[0.9950483,0.0000438229,0.000861923,0.00232122,0.0008042838,0.0009204437],"domain_scores_gemma":[0.9975008,0.0006594488,0.0002596425,0.00100204,0.0003417702,0.0002363385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003014967,0.00009628075,0.0000834427,0.0003008601,0.00001795706,0.0001588613,0.003340198,0.00006341883,0.0003252033,0.001062887,0.0002706199,0.9942501],"study_design_scores_gemma":[0.00243153,0.0007074232,0.0002404308,0.002659553,0.00005645891,0.0002823597,0.000007714535,0.401274,0.01213582,0.549844,0.02802285,0.002337826],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001244138,0.001747108,0.990092,0.0006003507,0.0017375,0.00143475,0.002046551,0.0003862586,0.0007113343],"genre_scores_gemma":[0.06405623,0.000640686,0.9256653,0.005287315,0.001198178,0.0002995165,0.002222997,0.0001841905,0.0004456386],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9919123,"threshold_uncertainty_score":0.9997566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02611180828481044,"score_gpt":0.294718516514478,"score_spread":0.2686067082296676,"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."}}