{"id":"W6894148083","doi":"10.5281/zenodo.8289064","title":"HTRomance, Medieval Spain corpus of ground-truth for Handwritten Text Recognition and Layout Segmentation","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Segmentation; Text recognition; Feature (linguistics); Pattern recognition (psychology); Image segmentation; Text segmentation","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":[0.002106515,0.002894168,0.001549355,0.007780956,0.001166709,0.003203468,0.003513964,0.001939768,0.08108585],"category_scores_gemma":[0.00605973,0.0007034075,0.0009990375,0.004996751,0.0008589239,0.001361289,0.003001131,0.001326647,0.1187223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001499179,"about_ca_system_score_gemma":0.002442979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0330648,"about_ca_topic_score_gemma":0.04821218,"domain_scores_codex":[0.9978572,0.0003638516,0.0002280785,0.0007075876,0.000589505,0.0002538348],"domain_scores_gemma":[0.9961578,0.0005717229,0.0001976936,0.001228158,0.001581369,0.0002631433],"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":[0.0003115868,0.00007654245,0.001017612,0.001384235,0.00007230561,0.0002186572,0.0001519729,0.000524461,0.001656138,0.0008286981,0.9439986,0.04975914],"study_design_scores_gemma":[0.0002561272,0.00004536107,0.01519308,0.0006919119,0.00006684919,0.0004396401,0.0003260224,0.0009275485,0.003893831,0.001806839,0.9762968,0.00005599411],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.006113204,0.002623294,0.003887689,0.0002794953,0.0006646714,0.0001478267,0.9540954,0.01181124,0.02037721],"genre_scores_gemma":[0.00594611,0.0003007211,0.004080813,0.00007721551,0.00007464034,0.000178485,0.9803237,0.001559521,0.007458857],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.08108585,"threshold_uncertainty_score":0.2712592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03730919105986626,"score_gpt":0.2552495770165464,"score_spread":0.2179403859566802,"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."}}