{"id":"W6931715084","doi":"10.5281/zenodo.8256728","title":"HTRomance, Medieval Italian 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":"Information Systems Education and Curriculum Development","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Segmentation; Text recognition; Feature (linguistics); Pattern recognition (psychology); Text segmentation; Image 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":[0.002397354,0.004149419,0.001674703,0.01031238,0.001843679,0.003130317,0.003772963,0.002674775,0.07555044],"category_scores_gemma":[0.00630087,0.0010587,0.001252233,0.005675131,0.001273462,0.002184876,0.003700761,0.001571789,0.1155891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001356689,"about_ca_system_score_gemma":0.00231924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01606696,"about_ca_topic_score_gemma":0.03457726,"domain_scores_codex":[0.9969829,0.0005307356,0.0002956964,0.001078583,0.0008086677,0.0003034636],"domain_scores_gemma":[0.9963301,0.0006959531,0.0002408252,0.001414028,0.001065769,0.0002532955],"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":[0.0003604369,0.0001292156,0.001018749,0.002753953,0.00009150139,0.0003562066,0.0002358075,0.000640302,0.004545286,0.001145716,0.9238473,0.06487563],"study_design_scores_gemma":[0.0002914876,0.000115691,0.01999007,0.0008711602,0.0001243601,0.001145725,0.0003550801,0.002369916,0.008879362,0.001962751,0.9637925,0.0001017571],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.01097756,0.004362683,0.007890533,0.0004800597,0.001049506,0.0004367408,0.9192283,0.02464655,0.03092805],"genre_scores_gemma":[0.008855842,0.0003623525,0.008096747,0.0001237546,0.0001616711,0.0004631033,0.9723696,0.00203273,0.007534252],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.07555044,"threshold_uncertainty_score":0.2527414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02987940687392079,"score_gpt":0.2453277859848166,"score_spread":0.2154483791108958,"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."}}