{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005073017,0.0001652579,0.0002104529,0.0005087557,0.0005324585,0.0005318983,0.0006658935,0.0001111749,0.001960408],"category_scores_gemma":[0.0002147049,0.0001721204,0.00004162634,0.0004955656,0.00007125978,0.0002850457,0.0003914826,0.0001036812,0.0009837354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001120048,"about_ca_system_score_gemma":0.00002337795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003484986,"about_ca_topic_score_gemma":8.037564e-7,"domain_scores_codex":[0.9985708,0.0001422418,0.0003847195,0.0003493841,0.0003445763,0.0002082988],"domain_scores_gemma":[0.9984882,0.00002799818,0.0003806443,0.0003117073,0.0006974365,0.00009397244],"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":[0.00001706034,0.00007563143,0.000001689884,0.0005615989,0.0000888328,7.392035e-7,0.002516365,0.000001499529,0.0001193689,0.01219426,0.7428882,0.2415347],"study_design_scores_gemma":[0.0006733274,0.0001077524,0.0001289686,0.0002600971,0.00001799425,0.00002709814,0.0005733537,0.0003489558,0.0001705002,0.0003309121,0.9971501,0.0002109404],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002793365,0.0002509862,0.2310954,0.0004971481,0.001085953,0.001753858,0.00078912,0.0009230553,0.7633252],"genre_scores_gemma":[0.06534572,0.001550291,0.07607719,0.001746125,0.001725464,0.00001052829,0.04654591,0.00868422,0.7983146],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2542619,"threshold_uncertainty_score":0.9997941,"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."}}