{"id":"W6949488576","doi":"10.5281/zenodo.13788176","title":"McCATMuS - Transcription model for handwritten, printed and typewritten documents from the 16th century to the 21st century","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Transcription (linguistics); Interoperability; Unicode; Normalization (sociology); Line (geometry)","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":[0.001144413,0.003054321,0.0009367584,0.003652318,0.001035298,0.002139661,0.002672154,0.001751268,0.02240904],"category_scores_gemma":[0.004381735,0.0006087387,0.002247167,0.002995881,0.0005966304,0.002019696,0.001889933,0.002098684,0.04380858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001949487,"about_ca_system_score_gemma":0.002353534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02023568,"about_ca_topic_score_gemma":0.04076288,"domain_scores_codex":[0.9987704,0.0001894005,0.0001216187,0.0005435904,0.000237534,0.0001374537],"domain_scores_gemma":[0.9984938,0.0002604554,0.00008265497,0.0004776753,0.0005854475,0.0001000352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008333416,0.0002967919,0.00434583,0.001659529,0.0002361657,0.000435073,0.000297759,0.01103783,0.008978713,0.001739874,0.7226571,0.247482],"study_design_scores_gemma":[0.0003877863,0.0006476161,0.02710096,0.001325729,0.0003469553,0.001574606,0.0008902985,0.1361624,0.03535052,0.006697504,0.7891842,0.0003314806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.05368378,0.006479571,0.06299873,0.001253121,0.002727051,0.001161022,0.7455758,0.09963796,0.02648306],"genre_scores_gemma":[0.03458425,0.0007297983,0.03994276,0.0003062039,0.0001679891,0.0007444493,0.9090543,0.001462346,0.0130079],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02240904,"threshold_uncertainty_score":0.07496578,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02879822394015591,"score_gpt":0.2527638435914121,"score_spread":0.2239656196512562,"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."}}