{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007127103,0.00015987,0.0001173557,0.0001295008,0.001442207,0.002391859,0.001538587,0.000062152,0.0004400183],"category_scores_gemma":[0.0001808727,0.0001115488,0.00006748565,0.0005147909,0.0000896386,0.0004956741,0.0008481071,0.0002591399,0.001033354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009752621,"about_ca_system_score_gemma":0.000008148598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002828103,"about_ca_topic_score_gemma":0.000002256669,"domain_scores_codex":[0.9983326,0.0002172019,0.0002366834,0.0005504041,0.0003358431,0.0003272443],"domain_scores_gemma":[0.9988648,0.00007270629,0.00004379015,0.0005544753,0.0003258786,0.0001383111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004570388,0.00006989711,8.767849e-7,0.00005284465,0.00007494991,0.000004305848,0.006699957,0.00002778808,0.006643898,0.03192908,0.1592959,0.7951548],"study_design_scores_gemma":[0.0002416121,0.0001162616,0.00009682014,0.00008562403,0.00002125145,0.00002797192,0.0003324623,0.03941861,0.0008823612,0.002412054,0.956203,0.000161995],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003381785,0.001328547,0.9560969,0.02244945,0.0004019683,0.002254543,0.0006601605,0.002461608,0.010965],"genre_scores_gemma":[0.981652,0.002394995,0.009837925,0.002596099,0.0003996876,0.000003341494,0.001069172,0.0009723215,0.001074518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9782702,"threshold_uncertainty_score":0.9998578,"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."}}