{"id":"W4394803700","doi":"10.46298/jdmdh.10542","title":"The Challenges of HTR Model Training: Feedback from the Project Donner le gout de l'archive a l'ere numerique","year":2023,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Rimouski; Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Université de Montréal; Université de Sherbrooke; Université du Québec à Rimouski","keywords":"Training (meteorology); Gout; Psychology; Computer science; Physical medicine and rehabilitation; Medicine; Physics; Internal medicine; Meteorology","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001048402,0.0001334587,0.0002298792,0.0001096825,0.0003781549,0.001138936,0.002598311,0.00002991523,0.000001158607],"category_scores_gemma":[0.0004060553,0.00007917797,0.00007862596,0.0001328643,0.0001762347,0.003672651,0.0007468448,0.0002023209,0.000003527266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001743777,"about_ca_system_score_gemma":0.0005431799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001614299,"about_ca_topic_score_gemma":0.000029235,"domain_scores_codex":[0.9985312,0.00005099702,0.0006555007,0.0001338982,0.0003843599,0.0002439933],"domain_scores_gemma":[0.9974395,0.001007369,0.0008053657,0.0005527225,0.0001610702,0.00003398562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002542696,0.00007130602,0.00003871055,0.0001697447,0.0002090681,0.00001228718,0.6311435,0.00119233,0.00001999339,0.1576338,0.01953827,0.1899455],"study_design_scores_gemma":[0.000406301,0.0001357502,0.0001530598,0.0007466994,0.00001932585,0.0001031612,0.1556592,0.757216,0.0000570839,0.07320493,0.0120745,0.0002239774],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1678548,0.003076673,0.7295034,0.005982498,0.0007581522,0.0004279931,0.0005517669,0.0002879297,0.09155677],"genre_scores_gemma":[0.9690569,0.0003139122,0.02980924,0.0001563502,0.0002993757,0.000003413637,0.00002522881,0.00001952593,0.0003160691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8012021,"threshold_uncertainty_score":0.999898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1937526202284116,"score_gpt":0.3030778760184903,"score_spread":0.1093252557900787,"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."}}