{"id":"W6969185994","doi":"10.5281/zenodo.8107448","title":"Workshop HTR-United: metadata, quality control and sharing process for HTR training data","year":2023,"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":"Suite; Process (computing); Quality (philosophy); Control (management); Training (meteorology); Training set","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"],"consensus_categories":[],"category_scores_codex":[0.00302568,0.0001542359,0.0002127522,0.0004465401,0.001566617,0.002205495,0.00327082,0.00006925224,0.0002915044],"category_scores_gemma":[0.002330127,0.000163204,0.0000343779,0.001311152,0.0001127112,0.001806142,0.002849899,0.000237215,0.0005062061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004054604,"about_ca_system_score_gemma":0.000007704684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000102119,"about_ca_topic_score_gemma":7.60298e-7,"domain_scores_codex":[0.9977589,0.0002544875,0.0003408346,0.000817552,0.0003781557,0.0004500298],"domain_scores_gemma":[0.9978803,0.0001847798,0.0001389645,0.001085728,0.0005241382,0.0001860748],"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":[0.00009049081,0.0001350747,0.00001463349,0.0003862441,0.0001649504,0.00002412464,0.005363134,0.0000544748,0.002746173,0.04575964,0.1068342,0.8384268],"study_design_scores_gemma":[0.001489942,0.0001832093,0.000461415,0.0001238467,0.00003299545,0.00008483223,0.00131438,0.1037667,0.0006855163,0.007556622,0.8837929,0.0005076628],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007665016,0.00005909646,0.9782994,0.002681283,0.00009190281,0.001034733,0.0009174527,0.004456393,0.004794694],"genre_scores_gemma":[0.9784853,0.0001334515,0.01015281,0.0007680787,0.0002246464,0.000001215197,0.00787253,0.001153197,0.001208783],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9708202,"threshold_uncertainty_score":0.9997332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2218400509208137,"score_gpt":0.361761120748736,"score_spread":0.1399210698279223,"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."}}