{"id":"W2577349305","doi":"","title":"Training & Quality Assessment of an Optical Character Recognition Model for Northern Haida.","year":2016,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Optical character recognition; Computer science; Character (mathematics); Language model; Unicode; Porting; Artificial intelligence; Natural language processing; Hidden Markov model; Speech recognition; Set (abstract data type); Image (mathematics)","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":[],"consensus_categories":[],"category_scores_codex":[0.001999834,0.00008227371,0.0001414077,0.0000711899,0.000058498,0.00005442922,0.0001335857,0.00006240162,0.00002048909],"category_scores_gemma":[0.0001320621,0.00005870962,0.00004325675,0.00005849314,0.0000320948,0.0004420023,0.00003415371,0.00003743924,0.000001475075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003400036,"about_ca_system_score_gemma":0.00004571881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001904283,"about_ca_topic_score_gemma":0.00007322981,"domain_scores_codex":[0.9988783,0.0001490026,0.0002564443,0.0002581073,0.0003238359,0.000134338],"domain_scores_gemma":[0.9991954,0.0001557644,0.0001446483,0.000208301,0.0002371745,0.00005871556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009485324,0.00003286807,0.0001066479,0.0000165779,0.000006971291,1.998207e-7,0.004493732,0.000008503348,0.02279605,0.0002842099,0.000001553302,0.9722432],"study_design_scores_gemma":[0.0009329293,0.0002249536,0.009958346,0.0001081984,0.00003125879,0.000004984791,0.0005171282,0.9643353,0.01193703,0.01172173,0.00003833461,0.0001897604],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5494052,0.00002021413,0.4498664,0.0001634325,0.00001275077,0.0002159114,0.00001598474,0.00005232415,0.0002477996],"genre_scores_gemma":[0.8992664,0.000007110665,0.1004191,0.00007082118,0.00005710146,0.0001064639,0.00003093824,0.000007057726,0.00003504183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9720534,"threshold_uncertainty_score":0.2394109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1226647332271734,"score_gpt":0.3879749591543143,"score_spread":0.265310225927141,"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."}}