{"id":"W2550742442","doi":"10.16995/dscn.315","title":"How to Do Lexical Quality Estimation of a Large OCRed Historical Finnish Newspaper Collection with Scarce Resources","year":2020,"lang":"en","type":"preprint","venue":"Digital Studies / Le champ numérique","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Newspaper; Usability; Computer science; Data collection; Quality (philosophy); Digital collections; Information retrieval; World Wide Web; Statistics; Mathematics; Sociology; Media studies","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00719854,0.001004332,0.001123594,0.01100687,0.001590232,0.005130279,0.001139977,0.001066555,0.003194839],"category_scores_gemma":[0.05409365,0.000704504,0.001114859,0.007445923,0.001228283,0.004746159,0.002026106,0.0007684215,0.003717261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001104226,"about_ca_system_score_gemma":0.001261175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009478221,"about_ca_topic_score_gemma":0.01282093,"domain_scores_codex":[0.9931207,0.001260596,0.001229485,0.001428322,0.002635529,0.0003253238],"domain_scores_gemma":[0.9644032,0.01171068,0.003397427,0.00386891,0.01602576,0.000594031],"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":[0.0005607166,0.0002536913,0.08854481,0.00343529,0.0005145395,0.001598378,0.01094354,0.004106218,0.06859075,0.002439568,0.02098997,0.7980224],"study_design_scores_gemma":[0.0001327826,0.0007789845,0.6377292,0.001450361,0.00107606,0.003856875,0.02264425,0.05718062,0.1240018,0.009448047,0.1409652,0.0007357306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6192213,0.004786854,0.334457,0.001483825,0.0006482087,0.00160675,0.01563041,0.006233176,0.01593241],"genre_scores_gemma":[0.5488381,0.001596739,0.4223028,0.0002373714,0.0002510544,0.00108445,0.01989002,0.001761761,0.004037779],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01100687,"threshold_uncertainty_score":0.03806996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03329315508436567,"score_gpt":0.3027029905237361,"score_spread":0.2694098354393705,"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."}}