{"id":"W2162940749","doi":"10.64152/10125/44156","title":"Evaluating automatic detection of misspellings in German","year":2008,"lang":"en","type":"article","venue":"Language learning & technology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Spell; Computer science; Edit distance; Natural language processing; German; Artificial intelligence; Competence (human resources); Linguistics; Psychology; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003601354,0.00007082299,0.0001440705,0.0003353393,0.00006995388,0.000007631648,0.0003658559,0.0001301073,0.00001017766],"category_scores_gemma":[0.0004118577,0.00007297812,0.00002700948,0.0007515202,0.00007967519,0.0001156057,0.00007766549,0.0003120369,0.00002922409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004390106,"about_ca_system_score_gemma":0.00002533782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001242223,"about_ca_topic_score_gemma":0.00003141105,"domain_scores_codex":[0.9991395,0.000087009,0.0002436677,0.0002313103,0.0001317647,0.0001667523],"domain_scores_gemma":[0.9993559,0.00008555333,0.0001395086,0.0003650298,0.00003871607,0.00001530686],"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":[0.000002277334,0.0000476651,0.006358929,0.00003277501,0.000004346198,0.00002459631,0.009170025,0.0006690644,0.3157609,0.001927674,8.451733e-7,0.666001],"study_design_scores_gemma":[0.0004915147,0.0003868756,0.04193254,0.00006655647,0.000006043987,0.0002452364,0.000569694,0.722401,0.2298347,0.003469396,0.0003496104,0.000246835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8822106,0.0001901865,0.1167275,0.0002333854,0.00002924043,0.00008717628,6.242084e-8,0.0004076048,0.0001142605],"genre_scores_gemma":[0.9829243,0.000006043328,0.01694719,0.00001574563,0.000007856658,0.000009240352,7.946438e-7,0.000005355007,0.00008346921],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.721732,"threshold_uncertainty_score":0.2975961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02104914928922183,"score_gpt":0.3133695975337752,"score_spread":0.2923204482445534,"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."}}