{"id":"W4416593371","doi":"10.1093/llc/fqaf123","title":"Analyzing spelling patterns in the manuscripts of the Tales of Canterbury","year":2025,"lang":"en","type":"article","venue":"Digital Scholarship in the Humanities","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Spelling; Set (abstract data type); Yield (engineering); Linguistic analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001940421,0.0002537082,0.0003262954,0.00692067,0.001757026,0.001955973,0.0003799867,0.0002424701,0.002628305],"category_scores_gemma":[0.01494374,0.0001006566,0.000170154,0.006360297,0.001369808,0.0004835192,0.0009354977,0.000342377,0.0004980944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001655648,"about_ca_system_score_gemma":0.00138692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02964072,"about_ca_topic_score_gemma":0.07872482,"domain_scores_codex":[0.9982048,0.0004749668,0.0002292605,0.0003885705,0.0005739288,0.0001283653],"domain_scores_gemma":[0.9845468,0.007229507,0.002490227,0.001361178,0.003844782,0.0005273933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.001044869,0.0001412263,0.4916107,0.0008920266,0.0003184399,0.002674324,0.09837497,0.002156141,0.07445862,0.003859565,0.005479161,0.3189899],"study_design_scores_gemma":[0.000008300229,0.00012175,0.9540691,0.00009907303,0.000039921,0.0004579915,0.01617655,0.001125604,0.01148396,0.0007171756,0.01561053,0.00008994588],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931376,0.0004622455,0.001544364,0.00006120345,0.00004654341,0.00004212899,0.00127004,0.00003815083,0.003397838],"genre_scores_gemma":[0.993282,0.0001579756,0.003482148,0.00001415782,0.00002158931,0.00003815211,0.001044669,0.00002619804,0.001933095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02964072,"threshold_uncertainty_score":0.05893642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06552031463400951,"score_gpt":0.3180423681299079,"score_spread":0.2525220534958984,"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."}}