{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001400321,0.0000646743,0.0001154312,0.00009831294,0.000201391,0.0002426388,0.0007637825,0.00004496322,0.00002236819],"category_scores_gemma":[0.0009387434,0.00003659815,0.00006500487,0.0002605903,0.0003701028,0.0001816739,0.00006049314,0.0002149772,0.0000017114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003728202,"about_ca_system_score_gemma":0.00008671996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002005326,"about_ca_topic_score_gemma":0.01370476,"domain_scores_codex":[0.9988628,0.0003956438,0.000265458,0.00008912053,0.0002316531,0.0001553397],"domain_scores_gemma":[0.9991639,0.0004729622,0.0001078853,0.0001919679,0.00005777795,0.00000555118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000006911194,0.00005999618,0.3549009,0.00002975442,0.0000110122,0.000005412185,0.07047079,0.00001100616,0.00001848111,0.5738497,0.00002922741,0.0006067781],"study_design_scores_gemma":[0.0004009509,0.00003255745,0.6849483,0.0005367802,0.00003507594,0.000002614589,0.1767405,0.00001250392,0.0002295108,0.1167502,0.02014118,0.0001699293],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.887729,0.0001755099,0.00003454279,0.0006652614,0.0002756923,0.0001632518,0.00001909738,0.000005413335,0.1109322],"genre_scores_gemma":[0.9982824,0.00002040562,0.000003595876,0.0005500946,0.00005720435,0.000005522035,0.000002887095,0.000002759153,0.0010751],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4570996,"threshold_uncertainty_score":0.7647576,"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."}}