{"id":"W6963092801","doi":"10.18710/iexvvn","title":"Replication Data for: Diverging grammaticalization patterns across Spanish varieties: the case of 'perdón' in Mexican and Peninsular Spanish","year":2023,"lang":"en","type":"dataset","venue":"Ghent University Academic Bibliography (Ghent University)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universiteit Gent","keywords":"Corpus linguistics; Grammaticalization; Quarter (Canadian coin); Text corpus; Pronunciation","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001412488,0.0006203254,0.0005912695,0.002307287,0.000989035,0.001482153,0.001351225,0.0009923928,0.05222866],"category_scores_gemma":[0.008240297,0.0002517012,0.0005386432,0.003829883,0.0005204778,0.0008317747,0.001782648,0.001210683,0.02760099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009755331,"about_ca_system_score_gemma":0.001552261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03348332,"about_ca_topic_score_gemma":0.06103326,"domain_scores_codex":[0.9992015,0.0001740812,0.00007635977,0.0002582705,0.0001760686,0.0001137647],"domain_scores_gemma":[0.9946051,0.001597215,0.0003974696,0.001429567,0.001623978,0.0003467114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002350768,0.00007637464,0.01035745,0.0006714731,0.00002740019,0.0001283367,0.001160071,0.0002277357,0.0006604529,0.001296463,0.9685222,0.01663695],"study_design_scores_gemma":[0.0003576374,0.00003749424,0.0990158,0.0003109919,0.00002979181,0.000138433,0.003032092,0.0004281232,0.0007783263,0.001500948,0.8943151,0.00005513446],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0103499,0.0001048979,0.0003584136,0.0003026685,0.0001202891,0.00008680722,0.9819838,0.0003296637,0.006363606],"genre_scores_gemma":[0.01273413,0.0000548143,0.001148896,0.00009229211,0.00003306978,0.0006423147,0.9812198,0.0002050165,0.003869585],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05222866,"threshold_uncertainty_score":0.1747223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05717242911642985,"score_gpt":0.3038393086808746,"score_spread":0.2466668795644448,"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."}}