{"id":"W4412151029","doi":"10.1080/14664208.2025.2524285","title":"Evaluating the validity of census data for tracking speaker numbers: an investigation of Canada’s Indigenous languages","year":2025,"lang":"en","type":"article","venue":"Current Issues in Language Planning","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Wenner-Gren Stiftelserna","keywords":"Census; Indigenous; Tracking (education); Linguistics; Geography; Statistics; Natural language processing; Genealogy; Computer science; Sociology; History; Demography; Mathematics; Population; Pedagogy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002258945,0.00006819524,0.0001604611,0.00006348517,0.0001729775,0.00002069142,0.0004200583,0.00004649007,0.00001903572],"category_scores_gemma":[0.003958389,0.00005859823,0.00001617663,0.0001800111,0.00009672021,0.00008251226,0.00006456051,0.0001079756,1.01321e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007437517,"about_ca_system_score_gemma":0.0007798512,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2318654,"about_ca_topic_score_gemma":0.2413185,"domain_scores_codex":[0.9987671,0.0003351931,0.0002916588,0.000177318,0.0002363703,0.0001923016],"domain_scores_gemma":[0.9987296,0.0006236513,0.000201107,0.0002944776,0.0001207264,0.00003038743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005190469,0.00009756922,0.2605855,0.0003914887,0.00005000207,0.00001326801,0.6886221,0.000868028,0.001588052,0.01298384,0.00254275,0.03220549],"study_design_scores_gemma":[0.003089635,0.0002865614,0.2368919,0.002675231,0.0004006142,0.000004102744,0.6765286,0.01440814,0.008147674,0.005219946,0.05140207,0.0009455445],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949711,0.001931289,0.0003502579,0.0003076041,0.0008844528,0.0003692493,0.000184831,0.00001766883,0.0009835664],"genre_scores_gemma":[0.9977099,0.00001120561,0.00153573,0.00005574593,0.0002421946,0.000007605156,0.0003332437,0.000004889913,0.00009944149],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04885932,"threshold_uncertainty_score":0.7732497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2232075762142746,"score_gpt":0.5056563730349884,"score_spread":0.2824487968207139,"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."}}