{"id":"W2531088284","doi":"10.1515/lingty-2016-0006","title":"Sampling for variety","year":2016,"lang":"en","type":"article","venue":"Linguistic Typology","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Variety (cybernetics); Sampling (signal processing); Stratification (seeds); Representation (politics); Computer science; Diversity (politics); Geography; Artificial intelligence; Sociology; Biology; Anthropology","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005921823,0.00007286377,0.0001421879,0.0000482025,0.0003423305,0.00001293269,0.0001719514,0.0001566391,0.0007737008],"category_scores_gemma":[0.02359861,0.00005523617,0.00005410549,0.00006583259,0.0003049909,0.00001194785,0.00002519148,0.00004469935,0.000127784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006235583,"about_ca_system_score_gemma":0.0002217119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004329688,"about_ca_topic_score_gemma":0.0004223835,"domain_scores_codex":[0.9990478,0.00009283015,0.0001867285,0.000220913,0.00008225574,0.0003695404],"domain_scores_gemma":[0.997937,0.001482591,0.00007746513,0.0001454305,0.000257712,0.00009982944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002014377,0.00001521204,0.0009292326,0.000002742877,0.00001119158,0.000002308531,0.001976265,2.110822e-7,0.0001793287,0.9929743,0.001120448,0.002768641],"study_design_scores_gemma":[0.0004231506,0.00003946302,0.0005756017,0.000005139816,0.000017264,0.000001846856,0.0001932215,0.000004421209,0.00002911346,0.1825271,0.8160927,0.00009096653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003308514,0.00007681457,0.6294371,0.01315844,0.01427528,0.0005735424,0.00006525713,0.0003783526,0.3387267],"genre_scores_gemma":[0.975493,0.00001952026,0.01427487,0.0009667405,0.003052133,0.00003400135,0.000004742694,0.00001213635,0.006142896],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9721844,"threshold_uncertainty_score":0.9846261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05980690076315893,"score_gpt":0.3738667254937471,"score_spread":0.3140598247305882,"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."}}