{"id":"W1990591837","doi":"10.1353/lan.2014.0076","title":"How to investigate linguistic diversity: Lessons from the Pacific Northwest","year":2014,"lang":"en","type":"article","venue":"Language","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Falsifiability; Syntax; Linguistics; Diversity (politics); Lexical diversity; Typology; Rule-based machine translation; Semantics (computer science); Historical linguistics; Computer science; Scale (ratio); Test (biology); Relative clause; Linguistic universal; Natural language processing; Artificial intelligence; Theoretical linguistics; Sociology; Geography; Epistemology; Philosophy; Archaeology; Ecology; Vocabulary","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":[],"consensus_categories":[],"category_scores_codex":[0.0002325058,0.000144996,0.0001370023,0.00005166525,0.0003294482,0.0004704662,0.001742493,0.00005728416,0.000005451864],"category_scores_gemma":[0.000740004,0.00009892333,0.00004640507,0.0003457907,0.0000585959,0.000178753,0.001295191,0.000211554,0.00004529176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002817576,"about_ca_system_score_gemma":0.00002157849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001746564,"about_ca_topic_score_gemma":0.0008802301,"domain_scores_codex":[0.9989247,0.0000886191,0.00008783241,0.0003740646,0.0002659422,0.000258785],"domain_scores_gemma":[0.9986621,0.0002268233,0.00006440967,0.0008557359,0.00006105861,0.0001298973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002150316,0.0001165064,0.03104541,0.00006928602,0.00009940731,0.0005510252,0.1606693,0.00001174284,0.02768118,0.3302168,0.01751703,0.4320008],"study_design_scores_gemma":[0.002022369,0.0006845391,0.04741259,0.001033212,0.0002485266,0.0001001714,0.005769945,0.0185708,0.1763176,0.5088903,0.2342255,0.00472442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1435322,0.002398586,0.8021738,0.04629125,0.0008011478,0.0004026468,0.00006526338,0.002207128,0.002127979],"genre_scores_gemma":[0.8547573,0.000002133604,0.1420562,0.002451638,0.00025646,0.00000660045,0.0000119217,0.000009723257,0.0004479751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7112252,"threshold_uncertainty_score":0.4536716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01536529150023137,"score_gpt":0.2480672163176107,"score_spread":0.2327019248173793,"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."}}