{"id":"W4231576889","doi":"10.31234/osf.io/a3y2p","title":"Characterizing the social diversity of bilingualism using language entropy","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Centre for Research on Brain Language and Music","funders":"","keywords":"Linguistics; Neuroscience of multilingualism; Multilingualism; Psychology; Computer science; Entropy (arrow of time); Natural language processing; Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007347094,0.0001134754,0.0002147166,0.00006787906,0.0007960369,0.00006677488,0.000522365,0.0002149539,0.0009783852],"category_scores_gemma":[0.0002274345,0.0000882083,0.000166276,0.0001046045,0.0002333286,0.00004370463,0.0008747565,0.0003127132,0.00002542758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001186289,"about_ca_system_score_gemma":0.000775223,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07212405,"about_ca_topic_score_gemma":0.0006823064,"domain_scores_codex":[0.9987516,0.0002935535,0.000200063,0.0001910406,0.0003455581,0.0002181912],"domain_scores_gemma":[0.9991776,0.0001261769,0.0002983872,0.000223035,0.0001249767,0.00004977655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000008147845,0.00004732982,0.002764691,0.0000685584,0.00004146539,6.136036e-7,0.9793608,0.00001527922,0.001660127,0.01257598,0.000207464,0.003249507],"study_design_scores_gemma":[0.001082548,0.00002953916,0.02972792,0.0003505932,0.0004649725,0.000001687639,0.8098914,0.002156877,0.009415169,0.004013544,0.1411081,0.001757704],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9653854,0.00006129278,0.00005017791,0.001930878,0.001822534,0.0003151666,0.00003631102,0.00004232176,0.03035594],"genre_scores_gemma":[0.9947402,0.0000387461,0.0001848055,0.0006820273,0.00171509,0.000001366395,0.0000145185,0.000008201271,0.002615058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1694695,"threshold_uncertainty_score":0.9999349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1360968030487849,"score_gpt":0.4765199884319377,"score_spread":0.3404231853831527,"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."}}