{"id":"W3093256017","doi":"10.1111/desc.13050","title":"Dual language statistical word segmentation in infancy: Simulating a language‐mixing bilingual environment","year":2020,"lang":"en","type":"article","venue":"Developmental Science","topic":"Language Development and Disorders","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Syllable; Psychology; Text segmentation; Linguistics; Syllabic verse; Population; Speech segmentation; First language; Word (group theory); Computer science; Segmentation; Natural language processing; Artificial intelligence; Speech recognition","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000484928,0.0002048656,0.0001837505,0.0001686987,0.0001808767,0.00008375115,0.0002733337,0.0000572317,0.002493979],"category_scores_gemma":[0.0002278433,0.0001975413,0.00002401724,0.0007839371,0.0002451103,0.0002799331,0.0002295215,0.0001958145,0.0005946667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001954781,"about_ca_system_score_gemma":0.0002626506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002312222,"about_ca_topic_score_gemma":0.00008663023,"domain_scores_codex":[0.997714,0.0000621181,0.0004084026,0.0006387458,0.0005720662,0.0006046233],"domain_scores_gemma":[0.999445,0.0001151212,0.00008846148,0.0001168254,0.00001221612,0.0002224176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0001334239,0.0001973237,0.1410288,0.00002990708,0.00002794785,0.0008892741,0.5212845,0.0002299285,0.06548077,0.0008250547,0.0002614117,0.2696117],"study_design_scores_gemma":[0.004632846,0.0001590986,0.6149843,0.00007463727,0.00001923728,0.00005695292,0.3572362,0.002577282,0.01751084,0.0001085732,0.001162904,0.001477094],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9880319,0.000109839,0.001347963,0.0002071226,0.0001905928,0.0003271801,0.00001379512,0.00008851774,0.00968314],"genre_scores_gemma":[0.9752135,0.000002858381,0.02338477,0.001046366,0.00005727811,0.00002779537,0.00006245023,0.00001827211,0.0001867033],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4739555,"threshold_uncertainty_score":0.9984179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01897781355869269,"score_gpt":0.3111967944463043,"score_spread":0.2922189808876116,"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."}}