{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003459421,0.0004001027,0.0003045857,0.0002533679,0.0002079691,0.0003948863,0.0005791801,0.0004620503,0.001420207],"category_scores_gemma":[0.001410797,0.0003473946,0.0003414659,0.000139803,0.0004025641,0.0003248289,0.0009449422,0.0003626852,0.0001905541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003815983,"about_ca_system_score_gemma":0.0004827522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003182544,"about_ca_topic_score_gemma":0.003640602,"domain_scores_codex":[0.9998156,0.00006664076,0.00001300212,0.00003083038,0.00004159393,0.00003231538],"domain_scores_gemma":[0.999525,0.0003047322,0.00004409729,0.00003469823,0.00003397528,0.00005763549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002869899,0.0008826116,0.02964427,0.0006001965,0.0001005816,0.003464569,0.005655093,0.1465927,0.7804365,0.004158197,0.0004179707,0.02517747],"study_design_scores_gemma":[0.0004863936,0.005088338,0.08595002,0.000114863,0.0001871975,0.001875867,0.001882192,0.7276204,0.1669929,0.0052488,0.004358348,0.0001945863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917813,0.00003804306,0.007120209,0.00002624219,0.000005960461,0.00003147649,0.000103791,0.00008953768,0.0008035749],"genre_scores_gemma":[0.984125,0.0001138314,0.01485469,0.00001942971,0.000002782285,0.0001524065,0.0001614718,0.0000496443,0.0005206397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003182544,"threshold_uncertainty_score":0.006327987,"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."}}