{"id":"W7071734181","doi":"","title":"Statistical Word Segmentation in Unfamiliar Speech","year":2025,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Pupillometry; Statistical learning; Flexibility (engineering); Segmentation; Word (group theory); Text segmentation; Statistical analysis; Speech segmentation; Statistical model; Phonetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003178174,0.0002026145,0.0001229685,0.000189138,0.0001238814,0.0005603952,0.0001459931,0.0001842494,0.001497845],"category_scores_gemma":[0.002254319,0.0001063064,0.00008449412,0.00009999026,0.0003409467,0.0007105481,0.000452976,0.0001512001,0.0003057066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001796752,"about_ca_system_score_gemma":0.0001920591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001074961,"about_ca_topic_score_gemma":0.001850338,"domain_scores_codex":[0.9998065,0.00004928285,0.00001609611,0.000067605,0.00003876875,0.00002182278],"domain_scores_gemma":[0.9991033,0.0004341032,0.0001628865,0.0001090908,0.0001277073,0.00006289605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004336604,0.00006139407,0.0393996,0.0001469273,0.00001599519,0.0004693172,0.002801554,0.002784147,0.7857,0.001098536,0.0003290955,0.1667598],"study_design_scores_gemma":[0.00003685484,0.001830314,0.6294388,0.000060946,0.00005882292,0.001774251,0.004378541,0.0775421,0.2752639,0.004410648,0.005141044,0.00006384351],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9910097,0.00004132971,0.007166356,0.0000205776,0.000004860167,0.00001068605,0.00002550546,0.00007390258,0.001647072],"genre_scores_gemma":[0.9962931,0.00002394763,0.003157515,0.00000837747,0.000001675657,0.000006064127,0.00003564833,0.00001143202,0.0004622089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001497845,"threshold_uncertainty_score":0.005010784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01952036631262871,"score_gpt":0.3039659382186552,"score_spread":0.2844455719060265,"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."}}