{"id":"W4406119379","doi":"10.3758/s13428-024-02582-2","title":"Expansion of the SyllabO+ corpus and database: Words, lemmas, and morphology","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Language Development and Disorders","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre de Recherche Industrielle du Québec; Université de Montréal; Université Laval; McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Morpheme; Transparency (behavior); Computer science; Linguistics; Natural language processing; Agreement; Syllabic verse; 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":[],"consensus_categories":[],"category_scores_codex":[0.003231336,0.0001068986,0.0002023341,0.0002540363,0.0001757842,0.00002370762,0.0002765476,0.0001239043,0.0005047505],"category_scores_gemma":[0.0005145012,0.00007452443,0.00002861959,0.0006290235,0.0005960495,0.00004727762,0.0005484353,0.0003838444,0.000004850112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000182024,"about_ca_system_score_gemma":0.000118099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007139642,"about_ca_topic_score_gemma":0.00005221399,"domain_scores_codex":[0.9969517,0.001891548,0.0002191064,0.0003594776,0.0002284768,0.0003496713],"domain_scores_gemma":[0.9984845,0.0007461146,0.00004424554,0.0005484828,0.000108486,0.00006816421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001833665,0.0001782233,0.2034487,0.00007022398,0.000041888,0.0000604583,0.00300235,4.429719e-8,0.1247112,0.0119832,0.008525532,0.6477948],"study_design_scores_gemma":[0.001823799,0.0001135409,0.9360071,0.00009437198,0.00006642297,0.0000495804,0.007486332,0.000005645784,0.02405539,0.001432568,0.02865229,0.0002128905],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9860147,0.006419004,0.001335938,0.0005419135,0.0004548127,0.0005850174,0.00002294985,0.00002025653,0.004605382],"genre_scores_gemma":[0.8934246,0.0007310424,0.0733465,0.0003199068,0.0000482801,0.0005249533,0.00003942866,0.00004226254,0.03152303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7325584,"threshold_uncertainty_score":0.5526664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1710921430824684,"score_gpt":0.5626949910866405,"score_spread":0.391602848004172,"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."}}