{"id":"W4411112921","doi":"10.18653/v1/2025.cmcl-1.24","title":"An Empirical Study of Language Syllabification using Syllabary and Lexical Networks","year":2025,"lang":"en","type":"article","venue":"","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Syllabification; Computer science; Natural language processing; Artificial intelligence; Empirical research; Linguistics; Speech recognition; Mathematics; Statistics; Syllable","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":[],"consensus_categories":[],"category_scores_codex":[0.0001432674,0.00004392129,0.00007101183,0.00007510317,0.00005785835,0.00002184374,0.0002296343,0.00004634307,0.00000378865],"category_scores_gemma":[0.000008198827,0.00003763767,0.000007469225,0.0002898109,0.00003235271,0.0001206218,0.00008863341,0.00007150018,3.204915e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001358018,"about_ca_system_score_gemma":0.00004921994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002978876,"about_ca_topic_score_gemma":0.0000096572,"domain_scores_codex":[0.9995229,0.00005047172,0.0001165808,0.0001789954,0.00006400013,0.00006705189],"domain_scores_gemma":[0.9995958,0.0000524241,0.00002644992,0.0002720201,0.00003267618,0.00002061552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009571118,0.002850778,0.6237001,0.00002013025,0.00006300912,0.000005778811,0.003065231,0.001355983,0.003558969,0.3229332,0.0004988894,0.04193833],"study_design_scores_gemma":[0.0003430171,0.0002581346,0.5086021,0.0000171729,0.00001679168,0.000005661624,0.005866557,0.4800528,0.001117606,0.003558969,0.00004311795,0.000118087],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7048684,0.00006712093,0.2940136,0.0005704888,0.00005803545,0.0000729729,8.022516e-8,0.00004607883,0.0003032631],"genre_scores_gemma":[0.9819925,0.000002052149,0.01779311,0.0001371477,0.0000116697,0.000004709767,7.72811e-7,0.000001139894,0.00005693712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4786968,"threshold_uncertainty_score":0.153482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02737865592202788,"score_gpt":0.4028329125226792,"score_spread":0.3754542566006513,"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."}}