{"id":"W4413579816","doi":"10.1007/978-981-96-4317-2_35","title":"Design, Development, and Annotation of the Persian Spoken Learner Corpus","year":2025,"lang":"en","type":"book-chapter","venue":"Springer handbooks in languages and linguistics.","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland; Cégep de l'Outaouais","funders":"","keywords":"Persian; Annotation; Natural language processing; Computer science; Artificial intelligence; Linguistics; Philosophy","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":[0.0002676073,0.0002313492,0.0002779066,0.0002013179,0.00009703673,0.00009116942,0.0004420993,0.0002034178,0.00000423078],"category_scores_gemma":[0.0003439412,0.0001765003,0.0000351885,0.00004919751,0.0001386919,0.00002353383,0.000480668,0.0003699109,6.128976e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004026223,"about_ca_system_score_gemma":0.0001367944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004953142,"about_ca_topic_score_gemma":0.0000414947,"domain_scores_codex":[0.9989641,0.00002381505,0.0002892408,0.0003718983,0.0001866508,0.0001642795],"domain_scores_gemma":[0.9991753,0.0001150963,0.0002109445,0.0003350226,0.0001267678,0.0000368441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002224979,0.00001554322,0.0002750346,0.0005849623,0.00006045987,0.00009489017,0.004950713,0.00000321981,0.0003778429,0.6935485,0.0002214103,0.2998452],"study_design_scores_gemma":[0.002802654,0.0004656787,0.001302509,0.0234292,0.0003935252,0.0001043268,0.0003763319,0.003866638,0.138247,0.3250521,0.499769,0.004191097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.0007530886,0.1841727,0.267366,0.0003209605,0.002019376,0.002028286,0.00003011553,0.0006863049,0.5426232],"genre_scores_gemma":[0.0871048,0.0006753274,0.7500646,0.0003164322,0.0002819799,0.00001666236,0.000008043825,0.00005531309,0.1614768],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4995476,"threshold_uncertainty_score":0.7197472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01398658037557553,"score_gpt":0.2596698051059358,"score_spread":0.2456832247303603,"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."}}