{"id":"W4406193067","doi":"10.1007/978-981-97-1818-4_35-1","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":"Annotation; Persian; Computer science; Natural language processing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00441013,0.00107324,0.0009447037,0.004829346,0.002640402,0.002936768,0.002582906,0.0009807008,0.02944946],"category_scores_gemma":[0.00792913,0.001130404,0.0004442516,0.0032605,0.001704847,0.003902092,0.005788731,0.00260067,0.02459002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001436598,"about_ca_system_score_gemma":0.004929834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01037145,"about_ca_topic_score_gemma":0.01754645,"domain_scores_codex":[0.997273,0.0009465498,0.0002987483,0.000803367,0.0005227589,0.0001555008],"domain_scores_gemma":[0.9942866,0.001770179,0.0001965264,0.001114361,0.002198138,0.0004342278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000773176,0.0004593123,0.006215898,0.002438362,0.00006834039,0.001335716,0.01292497,0.004340461,0.1351279,0.02563802,0.1726338,0.6380441],"study_design_scores_gemma":[0.0003247441,0.000565803,0.01874806,0.0004183351,0.0001174036,0.001675458,0.00892303,0.02737937,0.1304204,0.01523864,0.7959465,0.0002422831],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1002365,0.001871433,0.6079489,0.002092273,0.00125297,0.01220402,0.1302236,0.045728,0.09844235],"genre_scores_gemma":[0.1042234,0.0005959203,0.6216779,0.0005612686,0.0002307648,0.01774187,0.2071227,0.01188568,0.03596058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02944946,"threshold_uncertainty_score":0.09851825,"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."}}