{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004410136,0.001073242,0.000944705,0.00482935,0.002640403,0.002936773,0.002582909,0.0009807032,0.02944943],"category_scores_gemma":[0.00792913,0.001130406,0.0004442529,0.003260503,0.001704849,0.003902096,0.005788734,0.002600675,0.02459003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001436601,"about_ca_system_score_gemma":0.004929838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01037145,"about_ca_topic_score_gemma":0.01754643,"domain_scores_codex":[0.997273,0.0009465507,0.0002987489,0.0008033681,0.0005227594,0.000155501],"domain_scores_gemma":[0.9942866,0.001770182,0.0001965266,0.001114363,0.002198141,0.0004342285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007731764,0.0004593128,0.006215888,0.002438362,0.00006834045,0.001335719,0.01292497,0.004340472,0.1351282,0.02563803,0.1726336,0.6380441],"study_design_scores_gemma":[0.0003247444,0.0005658036,0.01874802,0.0004183354,0.0001174037,0.001675458,0.00892303,0.02737942,0.1304205,0.01523867,0.7959464,0.0002422833],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1002363,0.001871434,0.6079496,0.002092271,0.001252972,0.01220401,0.1302233,0.04572798,0.09844211],"genre_scores_gemma":[0.1042232,0.0005959208,0.6216785,0.0005612682,0.0002307651,0.01774186,0.2071224,0.01188568,0.03596049],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02944943,"threshold_uncertainty_score":0.09851819,"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."}}