{"id":"W4403094786","doi":"10.22541/au.172797494.46569043/v1","title":"Evaluation of Local Explainability Methods in Turkish Text Classification Tasks","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Turkish; Computer science; Artificial intelligence; Natural language processing; 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":[0.01191212,0.0001667071,0.0002794992,0.0002516769,0.00001534642,0.00009001171,0.0008783648,0.0002836815,0.00004806492],"category_scores_gemma":[0.0003496459,0.0001557026,0.0001003992,0.0003111803,0.00004933766,0.0001115605,0.001701449,0.0005864484,0.00001247194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006541057,"about_ca_system_score_gemma":0.0008432535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004385218,"about_ca_topic_score_gemma":0.0001059621,"domain_scores_codex":[0.9962109,0.0011958,0.000664987,0.0009043705,0.000857589,0.0001663479],"domain_scores_gemma":[0.9976718,0.0001805169,0.0001631019,0.001415454,0.000527982,0.00004109123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001109068,0.00004236981,0.00005985499,0.0001712939,0.00001261959,4.930488e-7,0.0008586204,0.03374879,0.0002932687,0.04600058,0.00005425563,0.9187567],"study_design_scores_gemma":[0.00007073779,0.000006438084,0.002060959,0.00006613487,0.00002321764,6.945983e-7,0.0001208801,0.72561,0.001472128,0.2704187,0.00004833368,0.0001017141],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01734293,0.000465525,0.9709391,0.0009441874,0.0009271374,0.0005654117,0.000001470515,0.0001126431,0.008701615],"genre_scores_gemma":[0.6435284,0.00000431196,0.3562486,0.00001922594,0.00003021799,0.0001111438,0.000003702256,0.000005512429,0.00004884012],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.918655,"threshold_uncertainty_score":0.6349369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1800156534794118,"score_gpt":0.443886896661136,"score_spread":0.2638712431817242,"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."}}