{"id":"W4413298069","doi":"10.1007/978-3-031-92602-0_30","title":"Evaluation of Local Explainability Methods in Turkish Text Classification Tasks","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007520821,0.0003326887,0.0006898052,0.0003864238,0.00006492913,0.0001258726,0.0005548471,0.0007761233,0.00001216687],"category_scores_gemma":[0.000494057,0.0003124955,0.00009044592,0.0003660616,0.0001557774,0.0001820907,0.000178603,0.0006705899,0.00000154324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005303792,"about_ca_system_score_gemma":0.0002764693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005350108,"about_ca_topic_score_gemma":0.001151874,"domain_scores_codex":[0.9962026,0.0009615284,0.001058029,0.0008260002,0.0006247472,0.0003270889],"domain_scores_gemma":[0.996619,0.001454908,0.0004229066,0.0008742731,0.0005717418,0.00005719737],"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":[0.00001049443,0.00002114716,0.0001337695,0.0001472357,0.00002019762,0.000003703346,0.0004053944,0.2958567,0.00002312125,0.08953065,0.00004491251,0.6138027],"study_design_scores_gemma":[0.0001165203,0.00004991765,0.0002138307,0.0007148524,0.00003321059,0.000004304165,0.0000455609,0.9267866,0.0001214674,0.070236,0.001432757,0.000244994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00008664561,0.01117929,0.9690219,0.0001524023,0.0009554132,0.001059729,0.000002571612,0.00003343379,0.01750863],"genre_scores_gemma":[0.993286,0.0002471411,0.005362408,0.0000622383,0.0001798476,0.000125504,0.00001641271,0.00002099941,0.0006994618],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9931993,"threshold_uncertainty_score":0.9999327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06882309600957642,"score_gpt":0.3543764321473846,"score_spread":0.2855533361378081,"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."}}