{"id":"W4410260480","doi":"10.52058/2786-6025-2025-4(45)-1286-1298","title":"ПІДБІР КРИТЕРІЇВ ОЦІНКИ ТА ПРОВЕДЕННЯ ПОРІВНЯЛЬНОГО АНАЛІЗУ ВЕЛИКИХ МОДЕЛЕЙ ШТУЧНОГО ІНТЕЛЕКТУ DEEPSEEK ТА CHATGPT","year":2025,"lang":"uk","type":"article","venue":"Наука і техніка сьогодні","topic":"Military Technology and Strategies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction","keywords":"Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.001234876,0.002194532,0.002289233,0.001694166,0.00109689,0.000396341,0.00274357,0.002787797,0.00320136],"category_scores_gemma":[0.0005279008,0.00243699,0.001005229,0.002925523,0.001156104,0.001157229,0.0008668388,0.003530465,0.003435282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000706583,"about_ca_system_score_gemma":0.0008497418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009668881,"about_ca_topic_score_gemma":0.001373338,"domain_scores_codex":[0.9907791,0.0003645788,0.002358334,0.002254419,0.0009675207,0.003276066],"domain_scores_gemma":[0.9944736,0.0007290315,0.0003516587,0.003467645,0.0003656275,0.0006124346],"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":[0.000544822,0.001027585,0.005075666,0.003357509,0.003609082,0.001114045,0.003945788,0.006332884,0.005806604,0.793926,0.1205878,0.0546722],"study_design_scores_gemma":[0.009605,0.001638012,0.02524976,0.003611786,0.002732692,0.000368144,0.01021263,0.03609376,0.01597452,0.2911029,0.594629,0.008781741],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1236196,0.07435166,0.01021184,0.007308389,0.0119958,0.002738554,0.0006624183,0.00606491,0.7630469],"genre_scores_gemma":[0.9651839,0.005984837,0.002093166,0.001085529,0.0007520196,0.0003373916,0.000257364,0.0003104169,0.02399538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8415643,"threshold_uncertainty_score":0.9990795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004891088753394681,"score_gpt":0.2114476570658201,"score_spread":0.2065565683124254,"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."}}