{"id":"W4414755928","doi":"10.32604/cmc.2025.069134","title":"Prompt-Guided Dialogue State Tracking with GPT-2 and Graph Attention","year":2025,"lang":"en","type":"article","venue":"Computers, materials & continua/Computers, materials & continua (Print)","topic":"Cognitive Functions and Memory","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Information Technology Research Centre; Ministry of Science and ICT, South Korea; Iran Telecommunication Research Center","keywords":"Leverage (statistics); Robustness (evolution); Generalizability theory; Graph; State (computer science); Flexibility (engineering); Key (lock); Component (thermodynamics)","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","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.002036936,0.001442136,0.002372099,0.00102356,0.0006074672,0.002048533,0.0009993848,0.0005033978,0.001257192],"category_scores_gemma":[0.0001019757,0.001369238,0.0002981067,0.0006501935,0.0006514149,0.000766552,0.00100666,0.0004081021,0.0004320214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001744983,"about_ca_system_score_gemma":0.0001720768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009549195,"about_ca_topic_score_gemma":0.0001429684,"domain_scores_codex":[0.9915349,0.001352559,0.002363903,0.002474855,0.0005323525,0.001741379],"domain_scores_gemma":[0.9955308,0.0005645093,0.001210254,0.001496698,0.0008325652,0.0003651687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.003550037,0.001180667,0.006375748,0.001108588,0.002614377,0.0007543405,0.004199004,0.00001631667,0.8381137,0.009267551,0.04831591,0.08450379],"study_design_scores_gemma":[0.02731274,0.002191215,0.6092066,0.006423253,0.001735212,0.001051097,0.001275895,0.00007262465,0.2569086,0.005869168,0.08210976,0.005843776],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9219131,0.0003628884,0.05029579,0.000639525,0.02059324,0.003166662,0.0004434293,0.0009660013,0.001619314],"genre_scores_gemma":[0.986546,0.0001103714,0.004992573,0.001382583,0.001635788,0.0005374501,0.0005745459,0.000217888,0.004002848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6028309,"threshold_uncertainty_score":0.9998329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01683025783187646,"score_gpt":0.2683501925890723,"score_spread":0.2515199347571959,"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."}}