{"id":"W7131619484","doi":"10.1109/ickg66886.2025.00021","title":"Quantifying Informativeness in Knowledge Graph-Augmented In-Context Learning for Multiple Choice Query Answering","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Leverage (statistics); Key (lock); Knowledge graph; Selection (genetic algorithm); Embedding; Question answering; Pipeline (software)","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":[0.001086441,0.0006444682,0.0008760072,0.001906547,0.0004800337,0.0003508741,0.001335539,0.0003049337,0.000009793388],"category_scores_gemma":[0.001062745,0.0007036355,0.0002926011,0.005606066,0.000167884,0.003143737,0.0009687559,0.001252535,0.00001167664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003186995,"about_ca_system_score_gemma":0.0002412604,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004317572,"about_ca_topic_score_gemma":0.01991528,"domain_scores_codex":[0.9952626,0.000344378,0.001620006,0.001106272,0.0002393363,0.00142744],"domain_scores_gemma":[0.9943373,0.004232418,0.0003721282,0.0006448619,0.0002650196,0.0001482783],"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":[0.0002206311,0.0003027566,0.2676277,0.0008418411,0.00006164134,0.00001270474,0.006092313,0.1899561,0.0008197539,0.01344049,0.00004121364,0.5205829],"study_design_scores_gemma":[0.004333047,0.0001384641,0.05119037,0.002382242,0.00001074852,0.000002406859,0.001878028,0.9302589,0.0023036,0.0006473139,0.006158309,0.0006966328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2176858,0.003226322,0.7741883,0.0002066183,0.001761093,0.001571425,0.000001923008,0.0001853041,0.001173158],"genre_scores_gemma":[0.9921523,0.0003267682,0.006097971,0.0003476584,0.00004963261,0.0002760065,0.000008156349,0.00003238968,0.0007090653],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7744665,"threshold_uncertainty_score":0.9995415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04087843100487856,"score_gpt":0.3274285805618252,"score_spread":0.2865501495569466,"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."}}