{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002640917,0.001937951,0.001317652,0.001784544,0.0007411827,0.001398034,0.002573133,0.002508232,0.002572438],"category_scores_gemma":[0.01515021,0.0005620262,0.001195724,0.001371591,0.001014888,0.005417382,0.002688443,0.003283339,0.0009881585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00147279,"about_ca_system_score_gemma":0.00109676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008812467,"about_ca_topic_score_gemma":0.01409504,"domain_scores_codex":[0.9981693,0.0007970068,0.00007812887,0.0006080874,0.0002121601,0.0001352429],"domain_scores_gemma":[0.9924051,0.006048997,0.0003081021,0.000620094,0.0003913227,0.000226328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001150237,0.000699278,0.0118507,0.0007895567,0.0002787347,0.0003720454,0.0009697202,0.5594183,0.01032851,0.01134154,0.009799499,0.3930019],"study_design_scores_gemma":[0.00002877244,0.0001147659,0.0007247438,0.00001857855,0.00004153188,0.00004767933,0.00007601667,0.9770383,0.001636582,0.01941635,0.0008421531,0.00001435053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2207307,0.002921612,0.7563986,0.001811502,0.0001455018,0.0003652362,0.001752405,0.0122503,0.003624159],"genre_scores_gemma":[0.8746204,0.0003756384,0.1199784,0.0005936814,0.00008188839,0.0001929813,0.00279011,0.0002070618,0.001159849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008812467,"threshold_uncertainty_score":0.01752234,"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."}}