{"id":"W7131634265","doi":"10.1109/ickg66886.2025.00020","title":"Evaluating Knowledge Graph-Enhanced Context for Multiple-Choice Question Answering","year":2025,"lang":"","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Relevance (law); Question answering; Selection (genetic algorithm); Context (archaeology); Scope (computer science); Key (lock); Knowledge representation and reasoning; Domain knowledge; General knowledge","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":[0.002485543,0.001727261,0.000947156,0.001655403,0.0004150142,0.001296523,0.001816218,0.002323949,0.003618595],"category_scores_gemma":[0.01862209,0.0003084418,0.001064954,0.000866352,0.0004601436,0.004207949,0.002313186,0.001726577,0.001378506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000848206,"about_ca_system_score_gemma":0.001148035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005974871,"about_ca_topic_score_gemma":0.007305108,"domain_scores_codex":[0.9978282,0.0009773526,0.0001100737,0.0006368856,0.0003363725,0.000111156],"domain_scores_gemma":[0.9915235,0.006773894,0.0003171573,0.000565919,0.0004819833,0.0003375044],"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":[0.004832237,0.002121102,0.01735139,0.003767539,0.0005562155,0.000564983,0.001607316,0.1091167,0.02345353,0.004420893,0.01646371,0.8157444],"study_design_scores_gemma":[0.0004532249,0.002849332,0.008249071,0.0002604251,0.0003857557,0.0004925531,0.0008094505,0.942772,0.01435614,0.01773035,0.01152519,0.0001164705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6978592,0.01553689,0.231937,0.001247958,0.0006358761,0.001115674,0.006154031,0.03740377,0.008109644],"genre_scores_gemma":[0.8574164,0.001157703,0.1306345,0.0004899202,0.0001184837,0.0003328031,0.008253684,0.0002077409,0.001388786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005974871,"threshold_uncertainty_score":0.01314497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08508419509513357,"score_gpt":0.3952205903199808,"score_spread":0.3101363952248473,"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."}}