{"id":"W4411171689","doi":"10.1109/access.2025.3578497","title":"Unsupervised Context-Linking Retriever for Question Answering on Long Narrative Books","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universiti Kebangsaan Malaysia; Ministry of Higher Education, Malaysia","keywords":"Question answering; Computer science; Context (archaeology); Narrative; Information retrieval; Labrador Retriever; Natural language processing; Artificial intelligence; World Wide Web; Linguistics; Medicine; History","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001039105,0.001648575,0.001098336,0.001528004,0.0006219264,0.0009095503,0.001708846,0.001463251,0.006648175],"category_scores_gemma":[0.005535088,0.0003474891,0.0009924627,0.0009162513,0.0004016064,0.002831676,0.001516957,0.001479322,0.007480829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005378143,"about_ca_system_score_gemma":0.0009401727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003598335,"about_ca_topic_score_gemma":0.006679382,"domain_scores_codex":[0.9989813,0.0002998657,0.00006834976,0.0003864237,0.0002025059,0.00006159735],"domain_scores_gemma":[0.9984034,0.0008374145,0.0001068321,0.0002684263,0.0003265985,0.00005735305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007704417,0.0004508804,0.002068795,0.001128559,0.00019864,0.001151098,0.000975828,0.04644255,0.08386359,0.00481291,0.03536533,0.8227715],"study_design_scores_gemma":[0.0001495601,0.0006955223,0.002737724,0.00009163482,0.0001952763,0.001049809,0.0007280928,0.8536519,0.1004466,0.00879171,0.03135622,0.0001058573],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.135486,0.004478719,0.7907208,0.0004657517,0.0002650815,0.0006280232,0.004100028,0.05504699,0.008808639],"genre_scores_gemma":[0.3575554,0.001304863,0.6037565,0.0007206828,0.0003331537,0.0006026985,0.01916109,0.001530032,0.01503553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006648175,"threshold_uncertainty_score":0.0222404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04394293215499163,"score_gpt":0.338799564082537,"score_spread":0.2948566319275454,"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."}}