{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003052225,0.0001290624,0.000158783,0.000131112,0.0002061018,0.0003789448,0.0009382238,0.00007707515,0.000002757103],"category_scores_gemma":[0.00006725506,0.0001268115,0.00005698824,0.0002405743,0.00001937624,0.0007870783,0.0001244705,0.0001406828,0.00000292346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009301017,"about_ca_system_score_gemma":0.00008101181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006268908,"about_ca_topic_score_gemma":0.00006229705,"domain_scores_codex":[0.9989051,0.00004693599,0.0002276166,0.000425215,0.0001652356,0.0002298553],"domain_scores_gemma":[0.9991866,0.0001762937,0.00006704377,0.0003927174,0.0001377793,0.00003950655],"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":[0.0002077556,0.000144472,0.009505508,0.0003677538,0.0001502461,0.00003867142,0.01219083,0.016908,0.005330191,0.2959854,0.002172564,0.6569986],"study_design_scores_gemma":[0.002450849,0.0001799618,0.005032373,0.001269363,0.00002655938,0.000003850163,0.0002512192,0.7893125,0.1531973,0.0437888,0.003779505,0.000707628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1888278,0.0000748642,0.8076379,0.0007637719,0.001271992,0.0003101403,9.32293e-7,0.0001507862,0.0009617907],"genre_scores_gemma":[0.9924954,0.000004087965,0.005065135,0.00167641,0.0001188391,0.00004758635,0.000001688856,0.000008072475,0.0005827354],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8036677,"threshold_uncertainty_score":0.5171224,"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."}}