{"id":"W6967295409","doi":"10.48448/s7sp-2t63","title":"EWEK-QA : Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systems","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Baseline (sea); Heuristics; Question answering; Set (abstract data type); Knowledge base; Pipeline (software); Graph","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003035136,0.0005607708,0.0005388497,0.003193293,0.0003043355,0.0005833355,0.0005803516,0.0003236658,0.00004937501],"category_scores_gemma":[0.0007602387,0.000525948,0.0001076657,0.003462822,0.001328621,0.0001336884,0.0001164164,0.0003317751,0.0009608879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006104992,"about_ca_system_score_gemma":0.001448599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001177202,"about_ca_topic_score_gemma":0.0003690034,"domain_scores_codex":[0.9959798,0.0001112935,0.0005767042,0.001528883,0.001024842,0.0007784361],"domain_scores_gemma":[0.997826,0.000270832,0.0004171004,0.0006106174,0.0005759982,0.0002994259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005149876,0.001163249,0.0000789695,0.01227472,0.0003561049,0.00003333441,0.002821176,0.03259528,0.6669518,0.06285783,0.2133258,0.007026738],"study_design_scores_gemma":[0.001635737,0.0004258362,0.00002791696,0.005034946,0.0002608332,0.00001111943,0.0005374972,0.9239209,0.005888821,0.0005899218,0.0603068,0.0013597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03272086,0.05109096,0.4805144,0.0005765671,0.03570722,0.01970152,0.005579044,0.01080509,0.3633043],"genre_scores_gemma":[0.888116,0.00004187345,0.007748273,0.00003642532,0.001041215,0.0002284157,0.0002461824,0.001500573,0.101041],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8913256,"threshold_uncertainty_score":0.999817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02287320731443135,"score_gpt":0.3219680933088861,"score_spread":0.2990948859944548,"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."}}