{"id":"W7106806816","doi":"10.48448/14az-j127","title":"Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Temporality; Evergreen; Trustworthiness; Classifier (UML); Benchmark (surveying); Hallucinating; Question answering; Key (lock)","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":[0.004342263,0.001170583,0.0006757762,0.00210534,0.001139053,0.002369645,0.001455978,0.001750794,0.01040094],"category_scores_gemma":[0.02070688,0.0002925452,0.001182903,0.00109912,0.0008411818,0.005094699,0.003540122,0.002477858,0.005562047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001490893,"about_ca_system_score_gemma":0.002006284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01405253,"about_ca_topic_score_gemma":0.02064724,"domain_scores_codex":[0.9973061,0.001087345,0.0001938832,0.0008214094,0.0004172728,0.0001739215],"domain_scores_gemma":[0.9910953,0.00447644,0.0003551756,0.002255593,0.001442752,0.0003747881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001432724,0.0007968242,0.0466411,0.002125137,0.0003172832,0.000561605,0.004126415,0.02095619,0.02691293,0.0189878,0.2432107,0.6339314],"study_design_scores_gemma":[0.0002954552,0.0005782397,0.02676379,0.0004436637,0.0002565229,0.0009618873,0.00295646,0.6268204,0.03715473,0.05737615,0.2461629,0.0002298253],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.4164495,0.009362385,0.3533621,0.009896155,0.001343775,0.001202002,0.06533867,0.09151419,0.05153128],"genre_scores_gemma":[0.744783,0.0005589977,0.1585584,0.002351509,0.0002451004,0.0003481319,0.07882095,0.001772557,0.01256141],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01405253,"threshold_uncertainty_score":0.03479463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04457943810939103,"score_gpt":0.3618385245303028,"score_spread":0.3172590864209118,"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."}}