{"id":"W4404366193","doi":"10.1007/s10115-024-02269-2","title":"An evidence-based approach for open-domain question answering","year":2024,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Question answering; Information retrieval; Relevance (law); Open domain; Benchmark (surveying); Context (archaeology); Graph; Construct (python library); Domain (mathematical analysis); Rank (graph theory); Knowledge graph; Artificial intelligence; Natural language processing; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.008876652,0.001167543,0.002158484,0.008564285,0.001715219,0.005490672,0.004875691,0.004410685,0.007717763],"category_scores_gemma":[0.04679403,0.00119981,0.003059961,0.005972971,0.001835754,0.008595634,0.005788034,0.004365994,0.002119573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001731156,"about_ca_system_score_gemma":0.003096782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005190116,"about_ca_topic_score_gemma":0.008744657,"domain_scores_codex":[0.9900252,0.004296345,0.001157671,0.001550315,0.002656766,0.0003137636],"domain_scores_gemma":[0.9604143,0.03180639,0.001133372,0.002387467,0.003580495,0.0006781162],"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":[0.0007208426,0.0009017002,0.004757807,0.001438792,0.0007180625,0.0007859999,0.001862717,0.04780253,0.007245023,0.194261,0.01374832,0.7257572],"study_design_scores_gemma":[0.0001339999,0.0001221288,0.001280021,0.0003226848,0.000422012,0.0004457294,0.0004967919,0.6428141,0.004442581,0.3325281,0.01689943,0.00009245564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003533508,0.0006947982,0.9912568,0.001207414,0.00006746026,0.0002094559,0.0005077625,0.000703431,0.001819313],"genre_scores_gemma":[0.143535,0.0006039762,0.8507194,0.0003830799,0.0002351769,0.0004095359,0.001882033,0.0001290708,0.002102688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008876652,"threshold_uncertainty_score":0.0469448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05172166446128868,"score_gpt":0.3110074057323632,"score_spread":0.2592857412710745,"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."}}