{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001210456,0.0000856109,0.0001100897,0.000149726,0.0001196312,0.001845844,0.0004273066,0.00005426203,5.0966e-7],"category_scores_gemma":[0.00002512906,0.00007362427,0.00002218903,0.0001936553,0.000009383433,0.01128053,0.00007504325,0.00005224024,0.00001958499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000527654,"about_ca_system_score_gemma":0.0001099939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002848829,"about_ca_topic_score_gemma":9.457763e-7,"domain_scores_codex":[0.9992369,0.00005944523,0.0003044223,0.0001707927,0.0001025174,0.0001259299],"domain_scores_gemma":[0.999428,0.00007041746,0.00005019323,0.000268207,0.0001182971,0.00006486161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001009465,0.00002391847,0.0001013404,0.001936985,0.00001189509,3.792265e-7,0.007864183,0.009213188,0.0002362936,0.8185205,0.0009055567,0.1611756],"study_design_scores_gemma":[0.0001488222,0.00005701971,0.00002817165,0.0003197317,0.000002458933,0.00000698671,0.0001819831,0.951762,0.0001058117,0.000171877,0.0471163,0.00009885951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001002216,0.002344789,0.9908417,0.00008856031,0.0006674958,0.0006330656,0.000003135685,0.0001950808,0.004223892],"genre_scores_gemma":[0.9469354,0.00001737998,0.05247855,0.00006478777,0.0001597361,0.0002280346,0.00002250986,0.000004807296,0.00008877592],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9459332,"threshold_uncertainty_score":0.9991903,"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."}}