{"id":"W6929316190","doi":"10.48448/gwr9-gg78","title":"Knowledge Corpus Error in Question Answering","year":2023,"lang":"en","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Question answering; Context (archaeology); String (physics); Corpus linguistics; Text corpus; Natural language; Error detection and correction","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":[0.0131892,0.000819827,0.0009845706,0.001697612,0.001595307,0.002492089,0.001908337,0.002332798,0.003604124],"category_scores_gemma":[0.1013423,0.0004924416,0.0005760029,0.001937405,0.002268902,0.005190289,0.004338873,0.002324351,0.001892452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001514515,"about_ca_system_score_gemma":0.001623478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006054285,"about_ca_topic_score_gemma":0.003899543,"domain_scores_codex":[0.9778622,0.01334955,0.001080448,0.003588353,0.003647229,0.0004721193],"domain_scores_gemma":[0.8945217,0.08512936,0.002620048,0.01093666,0.006208257,0.0005839202],"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":[0.001663229,0.0007118976,0.02193478,0.003029372,0.0003560597,0.001345956,0.008948293,0.06223062,0.02242156,0.04975729,0.06940915,0.7581918],"study_design_scores_gemma":[0.00040564,0.001083207,0.01603153,0.001165794,0.000446525,0.00393849,0.004110117,0.5439379,0.1193531,0.1572091,0.1520318,0.0002868559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3722548,0.01317205,0.5413419,0.009179627,0.001302904,0.0007752744,0.00317912,0.02145521,0.0373391],"genre_scores_gemma":[0.8334759,0.0009578009,0.1507234,0.001928323,0.0002973932,0.0002879579,0.004772208,0.001694306,0.005862602],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0131892,"threshold_uncertainty_score":0.06975204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07692308803523491,"score_gpt":0.3824865396209146,"score_spread":0.3055634515856797,"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."}}