{"id":"W2039447541","doi":"10.1145/564376.564448","title":"The impact of corpus size on question answering performance","year":2002,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Terabyte; Question answering; Computer science; Information retrieval; World Wide Web; Natural language processing","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":[],"consensus_categories":[],"category_scores_codex":[0.0001697943,0.00004766377,0.00005832432,0.00002281386,0.00009071308,0.00005974135,0.000363861,0.00001248587,0.00002306771],"category_scores_gemma":[0.00004994874,0.00002566378,0.00004888967,0.0002036222,0.0000187651,0.0001863676,0.0000447627,0.00004305907,0.00004638056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001536615,"about_ca_system_score_gemma":0.000005773703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134263,"about_ca_topic_score_gemma":0.000003509957,"domain_scores_codex":[0.9995749,0.00001999076,0.00009138564,0.0001018614,0.0001093554,0.000102506],"domain_scores_gemma":[0.9994258,0.0001229685,0.00004329389,0.0003596525,0.00002375171,0.0000245544],"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":[0.000008366389,0.0001103427,0.02390298,0.000007407549,0.00007127712,0.000003071069,0.0004960637,0.00791045,0.002816969,0.009970454,0.006116265,0.9485863],"study_design_scores_gemma":[0.00007748289,0.0002059328,0.04350453,0.00001769648,0.00000281226,0.000003562292,0.000006867611,0.9532937,0.002321785,0.00004865432,0.0004526391,0.0000643448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9737213,0.00007421481,0.01757686,0.0003828239,0.00006578366,0.00002418457,0.000001100303,0.00006972318,0.008084022],"genre_scores_gemma":[0.9969836,0.0001013475,0.0016996,0.00002067436,0.00001583944,8.563716e-7,2.447425e-7,0.000001615159,0.001176204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.948522,"threshold_uncertainty_score":0.1046539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01666226182163508,"score_gpt":0.2518497277000022,"score_spread":0.2351874658783671,"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."}}