{"id":"W4254133819","doi":"10.1145/564437.564448","title":"The impact of corpus size on question answering performance","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Terabyte; Question answering; Computer science; Information retrieval; Natural language processing; World Wide Web","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":[0.001507361,0.0001613235,0.0001609077,0.0003368804,0.0002565824,0.0003405235,0.001792656,0.00007854427,0.00002312962],"category_scores_gemma":[0.002692455,0.0001014449,0.00004516301,0.0005136988,0.0001643432,0.001724714,0.0006218557,0.0004427251,0.00002057164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002397263,"about_ca_system_score_gemma":0.0001721797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004209818,"about_ca_topic_score_gemma":0.000001706433,"domain_scores_codex":[0.9973925,0.00002473778,0.0006460777,0.0002086201,0.001380863,0.0003471609],"domain_scores_gemma":[0.9972218,0.0004705373,0.0003357947,0.0002181589,0.001660721,0.00009295376],"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":[0.002331925,0.0007857654,0.1211496,0.0004623794,0.0002401816,0.000002057939,0.02753051,0.0031611,0.003993841,0.5295585,0.003790927,0.3069932],"study_design_scores_gemma":[0.002537676,0.002590909,0.2864212,0.001679067,0.000003250796,0.00002897676,0.001741421,0.612369,0.07232685,0.0153591,0.004237874,0.0007046605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893844,0.00002403999,0.0004172771,0.001540746,0.0002209153,0.0003666226,0.000009963254,0.00002878362,0.008007216],"genre_scores_gemma":[0.9974054,0.0003112346,0.001840938,0.00005016592,0.00002507624,0.00001943349,0.000002037717,0.000004277484,0.0003414784],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6092079,"threshold_uncertainty_score":0.4136803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06702928582532092,"score_gpt":0.3316985989911562,"score_spread":0.2646693131658353,"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."}}