{"id":"W2113651401","doi":"10.1145/2362724.2362735","title":"Human question answering performance using an interactive document retrieval system","year":2012,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Question answering; Computer science; Information retrieval; Document retrieval; Human–computer information retrieval; World Wide Web; Search engine","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":[],"consensus_categories":[],"category_scores_codex":[0.0006150091,0.0001072976,0.00011935,0.0000880533,0.0001654318,0.0001664332,0.0003020746,0.00004463707,0.000007288181],"category_scores_gemma":[0.00000794333,0.00009265715,0.00002895746,0.0001712867,0.00001215296,0.002892545,0.0001063161,0.00007922674,0.0000603573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002710964,"about_ca_system_score_gemma":0.00002161029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002846572,"about_ca_topic_score_gemma":0.000006136316,"domain_scores_codex":[0.9989678,0.00009757982,0.0002021918,0.0002022182,0.0002211458,0.0003090208],"domain_scores_gemma":[0.9993344,0.0000125399,0.00008897505,0.0003511357,0.00005936958,0.0001535779],"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":[0.0001999825,0.0008877984,0.1067538,0.0009709311,0.0001925591,0.00004785234,0.02744317,0.003054114,0.3467636,0.4836766,0.000374324,0.02963526],"study_design_scores_gemma":[0.001742402,0.001162824,0.08862379,0.001027919,0.00004173716,0.000764904,0.003553325,0.512641,0.3873403,0.000260926,0.001154691,0.001686198],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8319179,0.00003197516,0.1617191,0.000007701313,0.001261935,0.000132517,2.445696e-7,0.0002654196,0.004663237],"genre_scores_gemma":[0.9895801,3.978665e-7,0.009920151,0.00002298277,0.0003677135,0.000002750772,0.000001666108,0.000006616364,0.00009763809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5095869,"threshold_uncertainty_score":0.3778449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02960798217115513,"score_gpt":0.2972875870218249,"score_spread":0.2676796048506698,"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."}}