{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006240576,0.00064595,0.0008203131,0.001085247,0.0005450519,0.00193804,0.0007244046,0.001627227,0.004525133],"category_scores_gemma":[0.03296662,0.0002254164,0.0004430429,0.0007212775,0.0004961889,0.001465156,0.0009985432,0.0005761646,0.002088635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000452965,"about_ca_system_score_gemma":0.000460046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003822442,"about_ca_topic_score_gemma":0.001771664,"domain_scores_codex":[0.9930273,0.003588427,0.0007073941,0.001173413,0.001172275,0.000331171],"domain_scores_gemma":[0.9413525,0.04756584,0.0015615,0.003239031,0.005090041,0.001191025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01536363,0.004399738,0.1229484,0.003033734,0.001369177,0.0009241732,0.02662914,0.01872773,0.2450454,0.002447393,0.01764567,0.5414658],"study_design_scores_gemma":[0.001533191,0.03337198,0.4068497,0.0004329063,0.001765373,0.003494996,0.008381955,0.2194667,0.2694647,0.00329744,0.0507218,0.001219258],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787243,0.0009231406,0.01114214,0.0001788126,0.00005515187,0.000192532,0.0004478749,0.001366244,0.006969669],"genre_scores_gemma":[0.9887057,0.0001925763,0.007950667,0.0001370722,0.00004027729,0.0001038687,0.0005799955,0.0000935049,0.002196326],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006240576,"threshold_uncertainty_score":0.03300369,"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."}}