{"id":"W2113557293","doi":"","title":"Enhanced Web Retrieval Task","year":2009,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Task (project management); Information retrieval; World Wide Web; Search engine; Adversarial information retrieval; Human–computer information retrieval; Cognitive models of information retrieval; Engineering","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":[0.0001750206,0.00006497073,0.00006958844,0.00007032823,0.00007878963,0.0001371095,0.0004842116,0.00003663844,0.0001274255],"category_scores_gemma":[0.00002882573,0.00005006537,0.00004085158,0.00041472,0.00001276639,0.0006995437,0.00005058079,0.00008749149,0.0006793776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002137825,"about_ca_system_score_gemma":0.00006717395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001131168,"about_ca_topic_score_gemma":3.09467e-7,"domain_scores_codex":[0.9991816,0.0000146047,0.0001525089,0.0001266689,0.0003148288,0.0002098025],"domain_scores_gemma":[0.9994944,0.00001594929,0.00002811295,0.0002748891,0.00009560323,0.00009100715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003946467,0.0001323538,0.00002723587,0.000004961355,0.000007328001,0.00001602841,0.001063049,0.00001491391,0.2141258,0.5297492,0.008871718,0.2459479],"study_design_scores_gemma":[0.001882386,0.001203826,0.01588072,0.00001900521,0.000007109128,0.00003974013,0.00007794475,0.09226725,0.8166587,0.009303893,0.06180784,0.0008516276],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1142518,0.00001493624,0.7461686,0.003225945,0.0002640766,0.0001666754,0.00000126502,0.0004843656,0.1354224],"genre_scores_gemma":[0.9862441,0.000006195412,0.008481215,0.001783196,0.00002906898,5.927291e-7,0.000001444878,0.000001186402,0.003452948],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8719923,"threshold_uncertainty_score":0.8732251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01397439744934049,"score_gpt":0.2637368972764694,"score_spread":0.2497624998271289,"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."}}