{"id":"W2949286092","doi":"10.48550/arxiv.1506.00717","title":"Assessing Efficiency-Effectiveness Tradeoffs in Multi-Stage Retrieval Systems Without Using Relevance Judgments","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Computer science; Relevance (law); Information retrieval; Set (abstract data type); Filter (signal processing); Matching (statistics); Data mining; Categorization; Quality (philosophy); Sequence (biology); Range (aeronautics); Artificial intelligence; Statistics; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02296027,0.001386708,0.002150174,0.004231206,0.001110674,0.00348787,0.001435317,0.002325565,0.00116849],"category_scores_gemma":[0.07727336,0.0009094515,0.0007470538,0.003249244,0.001269579,0.0069545,0.001748695,0.00128071,0.0005859494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002765786,"about_ca_system_score_gemma":0.001200256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004094264,"about_ca_topic_score_gemma":0.004763306,"domain_scores_codex":[0.9823524,0.007724029,0.001750659,0.002367665,0.005003273,0.0008020528],"domain_scores_gemma":[0.8835682,0.09905641,0.005257467,0.005685843,0.005262784,0.001169358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005369383,0.002635249,0.0707894,0.001512275,0.001100823,0.0004210416,0.001813084,0.4236527,0.1099898,0.008410272,0.00294892,0.3713571],"study_design_scores_gemma":[0.0002266444,0.002832216,0.03703186,0.00004248114,0.000271634,0.0002975122,0.0005020766,0.9115598,0.03761296,0.008488851,0.0009506345,0.0001833389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8374027,0.002441375,0.1541967,0.0005134387,0.00003559663,0.000465923,0.0002186545,0.001345005,0.003380579],"genre_scores_gemma":[0.919992,0.0002429317,0.07816155,0.00007529549,0.00003359788,0.0001963325,0.0002697091,0.0001316699,0.0008971242],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02296027,"threshold_uncertainty_score":0.121427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3072605242575094,"score_gpt":0.3051748975643966,"score_spread":0.002085626693112796,"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."}}