{"id":"W3200660033","doi":"10.1145/3459637.3482159","title":"Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Leverage (statistics); Embedding; Classifier (UML); Artificial intelligence","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":[0.00349574,0.001100161,0.001618298,0.002261295,0.000375614,0.001503765,0.001019321,0.001449414,0.001477198],"category_scores_gemma":[0.01999981,0.0003405623,0.0006276222,0.001708443,0.0007097248,0.003021186,0.0005696217,0.0009472002,0.001437212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009137,"about_ca_system_score_gemma":0.001003572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003997492,"about_ca_topic_score_gemma":0.004892233,"domain_scores_codex":[0.9976121,0.0005646728,0.0002877939,0.0005334548,0.0006834903,0.0003184729],"domain_scores_gemma":[0.9888725,0.00870396,0.0006141895,0.0007412201,0.0008152068,0.000253069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002676287,0.001488455,0.04930082,0.00129837,0.0004295679,0.0004961125,0.0002307289,0.239355,0.03401404,0.004989871,0.02047305,0.6452476],"study_design_scores_gemma":[0.0001200738,0.0006407763,0.00472546,0.00002660911,0.000128137,0.0003790581,0.0001019338,0.9785814,0.009673897,0.004133691,0.001452455,0.00003647374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.746518,0.0130695,0.2247865,0.001635408,0.0001369386,0.0006097508,0.001666941,0.003862241,0.007714709],"genre_scores_gemma":[0.9421868,0.001484815,0.05200191,0.0002875548,0.0001436655,0.0001764165,0.001806402,0.0001899889,0.001722453],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003997492,"threshold_uncertainty_score":0.01848745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03843103745758954,"score_gpt":0.2808800311148777,"score_spread":0.2424489936572882,"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."}}