{"id":"W3213719910","doi":"10.18653/v1/2021.sustainlp-1.8","title":"Learning to Rank in the Age of Muppets: Effectiveness–Efficiency Tradeoffs in Multi-Stage Ranking","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; University of Waterloo; Compute Canada","keywords":"Transformer; Computer science; Inference; Machine learning; Artificial intelligence; Ranking (information retrieval); Learning to rank; Recall; Engineering; Voltage","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":[0.01096834,0.001215353,0.002180249,0.002273684,0.001198278,0.003193971,0.002293048,0.002148419,0.004113747],"category_scores_gemma":[0.03747265,0.0007792409,0.0007805121,0.001910467,0.001183242,0.009069952,0.001885824,0.002420317,0.003777696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008407583,"about_ca_system_score_gemma":0.001166902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003002735,"about_ca_topic_score_gemma":0.006033176,"domain_scores_codex":[0.9956201,0.002087778,0.0002771797,0.0005569592,0.001047301,0.0004107183],"domain_scores_gemma":[0.9718533,0.01953201,0.0009453283,0.004880185,0.002073337,0.0007158205],"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":[0.001470842,0.0005605852,0.009157177,0.000535181,0.000231907,0.0003970471,0.0005192336,0.1760619,0.01222325,0.05643506,0.02311442,0.7192935],"study_design_scores_gemma":[0.00009799196,0.0007013599,0.00159074,0.00004450445,0.00009178081,0.000653176,0.0001939845,0.9294857,0.01053295,0.05136373,0.005184548,0.00005962076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1486165,0.008619179,0.8198367,0.003423622,0.0003277373,0.0002575046,0.0006238531,0.005328234,0.01296673],"genre_scores_gemma":[0.6845441,0.001960848,0.3008749,0.0004167045,0.0005594051,0.0001086679,0.0008815965,0.0005660146,0.01008778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01096834,"threshold_uncertainty_score":0.05800682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04921672770056092,"score_gpt":0.3025682367087625,"score_spread":0.2533515090082016,"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."}}