{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001732178,0.0001033513,0.0002053485,0.0001573848,0.00004709691,0.00006683676,0.000702651,0.00004381583,0.000009647367],"category_scores_gemma":[0.0003240632,0.00008054949,0.0000538241,0.0009619541,0.00001722236,0.0001930333,0.0002060698,0.0002499562,0.000005330362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004631685,"about_ca_system_score_gemma":0.00005959748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002883017,"about_ca_topic_score_gemma":0.0002825758,"domain_scores_codex":[0.9981437,0.0006267572,0.0002953245,0.0003842765,0.0002807546,0.0002692353],"domain_scores_gemma":[0.9988805,0.0006057391,0.00003708577,0.0004151253,0.00003741639,0.00002411691],"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":[0.00004234098,0.000882456,0.04112286,0.0002451479,0.00001817351,0.001589356,0.1054595,0.5957379,0.07226651,0.06805886,0.000006157672,0.1145707],"study_design_scores_gemma":[0.003212869,0.0001632434,0.1004972,0.0004390267,0.000004956078,0.00003112184,0.00461111,0.8672521,0.02159172,0.0003129957,0.001455852,0.0004277977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3736149,0.00009018421,0.6242559,0.000334271,0.0000982842,0.0001778271,1.452739e-7,0.00002767038,0.001400852],"genre_scores_gemma":[0.9671732,0.000005049912,0.03229797,0.0003620128,0.000008811488,0.00001725236,6.379556e-7,0.000005302925,0.0001297512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5935583,"threshold_uncertainty_score":0.3284713,"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."}}