{"id":"W4409183155","doi":"10.1007/978-3-031-88714-7_13","title":"LiT and Lean: Distilling Listwise Rerankers Into Encoder-Decoder Models","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Encoder; Lean manufacturing; Parallel computing; Manufacturing engineering; Operating system; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003326863,0.003041838,0.002213491,0.002664504,0.0009440221,0.002724384,0.003872732,0.003204578,0.01490874],"category_scores_gemma":[0.01211064,0.001820877,0.001826643,0.00276914,0.0008367363,0.005314312,0.001910128,0.004303505,0.01256603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001591204,"about_ca_system_score_gemma":0.002933426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01458166,"about_ca_topic_score_gemma":0.04024341,"domain_scores_codex":[0.997906,0.0008488616,0.000136435,0.0005672764,0.0003836972,0.0001578431],"domain_scores_gemma":[0.9921154,0.005749367,0.0002115465,0.0008477611,0.0009065455,0.0001692945],"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":[0.0005043013,0.0002287468,0.0005261464,0.0003182872,0.0002148242,0.0001963132,0.0001534783,0.1347315,0.004320542,0.0142784,0.04622496,0.7983025],"study_design_scores_gemma":[0.0000739107,0.00009856625,0.00008448734,0.00004743868,0.00005829318,0.00005383608,0.00003471516,0.9602934,0.003968216,0.03070183,0.004551111,0.00003425622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005872371,0.001113172,0.9582705,0.000370242,0.0003038182,0.0001448413,0.0014518,0.03050596,0.001967304],"genre_scores_gemma":[0.09707882,0.0008768843,0.8687194,0.0006845996,0.0004220108,0.0004002501,0.009393489,0.003910079,0.01851446],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01490874,"threshold_uncertainty_score":0.04987466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01996515089114864,"score_gpt":0.2498491505422226,"score_spread":0.229883999651074,"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."}}