{"id":"W2951780535","doi":"10.48550/arxiv.1809.07428","title":"Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Ranking (information retrieval); Recommender system; Distillation; Computer science; Machine learning; Information retrieval; Chromatography; Chemistry","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":[0.003595999,0.001534714,0.002632429,0.001167368,0.0007834201,0.001566746,0.003028008,0.002213467,0.002856637],"category_scores_gemma":[0.01360761,0.00118033,0.001324494,0.001659622,0.001023066,0.003825025,0.002067274,0.003732509,0.002299766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001103385,"about_ca_system_score_gemma":0.001601346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007338101,"about_ca_topic_score_gemma":0.011354,"domain_scores_codex":[0.9978681,0.0009360044,0.0001261923,0.0005516852,0.0003542075,0.0001637614],"domain_scores_gemma":[0.9933518,0.003596415,0.0003770142,0.001641914,0.0008365652,0.0001962873],"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":[0.0004835756,0.000476702,0.003864384,0.0003625506,0.0003145,0.0001275987,0.0002223419,0.5119838,0.005773012,0.02573528,0.0120087,0.4386475],"study_design_scores_gemma":[0.00002477508,0.0000698877,0.0001221146,0.000007357592,0.0000125317,0.00002129398,0.000007864218,0.9919652,0.000759071,0.006342431,0.0006546875,0.00001281437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02041279,0.0005597399,0.9749521,0.0004641292,0.00006341405,0.00006742033,0.000241493,0.002454389,0.0007845543],"genre_scores_gemma":[0.4110465,0.0004177231,0.5808484,0.0005859896,0.000241864,0.0003017506,0.001701356,0.0002986903,0.004557692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007338101,"threshold_uncertainty_score":0.01901764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09029474052494575,"score_gpt":0.193935070073426,"score_spread":0.1036403295484802,"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."}}