{"id":"W3093924713","doi":"10.1145/3340531.3411915","title":"Offline Evaluation by Maximum Similarity to an Ideal Ranking","year":2020,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ranking (information retrieval); Relevance (law); Learning to rank; Similarity (geometry); Correctness; Computer science; Rank (graph theory); Ideal (ethics); Information retrieval; Set (abstract data type); Measure (data warehouse); Data mining; Ranking SVM; Similarity measure; Artificial intelligence; Mathematics; Algorithm","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":[0.0006675249,0.00006993827,0.00007849478,0.00003852061,0.00009679701,0.000188119,0.0004692226,0.0000331087,0.0002764653],"category_scores_gemma":[0.00009182973,0.0000597395,0.00002588965,0.0003913742,0.000007933219,0.0009188265,0.0001463981,0.00009022823,0.0002260872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000308335,"about_ca_system_score_gemma":0.00007029127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003109055,"about_ca_topic_score_gemma":0.000004651495,"domain_scores_codex":[0.9987134,0.00006388426,0.0001900138,0.0001888072,0.0006686948,0.0001752432],"domain_scores_gemma":[0.9992934,0.00001696714,0.00002920294,0.0001925564,0.0002277808,0.0002400186],"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":[0.00007493817,0.0001516825,0.001075267,0.00002577767,0.00001173185,0.000006185167,0.008515259,0.002073902,0.01937802,0.02402032,0.04626562,0.8984013],"study_design_scores_gemma":[0.0004821694,0.0002591485,0.001997224,0.000002346271,0.000004578058,0.000001089306,0.00005478674,0.9719374,0.01027399,0.0006944087,0.014132,0.0001608245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08382911,0.000006746639,0.8970556,0.01537138,0.00009797385,0.0003515034,0.000005608074,0.0001935664,0.00308854],"genre_scores_gemma":[0.956758,9.566559e-7,0.03058552,0.01246826,0.00005819208,0.00001208051,0.00003035239,0.000003707585,0.0000829891],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9698635,"threshold_uncertainty_score":0.3027101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06998699835595117,"score_gpt":0.3268742644032515,"score_spread":0.2568872660473003,"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."}}