{"id":"W4380687254","doi":"10.48550/arxiv.2306.07471","title":"Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Sophistication; Popularity; Artificial intelligence; Benchmark (surveying); CLARITY; Optimal distinctiveness theory; Publication; Information retrieval; Data science; Political science; Geography; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02535726,0.004585448,0.003058648,0.008010868,0.002508166,0.0065655,0.01174947,0.005982025,0.02966528],"category_scores_gemma":[0.1041234,0.002264028,0.002981073,0.007931211,0.001837102,0.01106495,0.01035907,0.005758002,0.05362399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003223302,"about_ca_system_score_gemma":0.005712195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01859567,"about_ca_topic_score_gemma":0.02816859,"domain_scores_codex":[0.9750993,0.009736231,0.002420653,0.003634411,0.007613852,0.001495552],"domain_scores_gemma":[0.9278285,0.01511342,0.002006528,0.03696998,0.01546552,0.00261598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005839962,0.0007444975,0.001448525,0.001054286,0.0001895641,0.0001679187,0.0002358718,0.008164966,0.00193392,0.007412361,0.8827067,0.09535734],"study_design_scores_gemma":[0.00255748,0.001714172,0.005927099,0.001451435,0.0002932872,0.0009606311,0.0009329345,0.2246513,0.03067315,0.04738578,0.6828341,0.0006185767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.03093848,0.005465852,0.2495899,0.005191107,0.003825453,0.002808344,0.1953129,0.4614717,0.0453964],"genre_scores_gemma":[0.0636566,0.001239807,0.2518913,0.001809619,0.0004263009,0.004209206,0.625571,0.03620281,0.01499331],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02966528,"threshold_uncertainty_score":0.1341036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3203948243550147,"score_gpt":0.2444573021915565,"score_spread":0.07593752216345812,"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."}}