{"id":"W4416712105","doi":"10.48550/arxiv.2509.02558","title":"Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Natural Sciences and Engineering Research Council of Canada; Ministry of Science and ICT, South Korea","keywords":"Benchmark (surveying); Construct (python library); Range (aeronautics); Query expansion; Baseline (sea); Search engine; Question answering","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":[0.02487151,0.004105805,0.002949324,0.008804847,0.003591923,0.007275417,0.006300187,0.004467979,0.009941374],"category_scores_gemma":[0.0883854,0.001214729,0.002647769,0.006841224,0.00257378,0.01011114,0.006578918,0.004875656,0.01301583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00355228,"about_ca_system_score_gemma":0.004772633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02076359,"about_ca_topic_score_gemma":0.04141625,"domain_scores_codex":[0.9736158,0.01164092,0.002619979,0.003655246,0.007432435,0.00103567],"domain_scores_gemma":[0.9685171,0.01088961,0.001083922,0.01252163,0.006162312,0.0008254767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002148638,0.00161814,0.006929344,0.00499349,0.001348053,0.0003191647,0.0007235582,0.06072548,0.01350467,0.01428391,0.4170661,0.4763395],"study_design_scores_gemma":[0.002251367,0.002873239,0.00967369,0.001041813,0.0007595841,0.001055356,0.001365507,0.6760172,0.05469319,0.05837093,0.1912973,0.0006008662],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1738319,0.06060304,0.4272795,0.01149781,0.005927576,0.00388234,0.07683957,0.1911298,0.04900846],"genre_scores_gemma":[0.3254054,0.003726064,0.4778844,0.003839044,0.001089489,0.002500356,0.1607452,0.01206818,0.01274196],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02487151,"threshold_uncertainty_score":0.1315347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05225261252582453,"score_gpt":0.2928951518894453,"score_spread":0.2406425393636207,"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."}}