{"id":"W3180230246","doi":"10.1145/3404835.3463238","title":"Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":328,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Python (programming language); Computer science; Information retrieval; Scripting language; Ranking (information retrieval); Relevance (law); Data mining; Programming language","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":[0.003999939,0.0001099808,0.0001674735,0.0001251356,0.0004387323,0.0007129094,0.0002096306,0.0000543123,0.0007258991],"category_scores_gemma":[0.004445798,0.00008853821,0.00002031685,0.0005870999,0.0002390889,0.001157405,0.0002339328,0.0001264079,0.0001466186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003834233,"about_ca_system_score_gemma":0.0002527562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001817631,"about_ca_topic_score_gemma":0.00006721326,"domain_scores_codex":[0.9978577,0.0002680319,0.0003237732,0.000581202,0.0005731303,0.0003961609],"domain_scores_gemma":[0.9978204,0.0003997255,0.0001035262,0.0007649151,0.0008028022,0.0001086823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004925441,0.0000466356,0.002329497,0.0001530949,0.000005310691,0.00001558212,0.001516199,0.001596376,0.9802655,0.008888422,0.004175745,0.0005150838],"study_design_scores_gemma":[0.0009848892,0.0004114766,0.01305356,0.00006398771,0.00001636365,0.0002359805,0.001549993,0.005113152,0.9519573,0.002972253,0.02332643,0.0003145855],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813969,0.00002913627,0.01064666,0.002497767,0.00027608,0.0005086744,0.00001987216,0.0001560455,0.004468837],"genre_scores_gemma":[0.7949194,0.00002981129,0.1977341,0.0003209636,0.0001862575,0.0001077546,0.00004697994,0.00002634916,0.006628355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1870874,"threshold_uncertainty_score":0.7948086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07509590162092218,"score_gpt":0.3699382741183271,"score_spread":0.2948423724974049,"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."}}