{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005286136,0.002399837,0.00196223,0.00268932,0.001003484,0.004168073,0.005796676,0.001273889,0.0532053],"category_scores_gemma":[0.02430538,0.001633831,0.002550837,0.003367848,0.001232187,0.006473618,0.005561409,0.004544049,0.05830536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205795,"about_ca_system_score_gemma":0.004029183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004599178,"about_ca_topic_score_gemma":0.005502629,"domain_scores_codex":[0.9960763,0.001031473,0.0004800583,0.0005781768,0.001460788,0.0003731881],"domain_scores_gemma":[0.9924294,0.003353857,0.0004108155,0.002113565,0.001284917,0.000407452],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000807219,0.0003045194,0.001566806,0.002692234,0.000368717,0.0003175793,0.0005293373,0.01082623,0.009415631,0.0264814,0.720948,0.2257424],"study_design_scores_gemma":[0.0008709249,0.000244818,0.003057259,0.0004271036,0.0001701084,0.000824329,0.0002311961,0.253055,0.03835955,0.1445935,0.5577022,0.0004639867],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.002294215,0.0005328783,0.4075648,0.0005089633,0.0002144751,0.0005250017,0.02257217,0.5564833,0.009304187],"genre_scores_gemma":[0.04870607,0.001269248,0.7073594,0.001454412,0.0002406055,0.003439208,0.08344953,0.137875,0.01620645],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.9947138,"threshold_uncertainty_score":0.1779894,"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."}}