{"id":"W3154288935","doi":"","title":"Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations","year":2021,"lang":"en","type":"article","venue":"International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Python (programming language); Computer science; Information retrieval; Scripting language; Ranking (information retrieval); Empirical research; Data mining; Artificial intelligence; Machine learning; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":[0.005074273,0.002315041,0.001548092,0.001713136,0.000974377,0.003304148,0.005634859,0.001151194,0.04865607],"category_scores_gemma":[0.02097319,0.001694139,0.002080605,0.001664623,0.001519271,0.00613692,0.005691207,0.00504545,0.05073935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009875294,"about_ca_system_score_gemma":0.003445084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003287636,"about_ca_topic_score_gemma":0.003877228,"domain_scores_codex":[0.9972032,0.0007254115,0.0003272267,0.0004702372,0.0009526355,0.0003211841],"domain_scores_gemma":[0.9929662,0.00314547,0.0003435173,0.002142199,0.0009184831,0.0004841617],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001289542,0.0004532269,0.002749708,0.002456745,0.0003426257,0.0004906897,0.0009381102,0.009103066,0.01618957,0.02491833,0.6951302,0.2459381],"study_design_scores_gemma":[0.001024656,0.0003703107,0.004439078,0.0004739034,0.0001802768,0.001070873,0.0002767315,0.1865681,0.05277393,0.1013831,0.6508963,0.0005426914],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.003047858,0.0003157834,0.288722,0.0004350617,0.0002571972,0.0005298806,0.01162399,0.6841251,0.01094316],"genre_scores_gemma":[0.06375163,0.0008320864,0.6125839,0.001707352,0.0002510645,0.003883688,0.04968108,0.2443235,0.0229857],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.9949257,"threshold_uncertainty_score":0.1627708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2521258103347477,"score_gpt":0.4196982070748599,"score_spread":0.1675723967401122,"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."}}