{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002906684,0.0001756361,0.0001832236,0.001363984,0.0004045878,0.002344131,0.001112421,0.00009120348,0.0001461668],"category_scores_gemma":[0.005595653,0.0001679398,0.00001363647,0.001708339,0.0001502547,0.004233356,0.001358947,0.0005413272,0.0004254743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002991454,"about_ca_system_score_gemma":0.00139726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002457673,"about_ca_topic_score_gemma":0.0004466072,"domain_scores_codex":[0.99572,0.0002489119,0.0006205742,0.0006532315,0.002088131,0.0006691936],"domain_scores_gemma":[0.9937556,0.001064258,0.00007380683,0.0008341943,0.003718898,0.0005532088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.003856709,0.001004325,0.06559446,0.0001253164,0.0001210797,0.0007415776,0.03975589,0.001585056,0.008696843,0.7415984,0.006391424,0.130529],"study_design_scores_gemma":[0.003009472,0.006619557,0.3038542,0.001017691,0.000004381721,0.0004483763,0.02049074,0.03139492,0.303558,0.03806992,0.2894425,0.002090144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9456858,0.000004509789,0.03655802,0.009070616,0.0001985984,0.0008435906,0.00001793311,0.00009373514,0.00752717],"genre_scores_gemma":[0.9170288,0.00009610785,0.0798337,0.0008362213,0.00003579666,0.0001706647,0.00009401417,0.00001312853,0.001891553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7035284,"threshold_uncertainty_score":0.9986916,"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."}}