{"id":"W4410502462","doi":"10.1145/3736402","title":"Query Performance Prediction Using Relevance Judgments Generated by Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"HORIZON EUROPE Framework Programme; Ministerie van Economische Zaken en Klimaat; China Scholarship Council; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Ministerie van Onderwijs, Cultuur en Wetenschap; European Commission","keywords":"Relevance (law); Computer science; Interpretability; Recall; Metric (unit); Measure (data warehouse); Precision and recall; Scalar (mathematics); Information retrieval; Data mining; Machine learning; Artificial intelligence; Cognitive psychology; Mathematics; Psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.00570071,0.002113912,0.001464773,0.002863818,0.0005530289,0.00260839,0.001949203,0.001578027,0.001671945],"category_scores_gemma":[0.04108148,0.0007414091,0.001388229,0.001563533,0.0008929549,0.003717826,0.001670144,0.002909267,0.002017492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001581794,"about_ca_system_score_gemma":0.001788901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007705485,"about_ca_topic_score_gemma":0.009770912,"domain_scores_codex":[0.994769,0.001995681,0.0003587266,0.001244638,0.001330173,0.0003017836],"domain_scores_gemma":[0.9765114,0.01544933,0.001706793,0.002053891,0.003834331,0.0004442829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00143206,0.0006630924,0.02757039,0.001135517,0.0003850438,0.0005447976,0.0008150713,0.4669456,0.04941839,0.009189326,0.0183377,0.4235631],"study_design_scores_gemma":[0.00002618391,0.00009169131,0.001614384,0.00001757432,0.00002637066,0.00004316816,0.00003512741,0.9885873,0.004738785,0.004045497,0.000739089,0.0000348881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1013448,0.00142891,0.8808343,0.0006757977,0.0001519219,0.0004060777,0.001613601,0.01054634,0.002998273],"genre_scores_gemma":[0.7306072,0.0004598366,0.2595764,0.0003959391,0.0002792382,0.0005117336,0.004713565,0.0009437276,0.002512427],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007705485,"threshold_uncertainty_score":0.03014857,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02121226181174902,"score_gpt":0.2639589587016803,"score_spread":0.2427466968899313,"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."}}