{"id":"W4387848881","doi":"10.1145/3583780.3615270","title":"Noisy Perturbations for Estimating Query Difficulty in Dense Retrievers","year":2023,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Computer science; Query expansion; Robustness (evolution); Query optimization; Web query classification; Sargable; Ranking (information retrieval); Web search query; Query language; Query by Example; Data mining; Artificial intelligence; Information retrieval; Search engine","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":[],"consensus_categories":[],"category_scores_codex":[0.0003338751,0.00006855433,0.0000812474,0.0001549884,0.0001381456,0.0001149857,0.0002361766,0.00003640273,0.00001560629],"category_scores_gemma":[0.0006558319,0.00006285236,0.00004170502,0.0008241393,0.00001458334,0.0002802086,0.00006898531,0.00008076869,0.0001042074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003938742,"about_ca_system_score_gemma":0.00004493776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002266616,"about_ca_topic_score_gemma":0.00003374814,"domain_scores_codex":[0.9992252,0.00002939669,0.0001716594,0.0002218247,0.0001399798,0.0002119139],"domain_scores_gemma":[0.9992342,0.0004474793,0.00004239539,0.0001723429,0.00005070071,0.00005285411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003539511,0.0001703398,0.006263138,0.0001017793,0.00003772977,0.00006733963,0.02455997,0.1806858,0.006529898,0.5079499,0.05806781,0.2155309],"study_design_scores_gemma":[0.0003045106,0.00001723057,0.01173154,0.00001146088,9.536349e-7,0.000001936275,0.0003602792,0.9826469,0.00005710676,0.001269204,0.003503196,0.00009570365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03305609,0.000004791978,0.9612561,0.00211771,0.0003020109,0.000164957,0.000001103283,0.0004203469,0.00267686],"genre_scores_gemma":[0.4848769,0.000002217841,0.5071322,0.0005870327,0.00004711133,0.00004310141,0.00001559694,0.000009440741,0.007286361],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8019611,"threshold_uncertainty_score":0.2563045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03751847394280215,"score_gpt":0.2890422928063041,"score_spread":0.2515238188635019,"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."}}