{"paper":{"title":"Route Me If You Can: A Benchmark for Query Reformulation Selection","arxiv_id":"2609.14885","primary_cat":"cs.IR","submitted_at":"2026-09-14T01:06:41+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.8,"id":"s0","own":false,"role":"background","text":"LLM-based query reformulation can improve retrieval, but no single reformulation strategy is consistently optimal across queries, domains, retrievers, or model backbones.","hedge":{"p":0.93,"label":"asserted"},"own_p":0.09,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.19,"role_probabilities":{"gap":0.2,"method":0.0,"result":0.0,"background":0.8,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.86,"id":"s1","own":false,"role":"background","text":"This creates an inference-time decision problem: ``Given an original query and a pool of candidate reformulations, which one should be issued to the retriever?''.","hedge":{"p":0.86,"label":"asserted"},"own_p":0.07,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.14,"method":0.0,"result":0.0,"background":0.86,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.8,"id":"s2","own":false,"role":"gap","text":"Existing studies are hard to compare because they use different reformulator pools, retrievers, relevance signals, training labels, and evaluation metrics.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.21,"role_probabilities":{"gap":0.8,"method":0.0,"result":0.0,"background":0.2,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":0.97,"id":"s3","own":true,"role":"contribution","text":"We introduce QueryRoute, a benchmark that freezes the expensive artifacts needed to study this decision reproducibly: original queries, generated variants, ranked lists under multiple retrievers, retrieval scores, and per-query oracle labels.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.03,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.97,"interpretation":0.0}},{"i":4,"p":0.71,"id":"s4","own":true,"role":"method","text":"The benchmark contains 3,757 queries, 11 candidate systems, five reformulator backbones, and three retrievers across TREC DL, BEIR, and BRIGHT, yielding 619,905 retrieval outcomes.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.04,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.71,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.29,"interpretation":0.0}},{"i":5,"p":0.8,"id":"s5","own":true,"role":"method","text":"We benchmark supervised classification, routing, QPP, and LLM-as-judge selectors.","hedge":{"p":0.86,"label":"asserted"},"own_p":0.93,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.8,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.2,"interpretation":0.0}},{"i":6,"p":0.94,"id":"s6","own":true,"role":"result","text":"Results show substantial oracle headroom over fixed reformulators, but current selectors recover only part of it; selector rankings change across retrievers, and similar mean effectiveness can hide different query-level behavior.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.7,"quantitative":true,"quantitative_p":0.82,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.94,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.06}},{"i":7,"p":0.8,"id":"s7","own":true,"role":"contribution","text":"The released artifacts and evaluation harness allow future selectors to be compared without regenerating variants, rerunning retrieval, or rebuilding judge pipelines.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.76,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.14,"contribution":0.8,"interpretation":0.0}},{"i":8,"p":0.79,"id":"s8","own":true,"role":"contribution","text":"Code and data are available at https://github.com/haisonle001/QueryRoute","hedge":{"p":0.98,"label":"asserted"},"own_p":0.52,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.19,"contribution":0.79,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.97,"text":"Results show substantial oracle headroom over fixed reformulators, but current selectors recover only part of it; selector rankings change across retrievers, and similar mean effectiveness can hide different query-level behavior.","location":"abstract s6","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7014,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.11,"states_limitation":0.75,"human_participants":0.05,"controlled_comparison":0.77,"randomized_assignment":0.02,"states_quantitative_result":0.95,"compares_with_prior_results":0.86,"mentions_code_or_data_availability":0.99},"evidential_basis":{"p":0.93,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.03,"observation_or_experiment":0.93,"simulation_or_computation":0.04}},"contribution_type":{"p":1.0,"value":"dataset or benchmark","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":1.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We introduce QueryRoute, a benchmark that freezes the expensive artifacts needed to study this decision reproducibly: original queries, generated variants, ranked lists under multiple retrievers, retrieval scores, and per-query oracle labels.","location":"abstract s3"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":9,"sentences_in_abstract":9},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448}}