{"paper":{"title":"FlinkEval: A Synthetic Corpus for Evaluating Natural Language Interfaces to Streaming SQL","arxiv_id":"2611.17093","primary_cat":"cs.DB","submitted_at":"2026-11-12T16:54:35+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":0.91,"id":"s0","own":false,"role":"gap","text":"Existing natural-language-to-SQL benchmarks primarily evaluate queries over bounded relational data, leaving streaming semantics underexplored.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.19,"role_probabilities":{"gap":0.91,"method":0.0,"result":0.0,"background":0.09,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":1.0,"id":"s1","own":true,"role":"contribution","text":"We introduce FlinkEval, an execution-grounded synthetic benchmark comprising 3,903 question--SQL pairs across 45 industry domains and 45 semantic labels.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":2,"p":0.98,"id":"s2","own":true,"role":"method","text":"We create diverse schemas and domain-plausible, temporally consistent data through iterative generation and validation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"method","text":"SQL patterns collected from the human-written NL2SQL pairs and vendor documentation drive quota-balanced generation, and execution with a repair loop on Confluent Cloud Apache Flink produces reference queries covering windowing, temporal joins, pattern matching, nested types, and data manipulation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":0.67,"id":"s4","own":true,"role":"contribution","text":"The corpus includes paired schema-explicit and business-language requests, with annotations for analysis by query pattern, complexity, and execution mode.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.88,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.33,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.67,"interpretation":0.0}},{"i":5,"p":0.59,"id":"s5","own":true,"role":"method","text":"A seven-level Question Specification Ladder examines semantics-preserving reformulation and underspecified requests augmented with oracle-derived clues.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.9,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.95,"role_probabilities":{"gap":0.0,"method":0.59,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.41,"interpretation":0.0}},{"i":6,"p":0.93,"id":"s6","own":true,"role":"result","text":"Baseline evaluations combine execution outcomes with adjudicated LLM judgments, revealing challenges in pattern composition and request specification.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.53,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.93,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.04}}]},"compiled":{"main_claim":{"p":0.99,"text":"Baseline evaluations combine execution outcomes with adjudicated LLM judgments, revealing challenges in pattern composition and request specification.","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":5592,"cost_usd_reported":0.0},"compiled_at":"2026-11-14","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.15,"states_limitation":0.36,"human_participants":0.13,"controlled_comparison":0.57,"randomized_assignment":0.02,"states_quantitative_result":0.94,"compares_with_prior_results":0.8,"mentions_code_or_data_availability":0.09},"evidential_basis":{"p":0.89,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.89,"simulation_or_computation":0.11}},"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 FlinkEval, an execution-grounded synthetic benchmark comprising 3,903 question--SQL pairs across 45 industry domains and 45 semantic labels.","location":"abstract s1"}},"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":7,"sentences_in_abstract":7},"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,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}