{"paper":{"title":"Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL","arxiv_id":"2610.02739","primary_cat":"cs.CL","submitted_at":"2026-10-02T03:10:55+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":1.0,"id":"s0","own":false,"role":"background","text":"Agentic Text-to-SQL systems can interact with users to clarify underspecified queries before generating SQL.","hedge":{"p":0.51,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.59,"id":"s1","own":false,"role":"gap","text":"However, a correct execution result does not necessarily imply that the agent has adequately resolved the underlying underspecification: the agent may silently make unverified assumptions that happen to match the intended answer.","hedge":{"p":0.58,"label":"hedged_possibility"},"own_p":0.2,"main_claim_p":0.2,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.59,"method":0.0,"result":0.05,"background":0.34,"limitation":0.01,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":2,"p":0.85,"id":"s2","own":true,"role":"result","text":"We show that this behavior is driven in part by premature clarification termination.","hedge":{"p":0.92,"label":"asserted"},"own_p":0.88,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.85,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.14}},{"i":3,"p":0.93,"id":"s3","own":true,"role":"result","text":"Although forcing an agent to ask more questions improves execution accuracy, ambiguities are concentrated in earlier interactions, making brute-force questioning inefficient.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.79,"main_claim_p":0.06,"quantitative":true,"quantitative_p":0.57,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.93,"background":0.02,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.04}},{"i":4,"p":0.93,"id":"s4","own":true,"role":"result","text":"More importantly, even when explicitly prompted to plan its clarification process, the agent frequently abandons questions that it has already identified as relevant.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.86,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.04,"method":0.0,"result":0.93,"background":0.03,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":5,"p":0.58,"id":"s5","own":true,"role":"contribution","text":"To address this failure mode, we introduce PlanPool, which externalizes the clarification plan as a mutable question pool.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.84,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.42,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.58,"interpretation":0.0}},{"i":6,"p":0.98,"id":"s6","own":true,"role":"method","text":"Every planned question must be explicitly asked or dropped before submission, while newly discovered ambiguities can be added during interaction.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.55,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.08,"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":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"Across three benchmarks derived from BIRD-Interact and Spider, PlanPool consistently improves ambiguity coverage and reduces silent failures over unconstrained and prompt-based alternatives, while maintaining competitive execution accuracy.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.37,"quantitative":true,"quantitative_p":0.92,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"interpretation","text":"Our results highlight an important distinction in agentic reasoning: identifying missing information is not sufficient, and the agent must also reliably maintain and resolve it before committing to an answer.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.74,"main_claim_p":0.83,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":1.0}}]},"compiled":{"main_claim":{"p":0.92,"text":"Our results highlight an important distinction in agentic reasoning: identifying missing information is not sufficient, and the agent must also reliably maintain and resolve it before committing to an answer.","location":"abstract s8","hedge_strength":{"p":0.99,"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":6860,"cost_usd_reported":0.0},"compiled_at":"2026-10-05","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.05,"states_limitation":0.24,"human_participants":0.07,"controlled_comparison":0.91,"randomized_assignment":0.01,"states_quantitative_result":0.09,"compares_with_prior_results":0.94,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.99,"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":0.99,"simulation_or_computation":0.01}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"To address this failure mode, we introduce PlanPool, which externalizes the clarification plan as a mutable question pool.","location":"abstract s5"}},"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,"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"}}}