{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NOOB2WFCAWIGS7YCKUFMJXBGM4","short_pith_number":"pith:NOOB2WFC","schema_version":"1.0","canonical_sha256":"6b9c1d58a20590697f02550ac4dc26672a0a3f0fe17f74e101b38a7bb2710a44","source":{"kind":"arxiv","id":"2607.03991","version":1},"attestation_state":"computed","paper":{"title":"Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Elena Khabibullina, Isabella Cattinelli, Mor Aisenberg, Nadav Nesher, Yaron Anavi","submitted_at":"2026-07-04T19:18:53Z","abstract_excerpt":"Repeated LLM calls are the standard way to estimate how trustworthy a Text-to-SQL result is: run the pipeline multiple times, judge each SQL execution, and use the consistency of the verdicts as a confidence signal. The open question is when to stop, when the consistency has converged. We formulate this as a convergence-prediction problem and train a family of lightweight 1-D models that observe the running consistency trajectory and decide, at each step, whether further runs are unlikely to shift it materially, and we benchmark them against a principled Beta-Bernoulli stopping rule and a lear"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.03991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-04T19:18:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bf1fc86f39d1805447a1d4d49200a163a5ce3eb3ecb2d8c585ca58270d408038","abstract_canon_sha256":"ccea0d633ea75f91e682551d613b2157e62147a935e4aa893b3148b23ba47847"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:51.919581Z","signature_b64":"u2nqE39HI5NYNNIplLo3zxp5A3VbtYf0OFuoy+QHa3iMneYqjBznfikJQUBKZOMLIuhVAw8LeqZp4+eh3o49DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b9c1d58a20590697f02550ac4dc26672a0a3f0fe17f74e101b38a7bb2710a44","last_reissued_at":"2026-07-07T02:18:51.918950Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:51.918950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Elena Khabibullina, Isabella Cattinelli, Mor Aisenberg, Nadav Nesher, Yaron Anavi","submitted_at":"2026-07-04T19:18:53Z","abstract_excerpt":"Repeated LLM calls are the standard way to estimate how trustworthy a Text-to-SQL result is: run the pipeline multiple times, judge each SQL execution, and use the consistency of the verdicts as a confidence signal. The open question is when to stop, when the consistency has converged. We formulate this as a convergence-prediction problem and train a family of lightweight 1-D models that observe the running consistency trajectory and decide, at each step, whether further runs are unlikely to shift it materially, and we benchmark them against a principled Beta-Bernoulli stopping rule and a lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03991","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.03991/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.03991","created_at":"2026-07-07T02:18:51.919063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03991v1","created_at":"2026-07-07T02:18:51.919063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03991","created_at":"2026-07-07T02:18:51.919063+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOOB2WFCAWIG","created_at":"2026-07-07T02:18:51.919063+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOOB2WFCAWIGS7YC","created_at":"2026-07-07T02:18:51.919063+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOOB2WFC","created_at":"2026-07-07T02:18:51.919063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4","json":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4.json","graph_json":"https://pith.science/api/pith-number/NOOB2WFCAWIGS7YCKUFMJXBGM4/graph.json","events_json":"https://pith.science/api/pith-number/NOOB2WFCAWIGS7YCKUFMJXBGM4/events.json","paper":"https://pith.science/paper/NOOB2WFC"},"agent_actions":{"view_html":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4","download_json":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4.json","view_paper":"https://pith.science/paper/NOOB2WFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03991&json=true","fetch_graph":"https://pith.science/api/pith-number/NOOB2WFCAWIGS7YCKUFMJXBGM4/graph.json","fetch_events":"https://pith.science/api/pith-number/NOOB2WFCAWIGS7YCKUFMJXBGM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4/action/storage_attestation","attest_author":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4/action/author_attestation","sign_citation":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4/action/citation_signature","submit_replication":"https://pith.science/pith/NOOB2WFCAWIGS7YCKUFMJXBGM4/action/replication_record"}},"created_at":"2026-07-07T02:18:51.919063+00:00","updated_at":"2026-07-07T02:18:51.919063+00:00"}