{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NXI27MLPWFKW75JXWPFEYO74M4","short_pith_number":"pith:NXI27MLP","schema_version":"1.0","canonical_sha256":"6dd1afb16fb1556ff537b3ca4c3bfc671fef863a97f50ce481096f9304204957","source":{"kind":"arxiv","id":"2606.11424","version":1},"attestation_state":"computed","paper":{"title":"SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankan Bansal, Chuan Lei, Daniel Garcia, Dan Roth, Fjona Parllaku, Marianne Menglin Liu, Rongguang Wang, Sai Ashish Somayajula, Sujeeth Bharadwaj, Sujith Ravi, Syed Fahad Allam Shah, Tao Sheng","submitted_at":"2026-06-09T20:18:22Z","abstract_excerpt":"Natural language interfaces to databases aim to translate user questions into executable SQL, yet remain brittle in real-world settings where questions are underspecified and schemas are large and ambiguous. Ambiguity across user questions, database schemas, and model interpretations are central failure modes in NL2SQL, leading to misaligned intent, incorrect schema grounding, and erroneous SQL generation. Existing approaches rely on human clarification or treat ambiguity as a schema representation problem, but these do not scale nor resolve ambiguity autonomously. We propose SOMA-SQL to autom"},"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":"2606.11424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T20:18:22Z","cross_cats_sorted":[],"title_canon_sha256":"91c58c9b313083bbf40ebaa3a9851b2aca11c3d06506744f932c25fdcfc1433d","abstract_canon_sha256":"2cea0ad1ce7a402306a8a7ec2e4960510723ed9228b96a8fbc46911624f5a938"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:47.892460Z","signature_b64":"Q6gSFxJUZ0Ppv4OHiND9yW1hw/7hiXMJRgokExprAoQxwEFt/UGJw/t5iJCuzi8g0wYtcdWbWkUypuDKz68wDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dd1afb16fb1556ff537b3ca4c3bfc671fef863a97f50ce481096f9304204957","last_reissued_at":"2026-06-11T01:09:47.891548Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:47.891548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ankan Bansal, Chuan Lei, Daniel Garcia, Dan Roth, Fjona Parllaku, Marianne Menglin Liu, Rongguang Wang, Sai Ashish Somayajula, Sujeeth Bharadwaj, Sujith Ravi, Syed Fahad Allam Shah, Tao Sheng","submitted_at":"2026-06-09T20:18:22Z","abstract_excerpt":"Natural language interfaces to databases aim to translate user questions into executable SQL, yet remain brittle in real-world settings where questions are underspecified and schemas are large and ambiguous. Ambiguity across user questions, database schemas, and model interpretations are central failure modes in NL2SQL, leading to misaligned intent, incorrect schema grounding, and erroneous SQL generation. Existing approaches rely on human clarification or treat ambiguity as a schema representation problem, but these do not scale nor resolve ambiguity autonomously. We propose SOMA-SQL to autom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11424","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/2606.11424/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":"2606.11424","created_at":"2026-06-11T01:09:47.891700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11424v1","created_at":"2026-06-11T01:09:47.891700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11424","created_at":"2026-06-11T01:09:47.891700+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXI27MLPWFKW","created_at":"2026-06-11T01:09:47.891700+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXI27MLPWFKW75JX","created_at":"2026-06-11T01:09:47.891700+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXI27MLP","created_at":"2026-06-11T01:09:47.891700+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/NXI27MLPWFKW75JXWPFEYO74M4","json":"https://pith.science/pith/NXI27MLPWFKW75JXWPFEYO74M4.json","graph_json":"https://pith.science/api/pith-number/NXI27MLPWFKW75JXWPFEYO74M4/graph.json","events_json":"https://pith.science/api/pith-number/NXI27MLPWFKW75JXWPFEYO74M4/events.json","paper":"https://pith.science/paper/NXI27MLP"},"agent_actions":{"view_html":"https://pith.science/pith/NXI27MLPWFKW75JXWPFEYO74M4","download_json":"https://pith.science/pith/NXI27MLPWFKW75JXWPFEYO74M4.json","view_paper":"https://pith.science/paper/NXI27MLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11424&json=true","fetch_graph":"https://pith.science/api/pith-number/NXI27MLPWFKW75JXWPFEYO74M4/graph.json","fetch_events":"https://pith.science/api/pith-number/NXI27MLPWFKW75JXWPFEYO74M4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXI27MLPWFKW75JXWPFEYO74M4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXI27MLPWFKW75JXWPFEYO74M4/action/storage_attestation","attest_author":"https://pith.science/pith/NXI27MLPWFKW75JXWPFEYO74M4/action/author_attestation","sign_citation":"https://pith.science/pith/NXI27MLPWFKW75JXWPFEYO74M4/action/citation_signature","submit_replication":"https://pith.science/pith/NXI27MLPWFKW75JXWPFEYO74M4/action/replication_record"}},"created_at":"2026-06-11T01:09:47.891700+00:00","updated_at":"2026-06-11T01:09:47.891700+00:00"}