{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GVNGIX42QZOK6RBKLPG2DP7IYL","short_pith_number":"pith:GVNGIX42","schema_version":"1.0","canonical_sha256":"355a645f9a865caf442a5bcda1bfe8c2e9682fe0aa1eae8fc623f0cdab0878df","source":{"kind":"arxiv","id":"2505.19302","version":1},"attestation_state":"computed","paper":{"title":"ODIN: A NL2SQL Recommender to Handle Schema Ambiguity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Abishek Sankararaman, Balakrishnan Narayanaswamy, Chuan Lei, Jialin Ding, Kapil Vaidya, Tim Kraska, Xiao Qin","submitted_at":"2025-05-25T20:22:32Z","abstract_excerpt":"NL2SQL (natural language to SQL) systems translate natural language into SQL queries, allowing users with no technical background to interact with databases and create tools like reports or visualizations. While recent advancements in large language models (LLMs) have significantly improved NL2SQL accuracy, schema ambiguity remains a major challenge in enterprise environments with complex schemas, where multiple tables and columns with semantically similar names often co-exist. To address schema ambiguity, we introduce ODIN, a NL2SQL recommendation engine. Instead of producing a single SQL que"},"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":"2505.19302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-05-25T20:22:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"946139b6e9b555673b2178b8c281b4db8d30352835a45407314283eb4ea58e83","abstract_canon_sha256":"5ebee401335b93b61ff310b69901fcade5dbce028f6c9a46655c1c9fea088c1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:27.856760Z","signature_b64":"vEUT0uqM2cFI6nJ+bQd1UkHjB85am1t2fippqqeDuJE5vIH5qJNzeO21ABhCf818siV9T7XMoxU19a249AjpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"355a645f9a865caf442a5bcda1bfe8c2e9682fe0aa1eae8fc623f0cdab0878df","last_reissued_at":"2026-07-05T11:09:27.856224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:27.856224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ODIN: A NL2SQL Recommender to Handle Schema Ambiguity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Abishek Sankararaman, Balakrishnan Narayanaswamy, Chuan Lei, Jialin Ding, Kapil Vaidya, Tim Kraska, Xiao Qin","submitted_at":"2025-05-25T20:22:32Z","abstract_excerpt":"NL2SQL (natural language to SQL) systems translate natural language into SQL queries, allowing users with no technical background to interact with databases and create tools like reports or visualizations. While recent advancements in large language models (LLMs) have significantly improved NL2SQL accuracy, schema ambiguity remains a major challenge in enterprise environments with complex schemas, where multiple tables and columns with semantically similar names often co-exist. To address schema ambiguity, we introduce ODIN, a NL2SQL recommendation engine. Instead of producing a single SQL que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19302","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/2505.19302/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":"2505.19302","created_at":"2026-07-05T11:09:27.856288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19302v1","created_at":"2026-07-05T11:09:27.856288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19302","created_at":"2026-07-05T11:09:27.856288+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVNGIX42QZOK","created_at":"2026-07-05T11:09:27.856288+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVNGIX42QZOK6RBK","created_at":"2026-07-05T11:09:27.856288+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVNGIX42","created_at":"2026-07-05T11:09:27.856288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11424","citing_title":"SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00628","citing_title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL","json":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL.json","graph_json":"https://pith.science/api/pith-number/GVNGIX42QZOK6RBKLPG2DP7IYL/graph.json","events_json":"https://pith.science/api/pith-number/GVNGIX42QZOK6RBKLPG2DP7IYL/events.json","paper":"https://pith.science/paper/GVNGIX42"},"agent_actions":{"view_html":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL","download_json":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL.json","view_paper":"https://pith.science/paper/GVNGIX42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19302&json=true","fetch_graph":"https://pith.science/api/pith-number/GVNGIX42QZOK6RBKLPG2DP7IYL/graph.json","fetch_events":"https://pith.science/api/pith-number/GVNGIX42QZOK6RBKLPG2DP7IYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL/action/storage_attestation","attest_author":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL/action/author_attestation","sign_citation":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL/action/citation_signature","submit_replication":"https://pith.science/pith/GVNGIX42QZOK6RBKLPG2DP7IYL/action/replication_record"}},"created_at":"2026-07-05T11:09:27.856288+00:00","updated_at":"2026-07-05T11:09:27.856288+00:00"}