{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OFY23FVDNB6H7B72B7HQ4CIP44","short_pith_number":"pith:OFY23FVD","schema_version":"1.0","canonical_sha256":"7171ad96a3687c7f87fa0fcf0e090fe733fc223640b1b90c1eb4df44a0b2f215","source":{"kind":"arxiv","id":"2505.20591","version":1},"attestation_state":"computed","paper":{"title":"Effectiveness of Prompt Optimization in NL2SQL Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Eser Kandogan, Sairam Gurajada, Sajjadur Rahman","submitted_at":"2025-05-26T23:54:36Z","abstract_excerpt":"NL2SQL approaches have greatly benefited from the impressive capabilities of large language models (LLMs). In particular, bootstrapping an NL2SQL system for a specific domain can be as simple as instructing an LLM with sufficient contextual information, such as schema details and translation demonstrations. However, building an accurate system still requires the rigorous task of selecting the right context for each query-including identifying relevant schema elements, cell values, and suitable exemplars that help the LLM understand domain-specific nuances. Retrieval-based methods have become t"},"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":"2505.20591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T23:54:36Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"a7a5a33c7e96c4e62a7b3e756404b33fa78e28b077a849dc5fadf685f7a650d1","abstract_canon_sha256":"2ead9e68d920ae458ab08ef65c54f2994d717bd9450e080fdbc22c302b88e9ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:15.067878Z","signature_b64":"mepZbbhZbTgJoGlldVdJS458WzfT6cKnPMW6n9yUakCkFlfNHNDkiQndTxkwuxghCoraz0rsWy6ikSxbYGTVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7171ad96a3687c7f87fa0fcf0e090fe733fc223640b1b90c1eb4df44a0b2f215","last_reissued_at":"2026-07-05T11:10:15.067373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:15.067373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effectiveness of Prompt Optimization in NL2SQL Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Eser Kandogan, Sairam Gurajada, Sajjadur Rahman","submitted_at":"2025-05-26T23:54:36Z","abstract_excerpt":"NL2SQL approaches have greatly benefited from the impressive capabilities of large language models (LLMs). In particular, bootstrapping an NL2SQL system for a specific domain can be as simple as instructing an LLM with sufficient contextual information, such as schema details and translation demonstrations. However, building an accurate system still requires the rigorous task of selecting the right context for each query-including identifying relevant schema elements, cell values, and suitable exemplars that help the LLM understand domain-specific nuances. Retrieval-based methods have become t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20591","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/2505.20591/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":"2505.20591","created_at":"2026-07-05T11:10:15.067436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20591v1","created_at":"2026-07-05T11:10:15.067436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20591","created_at":"2026-07-05T11:10:15.067436+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFY23FVDNB6H","created_at":"2026-07-05T11:10:15.067436+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFY23FVDNB6H7B72","created_at":"2026-07-05T11:10:15.067436+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFY23FVD","created_at":"2026-07-05T11:10:15.067436+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/OFY23FVDNB6H7B72B7HQ4CIP44","json":"https://pith.science/pith/OFY23FVDNB6H7B72B7HQ4CIP44.json","graph_json":"https://pith.science/api/pith-number/OFY23FVDNB6H7B72B7HQ4CIP44/graph.json","events_json":"https://pith.science/api/pith-number/OFY23FVDNB6H7B72B7HQ4CIP44/events.json","paper":"https://pith.science/paper/OFY23FVD"},"agent_actions":{"view_html":"https://pith.science/pith/OFY23FVDNB6H7B72B7HQ4CIP44","download_json":"https://pith.science/pith/OFY23FVDNB6H7B72B7HQ4CIP44.json","view_paper":"https://pith.science/paper/OFY23FVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20591&json=true","fetch_graph":"https://pith.science/api/pith-number/OFY23FVDNB6H7B72B7HQ4CIP44/graph.json","fetch_events":"https://pith.science/api/pith-number/OFY23FVDNB6H7B72B7HQ4CIP44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFY23FVDNB6H7B72B7HQ4CIP44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFY23FVDNB6H7B72B7HQ4CIP44/action/storage_attestation","attest_author":"https://pith.science/pith/OFY23FVDNB6H7B72B7HQ4CIP44/action/author_attestation","sign_citation":"https://pith.science/pith/OFY23FVDNB6H7B72B7HQ4CIP44/action/citation_signature","submit_replication":"https://pith.science/pith/OFY23FVDNB6H7B72B7HQ4CIP44/action/replication_record"}},"created_at":"2026-07-05T11:10:15.067436+00:00","updated_at":"2026-07-05T11:10:15.067436+00:00"}