{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MTAO4ZFJTYSTDUQO54QJSUVIU6","short_pith_number":"pith:MTAO4ZFJ","schema_version":"1.0","canonical_sha256":"64c0ee64a99e2531d20eef209952a8a79837d96c9dd14fc211a8d3a17597d8ee","source":{"kind":"arxiv","id":"2505.19956","version":2},"attestation_state":"computed","paper":{"title":"DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jaehoon Lee, Jee-Hyong Lee, Jihyung Lee, Jin-Seop Lee, YunSeok Choi","submitted_at":"2025-05-26T13:19:10Z","abstract_excerpt":"Text-to-SQL, which translates a natural language question into an SQL query, has advanced with in-context learning of Large Language Models (LLMs). However, existing methods show little improvement in performance compared to randomly chosen demonstrations, and significant performance drops when smaller LLMs (e.g., Llama 3.1-8B) are used. This indicates that these methods heavily rely on the intrinsic capabilities of hyper-scaled LLMs, rather than effectively retrieving useful demonstrations. In this paper, we propose a novel approach for effectively retrieving demonstrations and generating SQL"},"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":"2505.19956","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-26T13:19:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"013f636f0c6c842907e3dd295e599985e9ec6c3f1355fd7728edb083b81fa99d","abstract_canon_sha256":"0d129684501c5931ac8732b11d8e09cb581412036a8400b956956987af79cb23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:55.114449Z","signature_b64":"hxpExi8W1ctGDg94iXlSAcrQZyFUeMFkz/ZySoJSGrmVlXUntzktBCtwWnDs3CerjFTjQhZdEmoMc4NHUi3tBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64c0ee64a99e2531d20eef209952a8a79837d96c9dd14fc211a8d3a17597d8ee","last_reissued_at":"2026-07-05T11:40:55.113950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:55.113950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jaehoon Lee, Jee-Hyong Lee, Jihyung Lee, Jin-Seop Lee, YunSeok Choi","submitted_at":"2025-05-26T13:19:10Z","abstract_excerpt":"Text-to-SQL, which translates a natural language question into an SQL query, has advanced with in-context learning of Large Language Models (LLMs). However, existing methods show little improvement in performance compared to randomly chosen demonstrations, and significant performance drops when smaller LLMs (e.g., Llama 3.1-8B) are used. This indicates that these methods heavily rely on the intrinsic capabilities of hyper-scaled LLMs, rather than effectively retrieving useful demonstrations. In this paper, we propose a novel approach for effectively retrieving demonstrations and generating SQL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19956","kind":"arxiv","version":2},"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/2505.19956/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":"2505.19956","created_at":"2026-07-05T11:40:55.114007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19956v2","created_at":"2026-07-05T11:40:55.114007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19956","created_at":"2026-07-05T11:40:55.114007+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTAO4ZFJTYST","created_at":"2026-07-05T11:40:55.114007+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTAO4ZFJTYSTDUQO","created_at":"2026-07-05T11:40:55.114007+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTAO4ZFJ","created_at":"2026-07-05T11:40:55.114007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26613","citing_title":"EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6","json":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6.json","graph_json":"https://pith.science/api/pith-number/MTAO4ZFJTYSTDUQO54QJSUVIU6/graph.json","events_json":"https://pith.science/api/pith-number/MTAO4ZFJTYSTDUQO54QJSUVIU6/events.json","paper":"https://pith.science/paper/MTAO4ZFJ"},"agent_actions":{"view_html":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6","download_json":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6.json","view_paper":"https://pith.science/paper/MTAO4ZFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19956&json=true","fetch_graph":"https://pith.science/api/pith-number/MTAO4ZFJTYSTDUQO54QJSUVIU6/graph.json","fetch_events":"https://pith.science/api/pith-number/MTAO4ZFJTYSTDUQO54QJSUVIU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6/action/storage_attestation","attest_author":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6/action/author_attestation","sign_citation":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6/action/citation_signature","submit_replication":"https://pith.science/pith/MTAO4ZFJTYSTDUQO54QJSUVIU6/action/replication_record"}},"created_at":"2026-07-05T11:40:55.114007+00:00","updated_at":"2026-07-05T11:40:55.114007+00:00"}