{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G27DJKVDY3J42NCISGW74HKEQC","short_pith_number":"pith:G27DJKVD","canonical_record":{"source":{"id":"2503.04959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T20:46:43Z","cross_cats_sorted":[],"title_canon_sha256":"c946044e59582d778aff1c4957517e8aa7b9816f7d6d64841230dd5ccf02974b","abstract_canon_sha256":"9eef8eeb38c6df998cfed1757039a5daf4b6c9b7a2d9314d4c8e814d46874ccf"},"schema_version":"1.0"},"canonical_sha256":"36be34aaa3c6d3cd344891adfe1d4480ba8441f571a1cac283ae2c2e8a648703","source":{"kind":"arxiv","id":"2503.04959","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04959","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04959v2","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04959","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"G27DJKVDY3J4","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"G27DJKVDY3J42NCI","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"G27DJKVD","created_at":"2026-07-05T11:06:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G27DJKVDY3J42NCISGW74HKEQC","target":"record","payload":{"canonical_record":{"source":{"id":"2503.04959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T20:46:43Z","cross_cats_sorted":[],"title_canon_sha256":"c946044e59582d778aff1c4957517e8aa7b9816f7d6d64841230dd5ccf02974b","abstract_canon_sha256":"9eef8eeb38c6df998cfed1757039a5daf4b6c9b7a2d9314d4c8e814d46874ccf"},"schema_version":"1.0"},"canonical_sha256":"36be34aaa3c6d3cd344891adfe1d4480ba8441f571a1cac283ae2c2e8a648703","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:29.224368Z","signature_b64":"kgYBd/o4/2so9uaCs8DwGdiAqe28gSQa09BobR4Pl7lgedWE52GntPG/AiUXSbNC09VhOd2vtLwQaJ5b/YCuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36be34aaa3c6d3cd344891adfe1d4480ba8441f571a1cac283ae2c2e8a648703","last_reissued_at":"2026-07-05T11:06:29.223817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:29.223817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.04959","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uFDLpx/Ex1jM0UHl2xb488WYJgpvx47dUKOsMAxHNH7SQQYBc0LXfduvAjDjoHG0mQmWCbv80WUwrSqMYjZgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:29:03.703012Z"},"content_sha256":"374665b6881570ca93512fd69e3f70ee5f17ce7004be71d0a72cfa38b6949d68","schema_version":"1.0","event_id":"sha256:374665b6881570ca93512fd69e3f70ee5f17ce7004be71d0a72cfa38b6949d68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G27DJKVDY3J42NCISGW74HKEQC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haolei Xu, Haoyuan Ma, Hengwei Liu, Jun Wang, Qiuying Peng, Weiming Lu, Wenqi Zhang, Yongliang Shen","submitted_at":"2025-03-06T20:46:43Z","abstract_excerpt":"Recent text-to-SQL systems powered by large language models (LLMs) have demonstrated remarkable performance in translating natural language queries into SQL. However, these systems often struggle with complex database structures and domain-specific queries, as they primarily focus on enhancing logical reasoning and SQL syntax while overlooking the critical need for comprehensive database understanding. To address this limitation, we propose DB-Explore, a novel framework that systematically aligns LLMs with database knowledge through automated exploration and instruction synthesis. DB-Explore c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04959","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/2503.04959/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bYyUJpaOwNRtntJyzCA6ZuqgFVUlOLq3sCvz8ex/JUGe/Fy0tQOuPuUr8shEq+kwDCAPjgRzEQj4DuNfv1ElBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:29:03.703598Z"},"content_sha256":"0bffc5089fb71d88c169f23c05996f5be17ca3eb21c4790c7de53d64450fd24c","schema_version":"1.0","event_id":"sha256:0bffc5089fb71d88c169f23c05996f5be17ca3eb21c4790c7de53d64450fd24c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/bundle.json","state_url":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G27DJKVDY3J42NCISGW74HKEQC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T02:29:03Z","links":{"resolver":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC","bundle":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/bundle.json","state":"https://pith.science/pith/G27DJKVDY3J42NCISGW74HKEQC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G27DJKVDY3J42NCISGW74HKEQC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G27DJKVDY3J42NCISGW74HKEQC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9eef8eeb38c6df998cfed1757039a5daf4b6c9b7a2d9314d4c8e814d46874ccf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T20:46:43Z","title_canon_sha256":"c946044e59582d778aff1c4957517e8aa7b9816f7d6d64841230dd5ccf02974b"},"schema_version":"1.0","source":{"id":"2503.04959","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04959","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04959v2","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04959","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"G27DJKVDY3J4","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"G27DJKVDY3J42NCI","created_at":"2026-07-05T11:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"G27DJKVD","created_at":"2026-07-05T11:06:29Z"}],"graph_snapshots":[{"event_id":"sha256:0bffc5089fb71d88c169f23c05996f5be17ca3eb21c4790c7de53d64450fd24c","target":"graph","created_at":"2026-07-05T11:06:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.04959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent text-to-SQL systems powered by large language models (LLMs) have demonstrated remarkable performance in translating natural language queries into SQL. However, these systems often struggle with complex database structures and domain-specific queries, as they primarily focus on enhancing logical reasoning and SQL syntax while overlooking the critical need for comprehensive database understanding. To address this limitation, we propose DB-Explore, a novel framework that systematically aligns LLMs with database knowledge through automated exploration and instruction synthesis. DB-Explore c","authors_text":"Haolei Xu, Haoyuan Ma, Hengwei Liu, Jun Wang, Qiuying Peng, Weiming Lu, Wenqi Zhang, Yongliang Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T20:46:43Z","title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04959","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:374665b6881570ca93512fd69e3f70ee5f17ce7004be71d0a72cfa38b6949d68","target":"record","created_at":"2026-07-05T11:06:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9eef8eeb38c6df998cfed1757039a5daf4b6c9b7a2d9314d4c8e814d46874ccf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T20:46:43Z","title_canon_sha256":"c946044e59582d778aff1c4957517e8aa7b9816f7d6d64841230dd5ccf02974b"},"schema_version":"1.0","source":{"id":"2503.04959","kind":"arxiv","version":2}},"canonical_sha256":"36be34aaa3c6d3cd344891adfe1d4480ba8441f571a1cac283ae2c2e8a648703","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36be34aaa3c6d3cd344891adfe1d4480ba8441f571a1cac283ae2c2e8a648703","first_computed_at":"2026-07-05T11:06:29.223817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:29.223817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kgYBd/o4/2so9uaCs8DwGdiAqe28gSQa09BobR4Pl7lgedWE52GntPG/AiUXSbNC09VhOd2vtLwQaJ5b/YCuDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:29.224368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04959","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:374665b6881570ca93512fd69e3f70ee5f17ce7004be71d0a72cfa38b6949d68","sha256:0bffc5089fb71d88c169f23c05996f5be17ca3eb21c4790c7de53d64450fd24c"],"state_sha256":"b8c8bd5f17074f57556a9c3a9ae0b06a489211f982604a25338aed146c529c77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6Fmg7EY8xlqvBy1axnxafQ12GFK5CU/DWHbsWZAqeC3waC6hy3s2wqY1uuOPjegc6QWRKjUcVND9WOdZyM4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:29:03.707051Z","bundle_sha256":"024c3ed406a2a8994eb128c93bfb575f3199faed6371c1d03f06c95249fb819d"}}