{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VTEWFITCQFNXP76UMLXH2WPUWD","short_pith_number":"pith:VTEWFITC","canonical_record":{"source":{"id":"2508.12769","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T09:43:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"20e3257a51c36ad6a626fffb9b5f43eaab59fd5f8b49ca5b8021b435f9dbfe69","abstract_canon_sha256":"f2e7c838d9a1d72b28c4af86550c3cee6978f1e48d71700ab43b68d7937d2a9f"},"schema_version":"1.0"},"canonical_sha256":"acc962a262815b77ffd462ee7d59f4b0e80a1bce4ed47163c0480d07476d4baf","source":{"kind":"arxiv","id":"2508.12769","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12769","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12769v3","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12769","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_12","alias_value":"VTEWFITCQFNX","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_16","alias_value":"VTEWFITCQFNXP76U","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_8","alias_value":"VTEWFITC","created_at":"2026-07-05T11:56:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VTEWFITCQFNXP76UMLXH2WPUWD","target":"record","payload":{"canonical_record":{"source":{"id":"2508.12769","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T09:43:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"20e3257a51c36ad6a626fffb9b5f43eaab59fd5f8b49ca5b8021b435f9dbfe69","abstract_canon_sha256":"f2e7c838d9a1d72b28c4af86550c3cee6978f1e48d71700ab43b68d7937d2a9f"},"schema_version":"1.0"},"canonical_sha256":"acc962a262815b77ffd462ee7d59f4b0e80a1bce4ed47163c0480d07476d4baf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:23.399768Z","signature_b64":"3F0Eo+albld8MulGeKTWBnEg4GB18BdhVILt53huEdL8B7SBZu3jA3FmjwtZhdtJ6ObBm0VnpDB8iLpe/PscAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc962a262815b77ffd462ee7d59f4b0e80a1bce4ed47163c0480d07476d4baf","last_reissued_at":"2026-07-05T11:56:23.399368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:23.399368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.12769","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:56:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L4axLaBA/X9/QoOlW009ThsgvMv2lqapmYg6xgvvgnPCxwEmXMNqIFxartKK7Sf570UBr0fkMU24JlfhTIcUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:23:01.549110Z"},"content_sha256":"ff0defb63ee8c60fc14476472488b2bc921b9f69dc62b2b0f70330679775359c","schema_version":"1.0","event_id":"sha256:ff0defb63ee8c60fc14476472488b2bc921b9f69dc62b2b0f70330679775359c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VTEWFITCQFNXP76UMLXH2WPUWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuanyi Liu, Liang Yan, Peiyi Han, Shaoming Duan, Yuhao Zhang, Zewu Peng, Zhibin Zhu, Zirui Wang","submitted_at":"2025-08-18T09:43:07Z","abstract_excerpt":"Recent advances in large language models (LLMs) have significantly improved the accuracy of Text-to-SQL systems. However, a critical challenge remains: the semantic mismatch between natural language questions (NLQs) and their corresponding SQL queries. This issue is exacerbated in large-scale databases, where semantically similar attributes hinder schema linking and semantic drift during SQL generation, ultimately reducing model accuracy. To address these challenges, we introduce CRED-SQL, a framework designed for large-scale databases that integrates Cluster Retrieval and Execution Descriptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12769","kind":"arxiv","version":3},"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/2508.12769/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":"2026-07-05T11:56:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+YH8Zm2jjszp1eeu5xKOjMVA41VFdvt6gBeWEcKXaZsmHr/wBbjPZKvJ8gRteWDEHBRisE9bJewsYtB6cBQbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T14:23:01.550106Z"},"content_sha256":"9ba8ff7b5554f19d0dacc04be65d1039ad73e9625d644cb2c8413f2017666480","schema_version":"1.0","event_id":"sha256:9ba8ff7b5554f19d0dacc04be65d1039ad73e9625d644cb2c8413f2017666480"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTEWFITCQFNXP76UMLXH2WPUWD/bundle.json","state_url":"https://pith.science/pith/VTEWFITCQFNXP76UMLXH2WPUWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTEWFITCQFNXP76UMLXH2WPUWD/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":"2026-08-17T14:23:01Z","links":{"resolver":"https://pith.science/pith/VTEWFITCQFNXP76UMLXH2WPUWD","bundle":"https://pith.science/pith/VTEWFITCQFNXP76UMLXH2WPUWD/bundle.json","state":"https://pith.science/pith/VTEWFITCQFNXP76UMLXH2WPUWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTEWFITCQFNXP76UMLXH2WPUWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VTEWFITCQFNXP76UMLXH2WPUWD","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":"f2e7c838d9a1d72b28c4af86550c3cee6978f1e48d71700ab43b68d7937d2a9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T09:43:07Z","title_canon_sha256":"20e3257a51c36ad6a626fffb9b5f43eaab59fd5f8b49ca5b8021b435f9dbfe69"},"schema_version":"1.0","source":{"id":"2508.12769","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12769","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12769v3","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12769","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_12","alias_value":"VTEWFITCQFNX","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_16","alias_value":"VTEWFITCQFNXP76U","created_at":"2026-07-05T11:56:23Z"},{"alias_kind":"pith_short_8","alias_value":"VTEWFITC","created_at":"2026-07-05T11:56:23Z"}],"graph_snapshots":[{"event_id":"sha256:9ba8ff7b5554f19d0dacc04be65d1039ad73e9625d644cb2c8413f2017666480","target":"graph","created_at":"2026-07-05T11:56:23Z","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/2508.12769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have significantly improved the accuracy of Text-to-SQL systems. However, a critical challenge remains: the semantic mismatch between natural language questions (NLQs) and their corresponding SQL queries. This issue is exacerbated in large-scale databases, where semantically similar attributes hinder schema linking and semantic drift during SQL generation, ultimately reducing model accuracy. To address these challenges, we introduce CRED-SQL, a framework designed for large-scale databases that integrates Cluster Retrieval and Execution Descriptio","authors_text":"Chuanyi Liu, Liang Yan, Peiyi Han, Shaoming Duan, Yuhao Zhang, Zewu Peng, Zhibin Zhu, Zirui Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T09:43:07Z","title":"CRED-SQL: Enhancing Real-world Large Scale Database Text-to-SQL Parsing through Cluster Retrieval and Execution Description"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12769","kind":"arxiv","version":3},"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:ff0defb63ee8c60fc14476472488b2bc921b9f69dc62b2b0f70330679775359c","target":"record","created_at":"2026-07-05T11:56:23Z","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":"f2e7c838d9a1d72b28c4af86550c3cee6978f1e48d71700ab43b68d7937d2a9f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-18T09:43:07Z","title_canon_sha256":"20e3257a51c36ad6a626fffb9b5f43eaab59fd5f8b49ca5b8021b435f9dbfe69"},"schema_version":"1.0","source":{"id":"2508.12769","kind":"arxiv","version":3}},"canonical_sha256":"acc962a262815b77ffd462ee7d59f4b0e80a1bce4ed47163c0480d07476d4baf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acc962a262815b77ffd462ee7d59f4b0e80a1bce4ed47163c0480d07476d4baf","first_computed_at":"2026-07-05T11:56:23.399368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:23.399368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3F0Eo+albld8MulGeKTWBnEg4GB18BdhVILt53huEdL8B7SBZu3jA3FmjwtZhdtJ6ObBm0VnpDB8iLpe/PscAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:23.399768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12769","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff0defb63ee8c60fc14476472488b2bc921b9f69dc62b2b0f70330679775359c","sha256:9ba8ff7b5554f19d0dacc04be65d1039ad73e9625d644cb2c8413f2017666480"],"state_sha256":"5230ec7d9cd9b935151f7736dbf3c03d9fe811229514b3defd56f387b3e46b97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOhC5fgLts8BPz0iWJ6OS6D86h/HZZzt7bk6pFGQqlaInqjflk4yv4MfDhZNCec7JCirIZhmOSJCJ9q2b2SHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T14:23:01.562570Z","bundle_sha256":"05dfb2c6ad986a6770365aae045be101134e86e457e8d17581715db38886e08b"}}