{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KFOIBYQJ6CFNPZYOVA33IV2BV4","short_pith_number":"pith:KFOIBYQJ","schema_version":"1.0","canonical_sha256":"515c80e209f08ad7e70ea837b45741af19e6becd8a58546cb450527ee8d118da","source":{"kind":"arxiv","id":"2408.16991","version":1},"attestation_state":"computed","paper":{"title":"Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jaein Kim, Richong Zhang, Zhijie Nie, Zhongyuan Wang","submitted_at":"2024-08-30T03:38:37Z","abstract_excerpt":"Recent Text-to-SQL methods leverage large language models (LLMs) by incorporating feedback from the database management system. While these methods effectively address execution errors in SQL queries, they struggle with database mismatches -- errors that do not trigger execution exceptions. Database mismatches include issues such as condition mismatches and stricter constraint mismatches, both of which are more prevalent in real-world scenarios. To address these challenges, we propose a tool-assisted agent framework for SQL inspection and refinement, equipping the LLM-based agent with two spec"},"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":"2408.16991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-30T03:38:37Z","cross_cats_sorted":[],"title_canon_sha256":"a8d975e03762dfe86d633f7f422c1b010cceacebc212bd0eff0e8e273eaa03ea","abstract_canon_sha256":"c6bb1eafac986ff12b6fd50d402e7b53e45346e9ac5dfb8a3823b082e2e7a3de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:09.154813Z","signature_b64":"6unXSkird5CPhf4GtPSgGCRefsmPnYKhbr1H0oVMCHV+uZNrzCiYYUpwwMmxQF5cDsc3X9fshmO0sLOPb/onCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"515c80e209f08ad7e70ea837b45741af19e6becd8a58546cb450527ee8d118da","last_reissued_at":"2026-07-05T09:01:09.154342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:09.154342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jaein Kim, Richong Zhang, Zhijie Nie, Zhongyuan Wang","submitted_at":"2024-08-30T03:38:37Z","abstract_excerpt":"Recent Text-to-SQL methods leverage large language models (LLMs) by incorporating feedback from the database management system. While these methods effectively address execution errors in SQL queries, they struggle with database mismatches -- errors that do not trigger execution exceptions. Database mismatches include issues such as condition mismatches and stricter constraint mismatches, both of which are more prevalent in real-world scenarios. To address these challenges, we propose a tool-assisted agent framework for SQL inspection and refinement, equipping the LLM-based agent with two spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16991","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/2408.16991/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":"2408.16991","created_at":"2026-07-05T09:01:09.154400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.16991v1","created_at":"2026-07-05T09:01:09.154400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16991","created_at":"2026-07-05T09:01:09.154400+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFOIBYQJ6CFN","created_at":"2026-07-05T09:01:09.154400+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFOIBYQJ6CFNPZYO","created_at":"2026-07-05T09:01:09.154400+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFOIBYQJ","created_at":"2026-07-05T09:01:09.154400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.00709","citing_title":"RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":206,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4","json":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4.json","graph_json":"https://pith.science/api/pith-number/KFOIBYQJ6CFNPZYOVA33IV2BV4/graph.json","events_json":"https://pith.science/api/pith-number/KFOIBYQJ6CFNPZYOVA33IV2BV4/events.json","paper":"https://pith.science/paper/KFOIBYQJ"},"agent_actions":{"view_html":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4","download_json":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4.json","view_paper":"https://pith.science/paper/KFOIBYQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.16991&json=true","fetch_graph":"https://pith.science/api/pith-number/KFOIBYQJ6CFNPZYOVA33IV2BV4/graph.json","fetch_events":"https://pith.science/api/pith-number/KFOIBYQJ6CFNPZYOVA33IV2BV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4/action/storage_attestation","attest_author":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4/action/author_attestation","sign_citation":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4/action/citation_signature","submit_replication":"https://pith.science/pith/KFOIBYQJ6CFNPZYOVA33IV2BV4/action/replication_record"}},"created_at":"2026-07-05T09:01:09.154400+00:00","updated_at":"2026-07-05T09:01:09.154400+00:00"}