{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q3PCYM4TDHPYDKOCJYIPWWQKEX","short_pith_number":"pith:Q3PCYM4T","schema_version":"1.0","canonical_sha256":"86de2c339319df81a9c24e10fb5a0a25e002fcb19dbeb5d445a676e0bd77c6df","source":{"kind":"arxiv","id":"2502.00675","version":5},"attestation_state":"computed","paper":{"title":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anupam Datta, Ashwin Ramachandran, Canwen Xu, Hao Zhang, Lanxiang Hu, Minghang Deng, Zhewei Yao","submitted_at":"2025-02-02T05:25:03Z","abstract_excerpt":"We present ReFoRCE, a Text-to-SQL agent that tops the Spider 2.0 leaderboard--a challenging benchmark reflecting complex, real-world Text-to-SQL scenarios. While Text-to-SQL systems enable natural language queries over structured databases, deploying them in enterprise environments remains difficult due to large, complex schemas (with over 1,000 columns), diverse SQL dialects (e.g., BigQuery, Snowflake), and sophisticated query requirements (e.g., transformations and analytics). ReFoRCE addresses these challenges through: (a) database information compression via pattern-based table grouping an"},"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":"2502.00675","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T05:25:03Z","cross_cats_sorted":[],"title_canon_sha256":"63e0307fa0bd047327bfd759e4b0ce560b4970722ad88cc890f854d7f60a5c2f","abstract_canon_sha256":"1fd07b30633338a0afe8ad63acaa22899810ba0bdcf3d7329dc61198ec3aba71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:19.183071Z","signature_b64":"xM6swR4WwzvDt9wP58B6jENXTQ/67LmaN+OsWdtDJ3yIR73bjoLNaluWs+idPIlSKN7FBOy6o4szdpXQ97SHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86de2c339319df81a9c24e10fb5a0a25e002fcb19dbeb5d445a676e0bd77c6df","last_reissued_at":"2026-07-05T11:15:19.182639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:19.182639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anupam Datta, Ashwin Ramachandran, Canwen Xu, Hao Zhang, Lanxiang Hu, Minghang Deng, Zhewei Yao","submitted_at":"2025-02-02T05:25:03Z","abstract_excerpt":"We present ReFoRCE, a Text-to-SQL agent that tops the Spider 2.0 leaderboard--a challenging benchmark reflecting complex, real-world Text-to-SQL scenarios. While Text-to-SQL systems enable natural language queries over structured databases, deploying them in enterprise environments remains difficult due to large, complex schemas (with over 1,000 columns), diverse SQL dialects (e.g., BigQuery, Snowflake), and sophisticated query requirements (e.g., transformations and analytics). ReFoRCE addresses these challenges through: (a) database information compression via pattern-based table grouping an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00675","kind":"arxiv","version":5},"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/2502.00675/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":"2502.00675","created_at":"2026-07-05T11:15:19.182698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00675v5","created_at":"2026-07-05T11:15:19.182698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00675","created_at":"2026-07-05T11:15:19.182698+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3PCYM4TDHPY","created_at":"2026-07-05T11:15:19.182698+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3PCYM4TDHPYDKOC","created_at":"2026-07-05T11:15:19.182698+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3PCYM4T","created_at":"2026-07-05T11:15:19.182698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06229","citing_title":"Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11424","citing_title":"SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31041","citing_title":"A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30862","citing_title":"Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26613","citing_title":"EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18768","citing_title":"ClinQueryAgent: A Conversational Agent for Population Health Management","ref_index":176,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19010","citing_title":"AgentNLQ: A General-Purpose Agent for Natural Language to SQL","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.17942","citing_title":"LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21480","citing_title":"Both Ends Count! Just How Good are LLM Agents at \"Text-to-Big SQL\"?","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02444","citing_title":"From Textual Columns to Query Plans: A Unified Relational-Semantic Execution Framework for Hybrid Query Processing","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16511","citing_title":"SQL Query Engine: A Self-Healing LLM Pipeline for Natural Language to PostgreSQL Translation","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX","json":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX.json","graph_json":"https://pith.science/api/pith-number/Q3PCYM4TDHPYDKOCJYIPWWQKEX/graph.json","events_json":"https://pith.science/api/pith-number/Q3PCYM4TDHPYDKOCJYIPWWQKEX/events.json","paper":"https://pith.science/paper/Q3PCYM4T"},"agent_actions":{"view_html":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX","download_json":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX.json","view_paper":"https://pith.science/paper/Q3PCYM4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00675&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3PCYM4TDHPYDKOCJYIPWWQKEX/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3PCYM4TDHPYDKOCJYIPWWQKEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX/action/storage_attestation","attest_author":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX/action/author_attestation","sign_citation":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX/action/citation_signature","submit_replication":"https://pith.science/pith/Q3PCYM4TDHPYDKOCJYIPWWQKEX/action/replication_record"}},"created_at":"2026-07-05T11:15:19.182698+00:00","updated_at":"2026-07-05T11:15:19.182698+00:00"}