{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IJYMPJBO2SMPX7JSBGNL5P7LX5","short_pith_number":"pith:IJYMPJBO","schema_version":"1.0","canonical_sha256":"4270c7a42ed498fbfd32099abebfebbf6276345e1889955a373b1beab0a27e9c","source":{"kind":"arxiv","id":"2409.02038","version":3},"attestation_state":"computed","paper":{"title":"BEAVER: An Enterprise Benchmark for Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"\\c{C}a\\u{g}atay Demiralp, Devin Yang, Fabian Wenz, Michael Cafarella, Michael Stonebraker, Nesime Tatbul, Peter Baile Chen, Weiyue Li, Yi Zhang","submitted_at":"2024-09-03T16:37:45Z","abstract_excerpt":"Existing text-to-SQL benchmarks have largely been constructed from public databases with well-structured schemas and simplistic question-SQL pairs. While large language models (LLMs) excel on these settings, their efficacy in complex private enterprise environments, characterized by intricate schemas, domain knowledge, and analytical user queries involving sophisticated structures and functions, remains unproven. To bridge this gap, we introduce BEAVER, the first text-to-SQL benchmark derived from private data warehouses. It comprises 9128 question-SQL pairs sourced from real-world query logs "},"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":"2409.02038","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-03T16:37:45Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"66ca5b55c7eba267765f19434826d3a10d1369315cac02f2b75a92e1112b29d7","abstract_canon_sha256":"74f2fc0bcd4e54a15a24bdce4d5aad8118df670d26891bbbdd4289bad80e3864"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:39.599854Z","signature_b64":"aEjLezU3C/P3nkZzHFaPdyJflKpLHpk2+OxGntT9+7ITbY8jYELD6vT2PLoSyd1WMxiwkJW5CxHUz3z08G2eCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4270c7a42ed498fbfd32099abebfebbf6276345e1889955a373b1beab0a27e9c","last_reissued_at":"2026-05-18T02:44:39.599380Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:39.599380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BEAVER: An Enterprise Benchmark for Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"\\c{C}a\\u{g}atay Demiralp, Devin Yang, Fabian Wenz, Michael Cafarella, Michael Stonebraker, Nesime Tatbul, Peter Baile Chen, Weiyue Li, Yi Zhang","submitted_at":"2024-09-03T16:37:45Z","abstract_excerpt":"Existing text-to-SQL benchmarks have largely been constructed from public databases with well-structured schemas and simplistic question-SQL pairs. While large language models (LLMs) excel on these settings, their efficacy in complex private enterprise environments, characterized by intricate schemas, domain knowledge, and analytical user queries involving sophisticated structures and functions, remains unproven. To bridge this gap, we introduce BEAVER, the first text-to-SQL benchmark derived from private data warehouses. It comprises 9128 question-SQL pairs sourced from real-world query logs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02038","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":""},"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":"2409.02038","created_at":"2026-05-18T02:44:39.599463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02038v3","created_at":"2026-05-18T02:44:39.599463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02038","created_at":"2026-05-18T02:44:39.599463+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJYMPJBO2SMP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJYMPJBO2SMPX7JS","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJYMPJBO","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2605.18766","citing_title":"Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Method","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2603.02537","citing_title":"Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21413","citing_title":"An Alternate Agentic AI Architecture (It's About the Data)","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00628","citing_title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":111,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":126,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17771","citing_title":"SPENCE: A Syntactic Probe for Detecting Contamination in NL2SQL Benchmarks","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21214","citing_title":"A Demonstration of SQLyzr: A Platform for Fine-Grained Text-to-SQL Evaluation and Analysis","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5","json":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5.json","graph_json":"https://pith.science/api/pith-number/IJYMPJBO2SMPX7JSBGNL5P7LX5/graph.json","events_json":"https://pith.science/api/pith-number/IJYMPJBO2SMPX7JSBGNL5P7LX5/events.json","paper":"https://pith.science/paper/IJYMPJBO"},"agent_actions":{"view_html":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5","download_json":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5.json","view_paper":"https://pith.science/paper/IJYMPJBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02038&json=true","fetch_graph":"https://pith.science/api/pith-number/IJYMPJBO2SMPX7JSBGNL5P7LX5/graph.json","fetch_events":"https://pith.science/api/pith-number/IJYMPJBO2SMPX7JSBGNL5P7LX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5/action/storage_attestation","attest_author":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5/action/author_attestation","sign_citation":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5/action/citation_signature","submit_replication":"https://pith.science/pith/IJYMPJBO2SMPX7JSBGNL5P7LX5/action/replication_record"}},"created_at":"2026-05-18T02:44:39.599463+00:00","updated_at":"2026-05-18T02:44:39.599463+00:00"}