{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7CLBF52STB74EYWSG2UWSE2YHK","short_pith_number":"pith:7CLBF52S","schema_version":"1.0","canonical_sha256":"f89612f752987fc262d236a96913583aa8469642b1e211189d6162d43ad33c85","source":{"kind":"arxiv","id":"2406.11434","version":1},"attestation_state":"computed","paper":{"title":"DB-GPT-Hub: Towards Open Benchmarking Text-to-SQL Empowered by Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Caigai Jiang, Danrui Qi, Fan Zhou, Faqiang Chen, Ganglin Wei, Gangwei Jiang, Hongyang Zhang, Siqiao Xue, Wang Zhao, Wenhui Shi, Zhixuan Chu","submitted_at":"2024-06-17T11:40:41Z","abstract_excerpt":"Large language models (LLMs) becomes the dominant paradigm for the challenging task of text-to-SQL. LLM-empowered text-to-SQL methods are typically categorized into prompting-based and tuning approaches. Compared to prompting-based methods, benchmarking fine-tuned LLMs for text-to-SQL is important yet under-explored, partially attributed to the prohibitively high computational cost. In this paper, we present DB-GPT-Hub, an open benchmark suite for LLM-empowered text-to-SQL, which primarily focuses on tuning LLMs at large scales. The proposed benchmark consists of: 1. a standardized and compreh"},"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":"2406.11434","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-06-17T11:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"f72d5dea1b60aa7afdedefa8ebbe4f751f4daddabf6c5ca7c8ed22366181c81b","abstract_canon_sha256":"828c9f29a896557329a6358e17ff276c44b9e4d8c6d730d341988c46bbe183e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:53.332484Z","signature_b64":"i7MSuMD7vGapafQAjTVDAighde8MgYrwY5Agnbtufmnvkx3Oak0jUcy88Z0A/KRfwIID/BCl5iM/iCAH4CcPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f89612f752987fc262d236a96913583aa8469642b1e211189d6162d43ad33c85","last_reissued_at":"2026-07-05T08:32:53.331977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:53.331977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DB-GPT-Hub: Towards Open Benchmarking Text-to-SQL Empowered by Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Caigai Jiang, Danrui Qi, Fan Zhou, Faqiang Chen, Ganglin Wei, Gangwei Jiang, Hongyang Zhang, Siqiao Xue, Wang Zhao, Wenhui Shi, Zhixuan Chu","submitted_at":"2024-06-17T11:40:41Z","abstract_excerpt":"Large language models (LLMs) becomes the dominant paradigm for the challenging task of text-to-SQL. LLM-empowered text-to-SQL methods are typically categorized into prompting-based and tuning approaches. Compared to prompting-based methods, benchmarking fine-tuned LLMs for text-to-SQL is important yet under-explored, partially attributed to the prohibitively high computational cost. In this paper, we present DB-GPT-Hub, an open benchmark suite for LLM-empowered text-to-SQL, which primarily focuses on tuning LLMs at large scales. The proposed benchmark consists of: 1. a standardized and compreh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11434","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/2406.11434/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":"2406.11434","created_at":"2026-07-05T08:32:53.332038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11434v1","created_at":"2026-07-05T08:32:53.332038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11434","created_at":"2026-07-05T08:32:53.332038+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CLBF52STB74","created_at":"2026-07-05T08:32:53.332038+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CLBF52STB74EYWS","created_at":"2026-07-05T08:32:53.332038+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CLBF52S","created_at":"2026-07-05T08:32:53.332038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":206,"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":221,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK","json":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK.json","graph_json":"https://pith.science/api/pith-number/7CLBF52STB74EYWSG2UWSE2YHK/graph.json","events_json":"https://pith.science/api/pith-number/7CLBF52STB74EYWSG2UWSE2YHK/events.json","paper":"https://pith.science/paper/7CLBF52S"},"agent_actions":{"view_html":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK","download_json":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK.json","view_paper":"https://pith.science/paper/7CLBF52S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11434&json=true","fetch_graph":"https://pith.science/api/pith-number/7CLBF52STB74EYWSG2UWSE2YHK/graph.json","fetch_events":"https://pith.science/api/pith-number/7CLBF52STB74EYWSG2UWSE2YHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK/action/storage_attestation","attest_author":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK/action/author_attestation","sign_citation":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK/action/citation_signature","submit_replication":"https://pith.science/pith/7CLBF52STB74EYWSG2UWSE2YHK/action/replication_record"}},"created_at":"2026-07-05T08:32:53.332038+00:00","updated_at":"2026-07-05T08:32:53.332038+00:00"}