{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4XRNFI5DDEZFLDUXHP6SF2DCTX","short_pith_number":"pith:4XRNFI5D","schema_version":"1.0","canonical_sha256":"e5e2d2a3a31932558e973bfd22e8629df1d4e1a1679d27a3c631038481eeb121","source":{"kind":"arxiv","id":"2312.03463","version":3},"attestation_state":"computed","paper":{"title":"DBCopilot: Natural Language Querying over Massive Databases via Schema Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Hao Wang, Hongyu Lin, Le Sun, Tianshu Wang, Xianpei Han, Xiaoyang Chen, Zhenyu Zeng","submitted_at":"2023-12-06T12:37:28Z","abstract_excerpt":"The development of Natural Language Interfaces to Databases (NLIDBs) has been greatly advanced by the advent of large language models (LLMs), which provide an intuitive way to translate natural language (NL) questions into Structured Query Language (SQL) queries. While significant progress has been made in LLM-based NL2SQL, existing approaches face several challenges in real-world scenarios of natural language querying over massive databases. In this paper, we present DBCopilot, a framework that addresses these challenges by employing a compact and flexible copilot model for routing over massi"},"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":"2312.03463","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T12:37:28Z","cross_cats_sorted":["cs.DB","cs.IR"],"title_canon_sha256":"97f49f4d013b59ea03add87641587d828597fd3e855848cda2caf021232504eb","abstract_canon_sha256":"a401e4836c51617083d48ec7d016869c009ffecd286f2b0731986434bdda9a7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:07.173223Z","signature_b64":"udSlUAV1RuPEmrkDgOnh9rgnmljBcB/gmv9LZ4sGX5AHpTyzVoYslWn3aTOlAjSOuklrp+uO6tlghPYnt9RXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5e2d2a3a31932558e973bfd22e8629df1d4e1a1679d27a3c631038481eeb121","last_reissued_at":"2026-07-05T10:18:07.172745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:07.172745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DBCopilot: Natural Language Querying over Massive Databases via Schema Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Hao Wang, Hongyu Lin, Le Sun, Tianshu Wang, Xianpei Han, Xiaoyang Chen, Zhenyu Zeng","submitted_at":"2023-12-06T12:37:28Z","abstract_excerpt":"The development of Natural Language Interfaces to Databases (NLIDBs) has been greatly advanced by the advent of large language models (LLMs), which provide an intuitive way to translate natural language (NL) questions into Structured Query Language (SQL) queries. While significant progress has been made in LLM-based NL2SQL, existing approaches face several challenges in real-world scenarios of natural language querying over massive databases. In this paper, we present DBCopilot, a framework that addresses these challenges by employing a compact and flexible copilot model for routing over massi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03463","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/2312.03463/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":"2312.03463","created_at":"2026-07-05T10:18:07.172798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03463v3","created_at":"2026-07-05T10:18:07.172798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03463","created_at":"2026-07-05T10:18:07.172798+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XRNFI5DDEZF","created_at":"2026-07-05T10:18:07.172798+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XRNFI5DDEZFLDUX","created_at":"2026-07-05T10:18:07.172798+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XRNFI5D","created_at":"2026-07-05T10:18:07.172798+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":169,"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":184,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX","json":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX.json","graph_json":"https://pith.science/api/pith-number/4XRNFI5DDEZFLDUXHP6SF2DCTX/graph.json","events_json":"https://pith.science/api/pith-number/4XRNFI5DDEZFLDUXHP6SF2DCTX/events.json","paper":"https://pith.science/paper/4XRNFI5D"},"agent_actions":{"view_html":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX","download_json":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX.json","view_paper":"https://pith.science/paper/4XRNFI5D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03463&json=true","fetch_graph":"https://pith.science/api/pith-number/4XRNFI5DDEZFLDUXHP6SF2DCTX/graph.json","fetch_events":"https://pith.science/api/pith-number/4XRNFI5DDEZFLDUXHP6SF2DCTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX/action/storage_attestation","attest_author":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX/action/author_attestation","sign_citation":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX/action/citation_signature","submit_replication":"https://pith.science/pith/4XRNFI5DDEZFLDUXHP6SF2DCTX/action/replication_record"}},"created_at":"2026-07-05T10:18:07.172798+00:00","updated_at":"2026-07-05T10:18:07.172798+00:00"}