{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RWWH6OLQYN6EHR7XHONABQTDT4","short_pith_number":"pith:RWWH6OLQ","schema_version":"1.0","canonical_sha256":"8dac7f3970c37c43c7f73b9a00c2639f0ef68f0936e0bd439a68d39066bd2656","source":{"kind":"arxiv","id":"2410.18406","version":1},"attestation_state":"computed","paper":{"title":"MoMQ: Mixture-of-Experts Enhances Multi-Dialect Query Generation across Relational and Non-Relational Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinyang Gao, Yifu Liu, Yu Li, Zhiling Luo, Zhisheng Lin","submitted_at":"2024-10-24T03:42:43Z","abstract_excerpt":"The improvement in translating natural language to structured query language (SQL) can be attributed to the advancements in large language models (LLMs). Open-source LLMs, tailored for specific database dialects such as MySQL, have shown great performance. However, cloud service providers are looking for a unified database manager service (e.g., Cosmos DB from Azure, Amazon Aurora from AWS, Lindorm from AlibabaCloud) that can support multiple dialects. This requirement has led to the concept of multi-dialect query generation, which presents challenges to LLMs. These challenges include syntacti"},"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":"2410.18406","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T03:42:43Z","cross_cats_sorted":["cs.AI","cs.DB","cs.LG"],"title_canon_sha256":"1d9c9f4a6c3b2783b2c75462ae042003c857219c86b5ad890bc072f43fa9cced","abstract_canon_sha256":"ca0e9e0e634329ce64a1494070e102af51879b81c4041437ad0f2850adb61538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:07.853143Z","signature_b64":"VC11Way55GbAYs01AmRiQM5dF9aZu0zEAnH1Omq1vgf9HoDCW9LZQxJAG8C1znkgxtazfGerQAAtHhagiFrOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dac7f3970c37c43c7f73b9a00c2639f0ef68f0936e0bd439a68d39066bd2656","last_reissued_at":"2026-07-05T09:25:07.852752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:07.852752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoMQ: Mixture-of-Experts Enhances Multi-Dialect Query Generation across Relational and Non-Relational Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinyang Gao, Yifu Liu, Yu Li, Zhiling Luo, Zhisheng Lin","submitted_at":"2024-10-24T03:42:43Z","abstract_excerpt":"The improvement in translating natural language to structured query language (SQL) can be attributed to the advancements in large language models (LLMs). Open-source LLMs, tailored for specific database dialects such as MySQL, have shown great performance. However, cloud service providers are looking for a unified database manager service (e.g., Cosmos DB from Azure, Amazon Aurora from AWS, Lindorm from AlibabaCloud) that can support multiple dialects. This requirement has led to the concept of multi-dialect query generation, which presents challenges to LLMs. These challenges include syntacti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18406","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/2410.18406/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":"2410.18406","created_at":"2026-07-05T09:25:07.852809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18406v1","created_at":"2026-07-05T09:25:07.852809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18406","created_at":"2026-07-05T09:25:07.852809+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWWH6OLQYN6E","created_at":"2026-07-05T09:25:07.852809+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWWH6OLQYN6EHR7X","created_at":"2026-07-05T09:25:07.852809+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWWH6OLQ","created_at":"2026-07-05T09:25:07.852809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.04701","citing_title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","ref_index":24,"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":217,"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":232,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4","json":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4.json","graph_json":"https://pith.science/api/pith-number/RWWH6OLQYN6EHR7XHONABQTDT4/graph.json","events_json":"https://pith.science/api/pith-number/RWWH6OLQYN6EHR7XHONABQTDT4/events.json","paper":"https://pith.science/paper/RWWH6OLQ"},"agent_actions":{"view_html":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4","download_json":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4.json","view_paper":"https://pith.science/paper/RWWH6OLQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18406&json=true","fetch_graph":"https://pith.science/api/pith-number/RWWH6OLQYN6EHR7XHONABQTDT4/graph.json","fetch_events":"https://pith.science/api/pith-number/RWWH6OLQYN6EHR7XHONABQTDT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4/action/storage_attestation","attest_author":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4/action/author_attestation","sign_citation":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4/action/citation_signature","submit_replication":"https://pith.science/pith/RWWH6OLQYN6EHR7XHONABQTDT4/action/replication_record"}},"created_at":"2026-07-05T09:25:07.852809+00:00","updated_at":"2026-07-05T09:25:07.852809+00:00"}