{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WHRKSJ73N37O7UBIHHWQJXAC3L","short_pith_number":"pith:WHRKSJ73","schema_version":"1.0","canonical_sha256":"b1e2a927fb6efeefd02839ed04dc02dad3453972d5a86acdd9771f3d13af7eb4","source":{"kind":"arxiv","id":"2402.16347","version":1},"attestation_state":"computed","paper":{"title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Cuiping Li, Hanbing Liu, Haoyang Li, Hong Chen, Hongyan Pan, Jing Zhang, Ju Fan, Jun Zhu, Renjie Wei, Xiaokang Zhang","submitted_at":"2024-02-26T07:00:58Z","abstract_excerpt":"Language models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). However, most of the state-of-the-art (SOTA) approaches rely on powerful yet closed-source large language models (LLMs), such as ChatGPT and GPT-4, which may have the limitations of unclear model architectures, data privacy risks, and expensive inference overheads. To address the limitations, we introduce CodeS, a series of pre-trained language models with parameters ranging from 1B to 15B, specifically designed for the text-to-SQL task. CodeS is a fully open-s"},"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":"2402.16347","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T07:00:58Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"beb01683de21808d9d6d60d83581312c521895053fd344a07283899029531237","abstract_canon_sha256":"5a34a3a39aeb614a2cbc28f8edce5ad7a77dac6819a4700b46435172e0802e0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:20.575710Z","signature_b64":"CPywQyMnzBWGPJded8BV08VtwcRcgNXZTjdfCzFGczMWWptUDnLtXs1NtjPGAy6k1yV5q3coqUe6lDRHqgUXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1e2a927fb6efeefd02839ed04dc02dad3453972d5a86acdd9771f3d13af7eb4","last_reissued_at":"2026-07-05T07:49:20.575249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:20.575249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Cuiping Li, Hanbing Liu, Haoyang Li, Hong Chen, Hongyan Pan, Jing Zhang, Ju Fan, Jun Zhu, Renjie Wei, Xiaokang Zhang","submitted_at":"2024-02-26T07:00:58Z","abstract_excerpt":"Language models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). However, most of the state-of-the-art (SOTA) approaches rely on powerful yet closed-source large language models (LLMs), such as ChatGPT and GPT-4, which may have the limitations of unclear model architectures, data privacy risks, and expensive inference overheads. To address the limitations, we introduce CodeS, a series of pre-trained language models with parameters ranging from 1B to 15B, specifically designed for the text-to-SQL task. CodeS is a fully open-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16347","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/2402.16347/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":"2402.16347","created_at":"2026-07-05T07:49:20.575305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16347v1","created_at":"2026-07-05T07:49:20.575305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16347","created_at":"2026-07-05T07:49:20.575305+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHRKSJ73N37O","created_at":"2026-07-05T07:49:20.575305+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHRKSJ73N37O7UBI","created_at":"2026-07-05T07:49:20.575305+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHRKSJ73","created_at":"2026-07-05T07:49:20.575305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05679","citing_title":"Data Flow Control: Data Safety Policies for AI Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":254,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28028","citing_title":"Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L","json":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L.json","graph_json":"https://pith.science/api/pith-number/WHRKSJ73N37O7UBIHHWQJXAC3L/graph.json","events_json":"https://pith.science/api/pith-number/WHRKSJ73N37O7UBIHHWQJXAC3L/events.json","paper":"https://pith.science/paper/WHRKSJ73"},"agent_actions":{"view_html":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L","download_json":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L.json","view_paper":"https://pith.science/paper/WHRKSJ73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16347&json=true","fetch_graph":"https://pith.science/api/pith-number/WHRKSJ73N37O7UBIHHWQJXAC3L/graph.json","fetch_events":"https://pith.science/api/pith-number/WHRKSJ73N37O7UBIHHWQJXAC3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L/action/storage_attestation","attest_author":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L/action/author_attestation","sign_citation":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L/action/citation_signature","submit_replication":"https://pith.science/pith/WHRKSJ73N37O7UBIHHWQJXAC3L/action/replication_record"}},"created_at":"2026-07-05T07:49:20.575305+00:00","updated_at":"2026-07-05T07:49:20.575305+00:00"}