{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WHRKSJ73N37O7UBIHHWQJXAC3L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5a34a3a39aeb614a2cbc28f8edce5ad7a77dac6819a4700b46435172e0802e0b","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T07:00:58Z","title_canon_sha256":"beb01683de21808d9d6d60d83581312c521895053fd344a07283899029531237"},"schema_version":"1.0","source":{"id":"2402.16347","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16347","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16347v1","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16347","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"WHRKSJ73N37O","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"WHRKSJ73N37O7UBI","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"WHRKSJ73","created_at":"2026-07-05T07:49:20Z"}],"graph_snapshots":[{"event_id":"sha256:b98130c7b9a7b1a7eacda59f57092ba9df88296990e97be6001faac61a163d94","target":"graph","created_at":"2026-07-05T07:49:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.16347/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Cuiping Li, Hanbing Liu, Haoyang Li, Hong Chen, Hongyan Pan, Jing Zhang, Ju Fan, Jun Zhu, Renjie Wei, Xiaokang Zhang","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T07:00:58Z","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16347","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7a39aa604c02f935243afaecbe671d3170f0065f1eeb32431b6fdd40504d7d83","target":"record","created_at":"2026-07-05T07:49:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5a34a3a39aeb614a2cbc28f8edce5ad7a77dac6819a4700b46435172e0802e0b","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T07:00:58Z","title_canon_sha256":"beb01683de21808d9d6d60d83581312c521895053fd344a07283899029531237"},"schema_version":"1.0","source":{"id":"2402.16347","kind":"arxiv","version":1}},"canonical_sha256":"b1e2a927fb6efeefd02839ed04dc02dad3453972d5a86acdd9771f3d13af7eb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1e2a927fb6efeefd02839ed04dc02dad3453972d5a86acdd9771f3d13af7eb4","first_computed_at":"2026-07-05T07:49:20.575249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:20.575249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CPywQyMnzBWGPJded8BV08VtwcRcgNXZTjdfCzFGczMWWptUDnLtXs1NtjPGAy6k1yV5q3coqUe6lDRHqgUXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:20.575710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16347","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a39aa604c02f935243afaecbe671d3170f0065f1eeb32431b6fdd40504d7d83","sha256:b98130c7b9a7b1a7eacda59f57092ba9df88296990e97be6001faac61a163d94"],"state_sha256":"4a34caa065cc7b901738a6cf5a3afec18f09cd8424e970863b1229d21bc5b14d"}