{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HE5ECJ4HDU4V2FN2TXFAUWGDJS","short_pith_number":"pith:HE5ECJ4H","schema_version":"1.0","canonical_sha256":"393a4127871d395d15ba9dca0a58c34ca7a79c257fdb57ac1c094340b673b371","source":{"kind":"arxiv","id":"2405.06674","version":1},"attestation_state":"computed","paper":{"title":"Open-SQL Framework: Enhancing Text-to-SQL on Open-source Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianbin Qin, Min Yang, Tianhao Qiu, Tianle Wang, Xiaojun Chen","submitted_at":"2024-05-04T15:40:17Z","abstract_excerpt":"Despite the success of large language models (LLMs) in Text-to-SQL tasks, open-source LLMs encounter challenges in contextual understanding and response coherence. To tackle these issues, we present \\ours, a systematic methodology tailored for Text-to-SQL with open-source LLMs. Our contributions include a comprehensive evaluation of open-source LLMs in Text-to-SQL tasks, the \\openprompt strategy for effective question representation, and novel strategies for supervised fine-tuning. We explore the benefits of Chain-of-Thought in step-by-step inference and propose the \\openexample method for enh"},"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":"2405.06674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-04T15:40:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"10aaf87cbd0ccf78dc6cac257120c4aeb37829725ae7f1be6bed4aea28efcf0d","abstract_canon_sha256":"b0a45766b7fd69eeb35cff3fb1b373e4c2111f4d224326a2a2654eedf74098d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:09.991489Z","signature_b64":"q8X0m0N8bPFkcarwCFAeZxBzLuiYGbL00gIVfCvY+YGL0Mmf9dvA/XVMMFgXKhHkfV0r5bSJtuSFlIn+3lZKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"393a4127871d395d15ba9dca0a58c34ca7a79c257fdb57ac1c094340b673b371","last_reissued_at":"2026-07-05T08:18:09.990852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:09.990852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-SQL Framework: Enhancing Text-to-SQL on Open-source Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianbin Qin, Min Yang, Tianhao Qiu, Tianle Wang, Xiaojun Chen","submitted_at":"2024-05-04T15:40:17Z","abstract_excerpt":"Despite the success of large language models (LLMs) in Text-to-SQL tasks, open-source LLMs encounter challenges in contextual understanding and response coherence. To tackle these issues, we present \\ours, a systematic methodology tailored for Text-to-SQL with open-source LLMs. Our contributions include a comprehensive evaluation of open-source LLMs in Text-to-SQL tasks, the \\openprompt strategy for effective question representation, and novel strategies for supervised fine-tuning. We explore the benefits of Chain-of-Thought in step-by-step inference and propose the \\openexample method for enh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06674","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/2405.06674/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":"2405.06674","created_at":"2026-07-05T08:18:09.990936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06674v1","created_at":"2026-07-05T08:18:09.990936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06674","created_at":"2026-07-05T08:18:09.990936+00:00"},{"alias_kind":"pith_short_12","alias_value":"HE5ECJ4HDU4V","created_at":"2026-07-05T08:18:09.990936+00:00"},{"alias_kind":"pith_short_16","alias_value":"HE5ECJ4HDU4V2FN2","created_at":"2026-07-05T08:18:09.990936+00:00"},{"alias_kind":"pith_short_8","alias_value":"HE5ECJ4H","created_at":"2026-07-05T08:18:09.990936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":170,"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":185,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08057","citing_title":"CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS","json":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS.json","graph_json":"https://pith.science/api/pith-number/HE5ECJ4HDU4V2FN2TXFAUWGDJS/graph.json","events_json":"https://pith.science/api/pith-number/HE5ECJ4HDU4V2FN2TXFAUWGDJS/events.json","paper":"https://pith.science/paper/HE5ECJ4H"},"agent_actions":{"view_html":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS","download_json":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS.json","view_paper":"https://pith.science/paper/HE5ECJ4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06674&json=true","fetch_graph":"https://pith.science/api/pith-number/HE5ECJ4HDU4V2FN2TXFAUWGDJS/graph.json","fetch_events":"https://pith.science/api/pith-number/HE5ECJ4HDU4V2FN2TXFAUWGDJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS/action/storage_attestation","attest_author":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS/action/author_attestation","sign_citation":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS/action/citation_signature","submit_replication":"https://pith.science/pith/HE5ECJ4HDU4V2FN2TXFAUWGDJS/action/replication_record"}},"created_at":"2026-07-05T08:18:09.990936+00:00","updated_at":"2026-07-05T08:18:09.990936+00:00"}