{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5RC6S2FSFEUPQV7LXA7PCC4RGI","short_pith_number":"pith:5RC6S2FS","schema_version":"1.0","canonical_sha256":"ec45e968b22928f857ebb83ef10b91321fdb4322e40e6159377e1440392d811b","source":{"kind":"arxiv","id":"2502.14913","version":1},"attestation_state":"computed","paper":{"title":"OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Guangwei Xu, Lingyan Zhao, Ruijie Guo, Xiangjin Xie","submitted_at":"2025-02-19T07:51:50Z","abstract_excerpt":"Although multi-agent collaborative Large Language Models (LLMs) have achieved significant breakthroughs in the Text-to-SQL task, their performance is still constrained by various factors. These factors include the incompleteness of the framework, failure to follow instructions, and model hallucination problems. To address these problems, we propose OpenSearch-SQL, which divides the Text-to-SQL task into four main modules: Preprocessing, Extraction, Generation, and Refinement, along with an Alignment module based on a consistency alignment mechanism. This architecture aligns the inputs and outp"},"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":"2502.14913","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T07:51:50Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"efa58b44ec13f3f16893ff1a644b2c21dd9a31bb7a1855d425ebe1e01350e315","abstract_canon_sha256":"bae486474e81327d4ec5d87f05c3246c8449c6bbf15a83c54f02f85535fd5821"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:55.422159Z","signature_b64":"AIkpwBJE5G2bOW/Dm3ZLX4D8daGbkc1vbmX6VVfG9i56GSiFhOIqe6huIVmUVyl8ze018CKip0JKLIRo1FdoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec45e968b22928f857ebb83ef10b91321fdb4322e40e6159377e1440392d811b","last_reissued_at":"2026-07-05T10:17:55.421640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:55.421640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Guangwei Xu, Lingyan Zhao, Ruijie Guo, Xiangjin Xie","submitted_at":"2025-02-19T07:51:50Z","abstract_excerpt":"Although multi-agent collaborative Large Language Models (LLMs) have achieved significant breakthroughs in the Text-to-SQL task, their performance is still constrained by various factors. These factors include the incompleteness of the framework, failure to follow instructions, and model hallucination problems. To address these problems, we propose OpenSearch-SQL, which divides the Text-to-SQL task into four main modules: Preprocessing, Extraction, Generation, and Refinement, along with an Alignment module based on a consistency alignment mechanism. This architecture aligns the inputs and outp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14913","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/2502.14913/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":"2502.14913","created_at":"2026-07-05T10:17:55.421702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14913v1","created_at":"2026-07-05T10:17:55.421702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14913","created_at":"2026-07-05T10:17:55.421702+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RC6S2FSFEUP","created_at":"2026-07-05T10:17:55.421702+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RC6S2FSFEUPQV7L","created_at":"2026-07-05T10:17:55.421702+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RC6S2FS","created_at":"2026-07-05T10:17:55.421702+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":105,"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":120,"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":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI","json":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI.json","graph_json":"https://pith.science/api/pith-number/5RC6S2FSFEUPQV7LXA7PCC4RGI/graph.json","events_json":"https://pith.science/api/pith-number/5RC6S2FSFEUPQV7LXA7PCC4RGI/events.json","paper":"https://pith.science/paper/5RC6S2FS"},"agent_actions":{"view_html":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI","download_json":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI.json","view_paper":"https://pith.science/paper/5RC6S2FS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14913&json=true","fetch_graph":"https://pith.science/api/pith-number/5RC6S2FSFEUPQV7LXA7PCC4RGI/graph.json","fetch_events":"https://pith.science/api/pith-number/5RC6S2FSFEUPQV7LXA7PCC4RGI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI/action/storage_attestation","attest_author":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI/action/author_attestation","sign_citation":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI/action/citation_signature","submit_replication":"https://pith.science/pith/5RC6S2FSFEUPQV7LXA7PCC4RGI/action/replication_record"}},"created_at":"2026-07-05T10:17:55.421702+00:00","updated_at":"2026-07-05T10:17:55.421702+00:00"}