{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XQJITP4WSPQV2SGCIMTR76OGII","short_pith_number":"pith:XQJITP4W","schema_version":"1.0","canonical_sha256":"bc1289bf9693e15d48c243271ff9c6423a38ff216aaf2ab0137a93fa22c5fd1b","source":{"kind":"arxiv","id":"2406.12692","version":3},"attestation_state":"computed","paper":{"title":"MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.HC"],"primary_cat":"cs.CL","authors_text":"Arian Askari, Christian Poelitz, Xinye Tang","submitted_at":"2024-06-18T15:06:06Z","abstract_excerpt":"Self-correction in text-to-SQL is the process of prompting large language model (LLM) to revise its previously incorrectly generated SQL, and commonly relies on manually crafted self-correction guidelines by human experts that are not only labor-intensive to produce but also limited by the human ability in identifying all potential error patterns in LLM responses. We introduce MAGIC, a novel multi-agent method that automates the creation of the self-correction guideline. MAGIC uses three specialized agents: a manager, a correction, and a feedback agent. These agents collaborate on the failures"},"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":"2406.12692","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T15:06:06Z","cross_cats_sorted":["cs.AI","cs.DB","cs.HC"],"title_canon_sha256":"5ebd9792433a9d970bd6ef3f8c8c7b3e5e582a6ebb0ebf5d7ac4972a8b46cd10","abstract_canon_sha256":"9fa6a31c65746fd30d0cec010e783e529556b0f8d91228497b217033885563c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:02.057560Z","signature_b64":"u87ZpPFJ+s+pKd59ltjz5VFfeaLluMARUvj+lZZYeEM/K0ShAxH14QdlYorKYsyCXHaTDbqUZfybysrxTAemDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc1289bf9693e15d48c243271ff9c6423a38ff216aaf2ab0137a93fa22c5fd1b","last_reissued_at":"2026-07-05T09:53:02.057095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:02.057095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.HC"],"primary_cat":"cs.CL","authors_text":"Arian Askari, Christian Poelitz, Xinye Tang","submitted_at":"2024-06-18T15:06:06Z","abstract_excerpt":"Self-correction in text-to-SQL is the process of prompting large language model (LLM) to revise its previously incorrectly generated SQL, and commonly relies on manually crafted self-correction guidelines by human experts that are not only labor-intensive to produce but also limited by the human ability in identifying all potential error patterns in LLM responses. We introduce MAGIC, a novel multi-agent method that automates the creation of the self-correction guideline. MAGIC uses three specialized agents: a manager, a correction, and a feedback agent. These agents collaborate on the failures"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12692","kind":"arxiv","version":3},"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/2406.12692/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":"2406.12692","created_at":"2026-07-05T09:53:02.057147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12692v3","created_at":"2026-07-05T09:53:02.057147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12692","created_at":"2026-07-05T09:53:02.057147+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQJITP4WSPQV","created_at":"2026-07-05T09:53:02.057147+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQJITP4WSPQV2SGC","created_at":"2026-07-05T09:53:02.057147+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQJITP4W","created_at":"2026-07-05T09:53:02.057147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":3,"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":202,"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":217,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII","json":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII.json","graph_json":"https://pith.science/api/pith-number/XQJITP4WSPQV2SGCIMTR76OGII/graph.json","events_json":"https://pith.science/api/pith-number/XQJITP4WSPQV2SGCIMTR76OGII/events.json","paper":"https://pith.science/paper/XQJITP4W"},"agent_actions":{"view_html":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII","download_json":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII.json","view_paper":"https://pith.science/paper/XQJITP4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12692&json=true","fetch_graph":"https://pith.science/api/pith-number/XQJITP4WSPQV2SGCIMTR76OGII/graph.json","fetch_events":"https://pith.science/api/pith-number/XQJITP4WSPQV2SGCIMTR76OGII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII/action/storage_attestation","attest_author":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII/action/author_attestation","sign_citation":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII/action/citation_signature","submit_replication":"https://pith.science/pith/XQJITP4WSPQV2SGCIMTR76OGII/action/replication_record"}},"created_at":"2026-07-05T09:53:02.057147+00:00","updated_at":"2026-07-05T09:53:02.057147+00:00"}