{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:POEYUF7JMQE7N2QPVG7AWDQQ2Q","short_pith_number":"pith:POEYUF7J","schema_version":"1.0","canonical_sha256":"7b898a17e96409f6ea0fa9be0b0e10d4359bca95a21a40e7b8c9527af290a2dd","source":{"kind":"arxiv","id":"2311.02962","version":1},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Code Generation for Universal Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Jiafeng Guo, Long Bai, Pan Yang, Wenxuan Liu, Xiang Li, Xiaolong Jin, Xueqi Cheng, Yantao Liu, Yucan Guo, Yutao Zeng, Zixuan Li","submitted_at":"2023-11-06T09:03:21Z","abstract_excerpt":"Information Extraction (IE) aims to extract structural knowledge (e.g., entities, relations, events) from natural language texts, which brings challenges to existing methods due to task-specific schemas and complex text expressions. Code, as a typical kind of formalized language, is capable of describing structural knowledge under various schemas in a universal way. On the other hand, Large Language Models (LLMs) trained on both codes and texts have demonstrated powerful capabilities of transforming texts into codes, which provides a feasible solution to IE tasks. Therefore, in this paper, we "},"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":"2311.02962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-11-06T09:03:21Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"c499cf9f9dfec1a5c90a1b0b3a76b98db6337df65662966a5a5fe495dfabf350","abstract_canon_sha256":"66241747a9121806e3023a901dd2f19a89f7d0c12faa19bc0db2947cac8e740b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:33.979383Z","signature_b64":"wylRVrRRF7TI/YzcagrkSKcXvxZv9baVyaNCtZ2ACGzR5GbfdVavJZpnZRg6c76NuwLS6l6lVEuA3aXTgueVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b898a17e96409f6ea0fa9be0b0e10d4359bca95a21a40e7b8c9527af290a2dd","last_reissued_at":"2026-07-05T07:09:33.978927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:33.978927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Code Generation for Universal Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"cs.AI","authors_text":"Jiafeng Guo, Long Bai, Pan Yang, Wenxuan Liu, Xiang Li, Xiaolong Jin, Xueqi Cheng, Yantao Liu, Yucan Guo, Yutao Zeng, Zixuan Li","submitted_at":"2023-11-06T09:03:21Z","abstract_excerpt":"Information Extraction (IE) aims to extract structural knowledge (e.g., entities, relations, events) from natural language texts, which brings challenges to existing methods due to task-specific schemas and complex text expressions. Code, as a typical kind of formalized language, is capable of describing structural knowledge under various schemas in a universal way. On the other hand, Large Language Models (LLMs) trained on both codes and texts have demonstrated powerful capabilities of transforming texts into codes, which provides a feasible solution to IE tasks. Therefore, in this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02962","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/2311.02962/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":"2311.02962","created_at":"2026-07-05T07:09:33.978982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02962v1","created_at":"2026-07-05T07:09:33.978982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02962","created_at":"2026-07-05T07:09:33.978982+00:00"},{"alias_kind":"pith_short_12","alias_value":"POEYUF7JMQE7","created_at":"2026-07-05T07:09:33.978982+00:00"},{"alias_kind":"pith_short_16","alias_value":"POEYUF7JMQE7N2QP","created_at":"2026-07-05T07:09:33.978982+00:00"},{"alias_kind":"pith_short_8","alias_value":"POEYUF7J","created_at":"2026-07-05T07:09:33.978982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30914","citing_title":"Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29407","citing_title":"LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":258,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q","json":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q.json","graph_json":"https://pith.science/api/pith-number/POEYUF7JMQE7N2QPVG7AWDQQ2Q/graph.json","events_json":"https://pith.science/api/pith-number/POEYUF7JMQE7N2QPVG7AWDQQ2Q/events.json","paper":"https://pith.science/paper/POEYUF7J"},"agent_actions":{"view_html":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q","download_json":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q.json","view_paper":"https://pith.science/paper/POEYUF7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02962&json=true","fetch_graph":"https://pith.science/api/pith-number/POEYUF7JMQE7N2QPVG7AWDQQ2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/POEYUF7JMQE7N2QPVG7AWDQQ2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q/action/storage_attestation","attest_author":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q/action/author_attestation","sign_citation":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q/action/citation_signature","submit_replication":"https://pith.science/pith/POEYUF7JMQE7N2QPVG7AWDQQ2Q/action/replication_record"}},"created_at":"2026-07-05T07:09:33.978982+00:00","updated_at":"2026-07-05T07:09:33.978982+00:00"}