{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G7DXLOS32BZD2LAEMTL5MNHLLQ","short_pith_number":"pith:G7DXLOS3","schema_version":"1.0","canonical_sha256":"37c775ba5bd0723d2c0464d7d634eb5c3b89c1c241b9ce73d35758d5903a8639","source":{"kind":"arxiv","id":"2403.07969","version":2},"attestation_state":"computed","paper":{"title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiafeng Guo, Long Bai, Miao Su, Pan Yang, Weicheng Ren, Wei Li, Wenxuan Liu, Xiang Li, Xiaolong Jin, Xueqi Cheng, Yantao Liu, Yidan Liu, Yucan Guo, Yutao Zeng, Yuxin Zuo, Zhilei Hu, Zixuan Li","submitted_at":"2024-03-12T14:56:34Z","abstract_excerpt":"In this paper, we propose KnowCoder, a Large Language Model (LLM) to conduct Universal Information Extraction (UIE) via code generation. KnowCoder aims to develop a kind of unified schema representation that LLMs can easily understand and an effective learning framework that encourages LLMs to follow schemas and extract structured knowledge accurately. To achieve these, KnowCoder introduces a code-style schema representation method to uniformly transform different schemas into Python classes, with which complex schema information, such as constraints among tasks in UIE, can be captured in an L"},"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":"2403.07969","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-12T14:56:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"327a8973caa0324895a6f36ec8677c155cdcf62b796dc60e76d9ac21ce2aae6e","abstract_canon_sha256":"e1e01d28bdbcd8a9f77679e5d84ad26f349ef21183a48f56d4bea5aff9c26356"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:04.345359Z","signature_b64":"Y/8vrtnP0Gi37S/tRevpVadLFZvtNYqtACup3ZTNdsu2rmu6YrK5ACsDD2lCjaojNXSkuF5ijYTrX/sdjYyGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37c775ba5bd0723d2c0464d7d634eb5c3b89c1c241b9ce73d35758d5903a8639","last_reissued_at":"2026-07-05T07:56:04.344882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:04.344882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiafeng Guo, Long Bai, Miao Su, Pan Yang, Weicheng Ren, Wei Li, Wenxuan Liu, Xiang Li, Xiaolong Jin, Xueqi Cheng, Yantao Liu, Yidan Liu, Yucan Guo, Yutao Zeng, Yuxin Zuo, Zhilei Hu, Zixuan Li","submitted_at":"2024-03-12T14:56:34Z","abstract_excerpt":"In this paper, we propose KnowCoder, a Large Language Model (LLM) to conduct Universal Information Extraction (UIE) via code generation. KnowCoder aims to develop a kind of unified schema representation that LLMs can easily understand and an effective learning framework that encourages LLMs to follow schemas and extract structured knowledge accurately. To achieve these, KnowCoder introduces a code-style schema representation method to uniformly transform different schemas into Python classes, with which complex schema information, such as constraints among tasks in UIE, can be captured in an L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07969","kind":"arxiv","version":2},"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/2403.07969/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":"2403.07969","created_at":"2026-07-05T07:56:04.344937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07969v2","created_at":"2026-07-05T07:56:04.344937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07969","created_at":"2026-07-05T07:56:04.344937+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7DXLOS32BZD","created_at":"2026-07-05T07:56:04.344937+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7DXLOS32BZD2LAE","created_at":"2026-07-05T07:56:04.344937+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7DXLOS3","created_at":"2026-07-05T07:56:04.344937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ","json":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ.json","graph_json":"https://pith.science/api/pith-number/G7DXLOS32BZD2LAEMTL5MNHLLQ/graph.json","events_json":"https://pith.science/api/pith-number/G7DXLOS32BZD2LAEMTL5MNHLLQ/events.json","paper":"https://pith.science/paper/G7DXLOS3"},"agent_actions":{"view_html":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ","download_json":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ.json","view_paper":"https://pith.science/paper/G7DXLOS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07969&json=true","fetch_graph":"https://pith.science/api/pith-number/G7DXLOS32BZD2LAEMTL5MNHLLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/G7DXLOS32BZD2LAEMTL5MNHLLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ/action/storage_attestation","attest_author":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ/action/author_attestation","sign_citation":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ/action/citation_signature","submit_replication":"https://pith.science/pith/G7DXLOS32BZD2LAEMTL5MNHLLQ/action/replication_record"}},"created_at":"2026-07-05T07:56:04.344937+00:00","updated_at":"2026-07-05T07:56:04.344937+00:00"}