{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JQFHRDON6Q3JPNUH7WX5BOGUXE","short_pith_number":"pith:JQFHRDON","schema_version":"1.0","canonical_sha256":"4c0a788dcdf43697b687fdafd0b8d4b93ebdade2999dfd7e89d878a2da587c94","source":{"kind":"arxiv","id":"2411.11779","version":1},"attestation_state":"computed","paper":{"title":"LLM-IE: A Python Package for Generative Information Extraction with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Enshuo Hsu, Kirk Roberts","submitted_at":"2024-11-18T17:56:13Z","abstract_excerpt":"Objectives: Despite the recent adoption of large language models (LLMs) for biomedical information extraction, challenges in prompt engineering and algorithms persist, with no dedicated software available. To address this, we developed LLM-IE: a Python package for building complete information extraction pipelines. Our key innovation is an interactive LLM agent to support schema definition and prompt design.\n  Materials and Methods: The LLM-IE supports named entity recognition, entity attribute extraction, and relation extraction tasks. We benchmarked on the i2b2 datasets and conducted a syste"},"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":"2411.11779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T17:56:13Z","cross_cats_sorted":[],"title_canon_sha256":"d62998b2448fd150aae54adc252da66eacab9c4241e2c769a1bdd19b7133fa9c","abstract_canon_sha256":"a210c774394ccaf6ebf57a317fe64e93408581b65b7933b984ba808a023524e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:13.800007Z","signature_b64":"tBBRkQ9fe2kUqMluIQHbC6d3gMMMZqJ7afuFrZXag9y6kHrS+6dLK2EfA4cHEbNgkVi+Rl5pB4i3pQNmvo2qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c0a788dcdf43697b687fdafd0b8d4b93ebdade2999dfd7e89d878a2da587c94","last_reissued_at":"2026-07-05T10:42:13.799518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:13.799518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-IE: A Python Package for Generative Information Extraction with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Enshuo Hsu, Kirk Roberts","submitted_at":"2024-11-18T17:56:13Z","abstract_excerpt":"Objectives: Despite the recent adoption of large language models (LLMs) for biomedical information extraction, challenges in prompt engineering and algorithms persist, with no dedicated software available. To address this, we developed LLM-IE: a Python package for building complete information extraction pipelines. Our key innovation is an interactive LLM agent to support schema definition and prompt design.\n  Materials and Methods: The LLM-IE supports named entity recognition, entity attribute extraction, and relation extraction tasks. We benchmarked on the i2b2 datasets and conducted a syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11779","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/2411.11779/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":"2411.11779","created_at":"2026-07-05T10:42:13.799571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11779v1","created_at":"2026-07-05T10:42:13.799571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11779","created_at":"2026-07-05T10:42:13.799571+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQFHRDON6Q3J","created_at":"2026-07-05T10:42:13.799571+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQFHRDON6Q3JPNUH","created_at":"2026-07-05T10:42:13.799571+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQFHRDON","created_at":"2026-07-05T10:42:13.799571+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/JQFHRDON6Q3JPNUH7WX5BOGUXE","json":"https://pith.science/pith/JQFHRDON6Q3JPNUH7WX5BOGUXE.json","graph_json":"https://pith.science/api/pith-number/JQFHRDON6Q3JPNUH7WX5BOGUXE/graph.json","events_json":"https://pith.science/api/pith-number/JQFHRDON6Q3JPNUH7WX5BOGUXE/events.json","paper":"https://pith.science/paper/JQFHRDON"},"agent_actions":{"view_html":"https://pith.science/pith/JQFHRDON6Q3JPNUH7WX5BOGUXE","download_json":"https://pith.science/pith/JQFHRDON6Q3JPNUH7WX5BOGUXE.json","view_paper":"https://pith.science/paper/JQFHRDON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11779&json=true","fetch_graph":"https://pith.science/api/pith-number/JQFHRDON6Q3JPNUH7WX5BOGUXE/graph.json","fetch_events":"https://pith.science/api/pith-number/JQFHRDON6Q3JPNUH7WX5BOGUXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQFHRDON6Q3JPNUH7WX5BOGUXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQFHRDON6Q3JPNUH7WX5BOGUXE/action/storage_attestation","attest_author":"https://pith.science/pith/JQFHRDON6Q3JPNUH7WX5BOGUXE/action/author_attestation","sign_citation":"https://pith.science/pith/JQFHRDON6Q3JPNUH7WX5BOGUXE/action/citation_signature","submit_replication":"https://pith.science/pith/JQFHRDON6Q3JPNUH7WX5BOGUXE/action/replication_record"}},"created_at":"2026-07-05T10:42:13.799571+00:00","updated_at":"2026-07-05T10:42:13.799571+00:00"}