{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D3EIJXQX5EBPYP2C5RU3QDMJUR","short_pith_number":"pith:D3EIJXQX","schema_version":"1.0","canonical_sha256":"1ec884de17e902fc3f42ec69b80d89a463db45fee45c699613ed7cb07b02d4dd","source":{"kind":"arxiv","id":"2403.03304","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Joseph Gatto, Omar Sharif, Parker Seegmiller, Sarah M. Preum","submitted_at":"2024-03-05T20:07:42Z","abstract_excerpt":"Event Argument Extraction (EAE) is an extremely difficult information extraction problem -- with significant limitations in few-shot cross-domain (FSCD) settings. A common solution to FSCD modeling is data augmentation. Unfortunately, existing augmentation methods are not well-suited to a variety of real-world EAE contexts including (i) The need to model long documents (10+ sentences) (ii) The need to model zero and few-shot roles (i.e. event roles with little to no training representation). In this work, we introduce two novel LLM-powered data augmentation frameworks for synthesizing extracti"},"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":"2403.03304","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T20:07:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6f01acdf2d179c7798deeb4d4ce401219ecad1fc80fac434c516a60d88251335","abstract_canon_sha256":"5b36751a4d67f8d90e3e742a5bbf950d0b1969a0d12f50a8be2e5a7a765a2794"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:12.606274Z","signature_b64":"7HSOoc0RxlvBd3N+T/6e1jFmzq+4NCfv/5rGRjMD8oDj3kzxHBldD/0OB8RMBfx+J7n9F7KGeK8Xl8yh2z84BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ec884de17e902fc3f42ec69b80d89a463db45fee45c699613ed7cb07b02d4dd","last_reissued_at":"2026-07-05T08:31:12.605747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:12.605747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Joseph Gatto, Omar Sharif, Parker Seegmiller, Sarah M. Preum","submitted_at":"2024-03-05T20:07:42Z","abstract_excerpt":"Event Argument Extraction (EAE) is an extremely difficult information extraction problem -- with significant limitations in few-shot cross-domain (FSCD) settings. A common solution to FSCD modeling is data augmentation. Unfortunately, existing augmentation methods are not well-suited to a variety of real-world EAE contexts including (i) The need to model long documents (10+ sentences) (ii) The need to model zero and few-shot roles (i.e. event roles with little to no training representation). In this work, we introduce two novel LLM-powered data augmentation frameworks for synthesizing extracti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03304","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/2403.03304/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":"2403.03304","created_at":"2026-07-05T08:31:12.605812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03304v2","created_at":"2026-07-05T08:31:12.605812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03304","created_at":"2026-07-05T08:31:12.605812+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3EIJXQX5EBP","created_at":"2026-07-05T08:31:12.605812+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3EIJXQX5EBPYP2C","created_at":"2026-07-05T08:31:12.605812+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3EIJXQX","created_at":"2026-07-05T08:31:12.605812+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/D3EIJXQX5EBPYP2C5RU3QDMJUR","json":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR.json","graph_json":"https://pith.science/api/pith-number/D3EIJXQX5EBPYP2C5RU3QDMJUR/graph.json","events_json":"https://pith.science/api/pith-number/D3EIJXQX5EBPYP2C5RU3QDMJUR/events.json","paper":"https://pith.science/paper/D3EIJXQX"},"agent_actions":{"view_html":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR","download_json":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR.json","view_paper":"https://pith.science/paper/D3EIJXQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03304&json=true","fetch_graph":"https://pith.science/api/pith-number/D3EIJXQX5EBPYP2C5RU3QDMJUR/graph.json","fetch_events":"https://pith.science/api/pith-number/D3EIJXQX5EBPYP2C5RU3QDMJUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/action/storage_attestation","attest_author":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/action/author_attestation","sign_citation":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/action/citation_signature","submit_replication":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/action/replication_record"}},"created_at":"2026-07-05T08:31:12.605812+00:00","updated_at":"2026-07-05T08:31:12.605812+00:00"}