{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D3EIJXQX5EBPYP2C5RU3QDMJUR","short_pith_number":"pith:D3EIJXQX","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"},"canonical_sha256":"1ec884de17e902fc3f42ec69b80d89a463db45fee45c699613ed7cb07b02d4dd","source":{"kind":"arxiv","id":"2403.03304","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03304","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03304v2","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03304","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"pith_short_12","alias_value":"D3EIJXQX5EBP","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"D3EIJXQX5EBPYP2C","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"D3EIJXQX","created_at":"2026-07-05T08:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D3EIJXQX5EBPYP2C5RU3QDMJUR","target":"record","payload":{"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"},"canonical_sha256":"1ec884de17e902fc3f42ec69b80d89a463db45fee45c699613ed7cb07b02d4dd","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"},"source_kind":"arxiv","source_id":"2403.03304","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wtpk4rpVNLmp8ufHHLzl7WeC6fJQmAFBhb3hw1RTUBWFXdtcmq4gNLv77Y+7KY87EYUvPyrUF2s2C6nxPugcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:48:21.800123Z"},"content_sha256":"bfdefb6bc5b43db4663cc58de4f77daabd8b20f13ed2bbdff8bd23c9d363ef3e","schema_version":"1.0","event_id":"sha256:bfdefb6bc5b43db4663cc58de4f77daabd8b20f13ed2bbdff8bd23c9d363ef3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D3EIJXQX5EBPYP2C5RU3QDMJUR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tHo09EZa6uHKAbpUXgnZhYqeN7ZB+lqZzveeNd1DEIuwquOeRF8PaAxA0DWaf5LTPgLSAWTVH4tu9o8sre8VDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T00:48:21.800503Z"},"content_sha256":"3e4ef32af738e23d442dceae6c0d0cd7f8020fb56705ac7aa41d839ea31aa8c4","schema_version":"1.0","event_id":"sha256:3e4ef32af738e23d442dceae6c0d0cd7f8020fb56705ac7aa41d839ea31aa8c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/bundle.json","state_url":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T00:48:21Z","links":{"resolver":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR","bundle":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/bundle.json","state":"https://pith.science/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D3EIJXQX5EBPYP2C5RU3QDMJUR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D3EIJXQX5EBPYP2C5RU3QDMJUR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5b36751a4d67f8d90e3e742a5bbf950d0b1969a0d12f50a8be2e5a7a765a2794","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T20:07:42Z","title_canon_sha256":"6f01acdf2d179c7798deeb4d4ce401219ecad1fc80fac434c516a60d88251335"},"schema_version":"1.0","source":{"id":"2403.03304","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03304","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03304v2","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03304","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"pith_short_12","alias_value":"D3EIJXQX5EBP","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"D3EIJXQX5EBPYP2C","created_at":"2026-07-05T08:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"D3EIJXQX","created_at":"2026-07-05T08:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:3e4ef32af738e23d442dceae6c0d0cd7f8020fb56705ac7aa41d839ea31aa8c4","target":"graph","created_at":"2026-07-05T08:31:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.03304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Joseph Gatto, Omar Sharif, Parker Seegmiller, Sarah M. Preum","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T20:07:42Z","title":"Large Language Models for Document-Level Event-Argument Data Augmentation for Challenging Role Types"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03304","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bfdefb6bc5b43db4663cc58de4f77daabd8b20f13ed2bbdff8bd23c9d363ef3e","target":"record","created_at":"2026-07-05T08:31:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5b36751a4d67f8d90e3e742a5bbf950d0b1969a0d12f50a8be2e5a7a765a2794","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-05T20:07:42Z","title_canon_sha256":"6f01acdf2d179c7798deeb4d4ce401219ecad1fc80fac434c516a60d88251335"},"schema_version":"1.0","source":{"id":"2403.03304","kind":"arxiv","version":2}},"canonical_sha256":"1ec884de17e902fc3f42ec69b80d89a463db45fee45c699613ed7cb07b02d4dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ec884de17e902fc3f42ec69b80d89a463db45fee45c699613ed7cb07b02d4dd","first_computed_at":"2026-07-05T08:31:12.605747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:12.605747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7HSOoc0RxlvBd3N+T/6e1jFmzq+4NCfv/5rGRjMD8oDj3kzxHBldD/0OB8RMBfx+J7n9F7KGeK8Xl8yh2z84BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:12.606274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03304","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfdefb6bc5b43db4663cc58de4f77daabd8b20f13ed2bbdff8bd23c9d363ef3e","sha256:3e4ef32af738e23d442dceae6c0d0cd7f8020fb56705ac7aa41d839ea31aa8c4"],"state_sha256":"6391effe1a09da33671fe711db328f9eb5e0e9b6f5105acf82fe620571b93cc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XxDeowKKGBGpoV1gHz55+9+9AD3tQgIThokaUjbGLfBmVmXpE61a8JxdBkISP47AlHKQucy1X8aFbEaOGrCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T00:48:21.803331Z","bundle_sha256":"ae29d6f7776def22ca2f6c46add0eb5afcfd6dba4dc74ee37e00658adb80a125"}}