{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MQ35TXWZHLAJIAE4IM7A2UXQVX","short_pith_number":"pith:MQ35TXWZ","schema_version":"1.0","canonical_sha256":"6437d9ded93ac094009c433e0d52f0adc4524a19c9bd3bc33e5c1ffdfc3f7f8d","source":{"kind":"arxiv","id":"2108.12724","version":3},"attestation_state":"computed","paper":{"title":"DEGREE: A Data-Efficient Generation-Based Event Extraction Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Elizabeth Boschee, I-Hung Hsu, Kai-Wei Chang, Kuan-Hao Huang, Nanyun Peng, Prem Natarajan, Scott Miller","submitted_at":"2021-08-29T00:27:31Z","abstract_excerpt":"Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge. In this paper, we focus on low-resource end-to-end event extraction and propose DEGREE, a data-efficient model that formulates event extraction as a conditional generation problem. Given a passage and a manually designed prompt, DEGREE learns to summarize the events mentioned in the passage into a natural sentence that follows a predefined pattern. The final "},"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":"2108.12724","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-29T00:27:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a443413e3c2b94b2c0e9f6f9429bc8b0ce255d0395d890e0fd2f18508e536661","abstract_canon_sha256":"ba5b182c168db45c59f82a4b04d27c6414c9c7bb1ae723bdef7115742e5ef2d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:15.788224Z","signature_b64":"NQv59SP3QfUB6vz0gtt2beznAvkVailEDPQe0JXdXQAvmeeK/bWlEvJVX1VgOCMlIscwdWjV59FdV/mIQG9oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6437d9ded93ac094009c433e0d52f0adc4524a19c9bd3bc33e5c1ffdfc3f7f8d","last_reissued_at":"2026-07-05T04:20:15.787723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:15.787723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEGREE: A Data-Efficient Generation-Based Event Extraction Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Elizabeth Boschee, I-Hung Hsu, Kai-Wei Chang, Kuan-Hao Huang, Nanyun Peng, Prem Natarajan, Scott Miller","submitted_at":"2021-08-29T00:27:31Z","abstract_excerpt":"Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge. In this paper, we focus on low-resource end-to-end event extraction and propose DEGREE, a data-efficient model that formulates event extraction as a conditional generation problem. Given a passage and a manually designed prompt, DEGREE learns to summarize the events mentioned in the passage into a natural sentence that follows a predefined pattern. The final "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12724","kind":"arxiv","version":3},"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/2108.12724/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":"2108.12724","created_at":"2026-07-05T04:20:15.787789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.12724v3","created_at":"2026-07-05T04:20:15.787789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12724","created_at":"2026-07-05T04:20:15.787789+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQ35TXWZHLAJ","created_at":"2026-07-05T04:20:15.787789+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQ35TXWZHLAJIAE4","created_at":"2026-07-05T04:20:15.787789+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQ35TXWZ","created_at":"2026-07-05T04:20:15.787789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18811","citing_title":"NewsEdits 2.0: Learning the Intentions Behind Updating News","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX","json":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX.json","graph_json":"https://pith.science/api/pith-number/MQ35TXWZHLAJIAE4IM7A2UXQVX/graph.json","events_json":"https://pith.science/api/pith-number/MQ35TXWZHLAJIAE4IM7A2UXQVX/events.json","paper":"https://pith.science/paper/MQ35TXWZ"},"agent_actions":{"view_html":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX","download_json":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX.json","view_paper":"https://pith.science/paper/MQ35TXWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.12724&json=true","fetch_graph":"https://pith.science/api/pith-number/MQ35TXWZHLAJIAE4IM7A2UXQVX/graph.json","fetch_events":"https://pith.science/api/pith-number/MQ35TXWZHLAJIAE4IM7A2UXQVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX/action/storage_attestation","attest_author":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX/action/author_attestation","sign_citation":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX/action/citation_signature","submit_replication":"https://pith.science/pith/MQ35TXWZHLAJIAE4IM7A2UXQVX/action/replication_record"}},"created_at":"2026-07-05T04:20:15.787789+00:00","updated_at":"2026-07-05T04:20:15.787789+00:00"}