{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GGXJ76ZJX4TYW7OJ5IQKSCHLO2","short_pith_number":"pith:GGXJ76ZJ","schema_version":"1.0","canonical_sha256":"31ae9ffb29bf278b7dc9ea20a908eb769210deef5a589d17f414907295de79f6","source":{"kind":"arxiv","id":"2208.07989","version":2},"attestation_state":"computed","paper":{"title":"DICE: Data-Efficient Clinical Event Extraction with Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander K. Taylor, Mingyu Derek Ma, Nanyun Peng, Wei Wang","submitted_at":"2022-08-16T23:12:04Z","abstract_excerpt":"Event extraction for the clinical domain is an under-explored research area. The lack of training data along with the high volume of domain-specific terminologies with vague entity boundaries makes the task especially challenging. In this paper, we introduce DICE, a robust and data-efficient generative model for clinical event extraction. DICE frames event extraction as a conditional generation problem and introduces a contrastive learning objective to accurately decide the boundaries of biomedical mentions. DICE also trains an auxiliary mention identification task jointly with event extractio"},"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":"2208.07989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-16T23:12:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bd15bdd9e817ac4f46da6807ca9f0ba17710ef510aa6f4b6620ca81a68eb55cc","abstract_canon_sha256":"0cadf9f3b974fb6d93a0646fdeab84b4a7903d1471c99bc194544238faf24a3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:52.903727Z","signature_b64":"VBJjqYPAUMI7h79ILA0xAc9VIi0e70mg85wiQpazQ0su5yfs42bYrRTrzcHI+CtCOCrrej/5VTU2YCyfMDHvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ae9ffb29bf278b7dc9ea20a908eb769210deef5a589d17f414907295de79f6","last_reissued_at":"2026-07-05T06:13:52.903222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:52.903222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DICE: Data-Efficient Clinical Event Extraction with Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander K. Taylor, Mingyu Derek Ma, Nanyun Peng, Wei Wang","submitted_at":"2022-08-16T23:12:04Z","abstract_excerpt":"Event extraction for the clinical domain is an under-explored research area. The lack of training data along with the high volume of domain-specific terminologies with vague entity boundaries makes the task especially challenging. In this paper, we introduce DICE, a robust and data-efficient generative model for clinical event extraction. DICE frames event extraction as a conditional generation problem and introduces a contrastive learning objective to accurately decide the boundaries of biomedical mentions. DICE also trains an auxiliary mention identification task jointly with event extractio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07989","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/2208.07989/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":"2208.07989","created_at":"2026-07-05T06:13:52.903280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.07989v2","created_at":"2026-07-05T06:13:52.903280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07989","created_at":"2026-07-05T06:13:52.903280+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGXJ76ZJX4TY","created_at":"2026-07-05T06:13:52.903280+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGXJ76ZJX4TYW7OJ","created_at":"2026-07-05T06:13:52.903280+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGXJ76ZJ","created_at":"2026-07-05T06:13:52.903280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00134","citing_title":"Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2","json":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2.json","graph_json":"https://pith.science/api/pith-number/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/graph.json","events_json":"https://pith.science/api/pith-number/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/events.json","paper":"https://pith.science/paper/GGXJ76ZJ"},"agent_actions":{"view_html":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2","download_json":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2.json","view_paper":"https://pith.science/paper/GGXJ76ZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.07989&json=true","fetch_graph":"https://pith.science/api/pith-number/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/graph.json","fetch_events":"https://pith.science/api/pith-number/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/action/storage_attestation","attest_author":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/action/author_attestation","sign_citation":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/action/citation_signature","submit_replication":"https://pith.science/pith/GGXJ76ZJX4TYW7OJ5IQKSCHLO2/action/replication_record"}},"created_at":"2026-07-05T06:13:52.903280+00:00","updated_at":"2026-07-05T06:13:52.903280+00:00"}