{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2OQIKWLXG6DTR6Y3LAOY4T57UL","short_pith_number":"pith:2OQIKWLX","schema_version":"1.0","canonical_sha256":"d3a0855977378738fb1b581d8e4fbfa2c02a9f178bccac3845d3c7547ed2d079","source":{"kind":"arxiv","id":"2204.10360","version":1},"attestation_state":"computed","paper":{"title":"Decorate the Examples: A Simple Method of Prompt Design for Biomedical Relation Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui-Syuan Yeh, Pierre Zweigenbaum, Thomas Lavergne","submitted_at":"2022-04-21T18:39:22Z","abstract_excerpt":"Relation extraction is a core problem for natural language processing in the biomedical domain. Recent research on relation extraction showed that prompt-based learning improves the performance on both fine-tuning on full training set and few-shot training. However, less effort has been made on domain-specific tasks where good prompt design can be even harder. In this paper, we investigate prompting for biomedical relation extraction, with experiments on the ChemProt dataset. We present a simple yet effective method to systematically generate comprehensive prompts that reformulate the relation"},"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":"2204.10360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-21T18:39:22Z","cross_cats_sorted":[],"title_canon_sha256":"75a28865c6fb9c4f856992386efd417e64ea0bb72b579377c27f65e2390b2b48","abstract_canon_sha256":"98275212cb2c94b7fc9cbcd4eecca1702014ddcc69babeffa785a3536cb34276"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:56.017906Z","signature_b64":"Duq2Cac4ES0aGsMHSm9jX3RPUp/UM64J2RjONjn+STVjmosfKDqUXXRQB4KY3rxn462TE1tEjRtRmOqkS1YbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3a0855977378738fb1b581d8e4fbfa2c02a9f178bccac3845d3c7547ed2d079","last_reissued_at":"2026-07-05T04:16:56.017513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:56.017513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decorate the Examples: A Simple Method of Prompt Design for Biomedical Relation Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui-Syuan Yeh, Pierre Zweigenbaum, Thomas Lavergne","submitted_at":"2022-04-21T18:39:22Z","abstract_excerpt":"Relation extraction is a core problem for natural language processing in the biomedical domain. Recent research on relation extraction showed that prompt-based learning improves the performance on both fine-tuning on full training set and few-shot training. However, less effort has been made on domain-specific tasks where good prompt design can be even harder. In this paper, we investigate prompting for biomedical relation extraction, with experiments on the ChemProt dataset. We present a simple yet effective method to systematically generate comprehensive prompts that reformulate the relation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10360","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/2204.10360/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":"2204.10360","created_at":"2026-07-05T04:16:56.017569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.10360v1","created_at":"2026-07-05T04:16:56.017569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10360","created_at":"2026-07-05T04:16:56.017569+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OQIKWLXG6DT","created_at":"2026-07-05T04:16:56.017569+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OQIKWLXG6DTR6Y3","created_at":"2026-07-05T04:16:56.017569+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OQIKWLX","created_at":"2026-07-05T04:16:56.017569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14374","citing_title":"Error-Aware Curriculum Learning for Biomedical Relation Classification","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL","json":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL.json","graph_json":"https://pith.science/api/pith-number/2OQIKWLXG6DTR6Y3LAOY4T57UL/graph.json","events_json":"https://pith.science/api/pith-number/2OQIKWLXG6DTR6Y3LAOY4T57UL/events.json","paper":"https://pith.science/paper/2OQIKWLX"},"agent_actions":{"view_html":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL","download_json":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL.json","view_paper":"https://pith.science/paper/2OQIKWLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.10360&json=true","fetch_graph":"https://pith.science/api/pith-number/2OQIKWLXG6DTR6Y3LAOY4T57UL/graph.json","fetch_events":"https://pith.science/api/pith-number/2OQIKWLXG6DTR6Y3LAOY4T57UL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL/action/storage_attestation","attest_author":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL/action/author_attestation","sign_citation":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL/action/citation_signature","submit_replication":"https://pith.science/pith/2OQIKWLXG6DTR6Y3LAOY4T57UL/action/replication_record"}},"created_at":"2026-07-05T04:16:56.017569+00:00","updated_at":"2026-07-05T04:16:56.017569+00:00"}