{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OYOJPADFQ7X4DHXUKAWGWVJHYG","short_pith_number":"pith:OYOJPADF","schema_version":"1.0","canonical_sha256":"761c97806587efc19ef4502c6b5527c1adf215ded3cf3e6e0d97ce275eb7b7e8","source":{"kind":"arxiv","id":"2507.04642","version":2},"attestation_state":"computed","paper":{"title":"R1-RE: Cross-Domain Relation Extraction with RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongtu Zhu, Kaixian Yu, Runpeng Dai, Run Yang, Tong Zheng","submitted_at":"2025-07-07T03:50:59Z","abstract_excerpt":"Relation extraction (RE) is a core task in natural language processing. Traditional approaches typically frame RE as a supervised learning problem, directly mapping context to labels-an approach that often suffers from poor out-of-domain (OOD) generalization. Inspired by the workflow of human annotators, we reframe RE as a reasoning task guided by annotation guidelines and introduce R1-RE, the first reinforcement learning with verifiable reward (RLVR) framework for RE tasks. Our method elicits the reasoning abilities of small language models for annotation tasks, resulting in significantly imp"},"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":"2507.04642","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T03:50:59Z","cross_cats_sorted":[],"title_canon_sha256":"d74474fd621488811e62607ea88d0251d92ac9307e70aa3f14fc4db3d7686f0a","abstract_canon_sha256":"4ad100f0a6f4818dfca8d0bd72f4eaebade3df26e5047614a81e45de773f2d9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:34.010152Z","signature_b64":"/KfdZ9oE6gpLtqtWrzGIPFsnkHVz7HStF4ygw/tyUC4Wco9hL+uQQ3OK5T2dlGhw0e78r6m2TVNGJuLsM+JXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"761c97806587efc19ef4502c6b5527c1adf215ded3cf3e6e0d97ce275eb7b7e8","last_reissued_at":"2026-07-05T11:49:34.009680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:34.009680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R1-RE: Cross-Domain Relation Extraction with RLVR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongtu Zhu, Kaixian Yu, Runpeng Dai, Run Yang, Tong Zheng","submitted_at":"2025-07-07T03:50:59Z","abstract_excerpt":"Relation extraction (RE) is a core task in natural language processing. Traditional approaches typically frame RE as a supervised learning problem, directly mapping context to labels-an approach that often suffers from poor out-of-domain (OOD) generalization. Inspired by the workflow of human annotators, we reframe RE as a reasoning task guided by annotation guidelines and introduce R1-RE, the first reinforcement learning with verifiable reward (RLVR) framework for RE tasks. Our method elicits the reasoning abilities of small language models for annotation tasks, resulting in significantly imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04642","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/2507.04642/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":"2507.04642","created_at":"2026-07-05T11:49:34.009735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04642v2","created_at":"2026-07-05T11:49:34.009735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04642","created_at":"2026-07-05T11:49:34.009735+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYOJPADFQ7X4","created_at":"2026-07-05T11:49:34.009735+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYOJPADFQ7X4DHXU","created_at":"2026-07-05T11:49:34.009735+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYOJPADF","created_at":"2026-07-05T11:49:34.009735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18493","citing_title":"Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG","json":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG.json","graph_json":"https://pith.science/api/pith-number/OYOJPADFQ7X4DHXUKAWGWVJHYG/graph.json","events_json":"https://pith.science/api/pith-number/OYOJPADFQ7X4DHXUKAWGWVJHYG/events.json","paper":"https://pith.science/paper/OYOJPADF"},"agent_actions":{"view_html":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG","download_json":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG.json","view_paper":"https://pith.science/paper/OYOJPADF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04642&json=true","fetch_graph":"https://pith.science/api/pith-number/OYOJPADFQ7X4DHXUKAWGWVJHYG/graph.json","fetch_events":"https://pith.science/api/pith-number/OYOJPADFQ7X4DHXUKAWGWVJHYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG/action/storage_attestation","attest_author":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG/action/author_attestation","sign_citation":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG/action/citation_signature","submit_replication":"https://pith.science/pith/OYOJPADFQ7X4DHXUKAWGWVJHYG/action/replication_record"}},"created_at":"2026-07-05T11:49:34.009735+00:00","updated_at":"2026-07-05T11:49:34.009735+00:00"}