{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:23HCQLQABOZBNMIN3NO4CVH6QE","short_pith_number":"pith:23HCQLQA","schema_version":"1.0","canonical_sha256":"d6ce282e000bb216b10ddb5dc154fe812f66d4b27676515445e96235d70dec2d","source":{"kind":"arxiv","id":"2509.09082","version":1},"attestation_state":"computed","paper":{"title":"MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mengjiao Bao, Ruiyu Fang, Shiquan Wang, Shuangyong Song, Yongxiang Li, Zhenhe Wu, Zhongjiang He, Zhongqiu Li","submitted_at":"2025-09-11T01:08:58Z","abstract_excerpt":"Large language models (LLMs) demonstrate robust capabilities across diverse research domains. However, their performance in universal information extraction (UIE) remains insufficient, especially when tackling structured output scenarios that involve complex schema descriptions and require multi-step reasoning. While existing approaches enhance the performance of LLMs through in-context learning and instruction tuning, significant limitations nonetheless persist. To enhance the model's generalization ability, we propose integrating reinforcement learning (RL) with multi-perspective reasoning f"},"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":"2509.09082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-11T01:08:58Z","cross_cats_sorted":[],"title_canon_sha256":"ff86fbcea0862ee27c6db0bcfbfed45344867fc4ec5bd925c37c0a0cda21574d","abstract_canon_sha256":"fc504778774f9bbc74cfd4cb56b62b49e6bb682f967e727880c5a722c386d427"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:29.035159Z","signature_b64":"/bgY9gXVkghz1dWEOAhrTQpvXpmkF2tB/AspcxkS3sBipjEIdckzj1fyh0dsrh9PnW8AYvLAXQcNzqViKS9mBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6ce282e000bb216b10ddb5dc154fe812f66d4b27676515445e96235d70dec2d","last_reissued_at":"2026-07-05T12:09:29.034621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:29.034621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mengjiao Bao, Ruiyu Fang, Shiquan Wang, Shuangyong Song, Yongxiang Li, Zhenhe Wu, Zhongjiang He, Zhongqiu Li","submitted_at":"2025-09-11T01:08:58Z","abstract_excerpt":"Large language models (LLMs) demonstrate robust capabilities across diverse research domains. However, their performance in universal information extraction (UIE) remains insufficient, especially when tackling structured output scenarios that involve complex schema descriptions and require multi-step reasoning. While existing approaches enhance the performance of LLMs through in-context learning and instruction tuning, significant limitations nonetheless persist. To enhance the model's generalization ability, we propose integrating reinforcement learning (RL) with multi-perspective reasoning f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09082","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/2509.09082/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":"2509.09082","created_at":"2026-07-05T12:09:29.034681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09082v1","created_at":"2026-07-05T12:09:29.034681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09082","created_at":"2026-07-05T12:09:29.034681+00:00"},{"alias_kind":"pith_short_12","alias_value":"23HCQLQABOZB","created_at":"2026-07-05T12:09:29.034681+00:00"},{"alias_kind":"pith_short_16","alias_value":"23HCQLQABOZBNMIN","created_at":"2026-07-05T12:09:29.034681+00:00"},{"alias_kind":"pith_short_8","alias_value":"23HCQLQA","created_at":"2026-07-05T12:09:29.034681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03022","citing_title":"Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01923","citing_title":"Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE","json":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE.json","graph_json":"https://pith.science/api/pith-number/23HCQLQABOZBNMIN3NO4CVH6QE/graph.json","events_json":"https://pith.science/api/pith-number/23HCQLQABOZBNMIN3NO4CVH6QE/events.json","paper":"https://pith.science/paper/23HCQLQA"},"agent_actions":{"view_html":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE","download_json":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE.json","view_paper":"https://pith.science/paper/23HCQLQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09082&json=true","fetch_graph":"https://pith.science/api/pith-number/23HCQLQABOZBNMIN3NO4CVH6QE/graph.json","fetch_events":"https://pith.science/api/pith-number/23HCQLQABOZBNMIN3NO4CVH6QE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE/action/storage_attestation","attest_author":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE/action/author_attestation","sign_citation":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE/action/citation_signature","submit_replication":"https://pith.science/pith/23HCQLQABOZBNMIN3NO4CVH6QE/action/replication_record"}},"created_at":"2026-07-05T12:09:29.034681+00:00","updated_at":"2026-07-05T12:09:29.034681+00:00"}