{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U5KMJQNC2LMBCMUVVFQHUISKKR","short_pith_number":"pith:U5KMJQNC","schema_version":"1.0","canonical_sha256":"a754c4c1a2d2d8113295a9607a224a5479f0da895c00d4ef8fb268ffabc779b3","source":{"kind":"arxiv","id":"2503.23513","version":2},"attestation_state":"computed","paper":{"title":"RARE: Retrieval-Augmented Reasoning Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongsheng Ma, Feiyu Xiong, Jiayang Yu, Linpeng Tang, Weinan E, Wentao Zhang, Yanfeng Wang, Yu Wang, Zhe Chen, Zhengren Wang, Zhiyu Li","submitted_at":"2025-03-30T16:49:44Z","abstract_excerpt":"Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning capabilities under constrained parameter budgets. Inspired by Bloom's Taxonomy in educational theory, we propose Retrieval-Augmented Reasoning Modeling (RARE), a novel paradigm that decouples knowledge storage from reasoning optimization. RARE externalizes domain knowledge to retrievable sources and internalizes domain-specific reasoning patterns during train"},"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":"2503.23513","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-30T16:49:44Z","cross_cats_sorted":[],"title_canon_sha256":"3a7016ccace64160b6d1341c7f880a2d75131c46785c2aa3a43c9595ea913aef","abstract_canon_sha256":"0d40ea7ec30bd5fd1f75e7e8dfaa2df33cbed7f1e5ee673d0a1014c895cd752b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:48.424852Z","signature_b64":"G9JyWmwi2HakBdt0l5Mrg7aLLi4+IJgblz0w4SdRliVeveJ0+gMbDY/6DKVAgR5q9xdM1RKGHnv12UNESdW1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a754c4c1a2d2d8113295a9607a224a5479f0da895c00d4ef8fb268ffabc779b3","last_reissued_at":"2026-07-05T11:04:48.424333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:48.424333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RARE: Retrieval-Augmented Reasoning Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongsheng Ma, Feiyu Xiong, Jiayang Yu, Linpeng Tang, Weinan E, Wentao Zhang, Yanfeng Wang, Yu Wang, Zhe Chen, Zhengren Wang, Zhiyu Li","submitted_at":"2025-03-30T16:49:44Z","abstract_excerpt":"Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning capabilities under constrained parameter budgets. Inspired by Bloom's Taxonomy in educational theory, we propose Retrieval-Augmented Reasoning Modeling (RARE), a novel paradigm that decouples knowledge storage from reasoning optimization. RARE externalizes domain knowledge to retrievable sources and internalizes domain-specific reasoning patterns during train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23513","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/2503.23513/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":"2503.23513","created_at":"2026-07-05T11:04:48.424404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23513v2","created_at":"2026-07-05T11:04:48.424404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23513","created_at":"2026-07-05T11:04:48.424404+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5KMJQNC2LMB","created_at":"2026-07-05T11:04:48.424404+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5KMJQNC2LMBCMUV","created_at":"2026-07-05T11:04:48.424404+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5KMJQNC","created_at":"2026-07-05T11:04:48.424404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00052","citing_title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2504.21776","citing_title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12882","citing_title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR","json":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR.json","graph_json":"https://pith.science/api/pith-number/U5KMJQNC2LMBCMUVVFQHUISKKR/graph.json","events_json":"https://pith.science/api/pith-number/U5KMJQNC2LMBCMUVVFQHUISKKR/events.json","paper":"https://pith.science/paper/U5KMJQNC"},"agent_actions":{"view_html":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR","download_json":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR.json","view_paper":"https://pith.science/paper/U5KMJQNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23513&json=true","fetch_graph":"https://pith.science/api/pith-number/U5KMJQNC2LMBCMUVVFQHUISKKR/graph.json","fetch_events":"https://pith.science/api/pith-number/U5KMJQNC2LMBCMUVVFQHUISKKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR/action/storage_attestation","attest_author":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR/action/author_attestation","sign_citation":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR/action/citation_signature","submit_replication":"https://pith.science/pith/U5KMJQNC2LMBCMUVVFQHUISKKR/action/replication_record"}},"created_at":"2026-07-05T11:04:48.424404+00:00","updated_at":"2026-07-05T11:04:48.424404+00:00"}