{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TS5TBZOF5Y4R7LJXNU7H47QVBK","short_pith_number":"pith:TS5TBZOF","schema_version":"1.0","canonical_sha256":"9cbb30e5c5ee391fad376d3e7e7e150ab3ed858860fda5f4795bee4d25c28ea6","source":{"kind":"arxiv","id":"2503.21729","version":3},"attestation_state":"computed","paper":{"title":"ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiajie Zhang, Jinxin Liu, Juanzi Li, Lei Hou, Shulin Cao, Weichuan Liu, Xiaoyin Che, Zhicheng Lee","submitted_at":"2025-03-27T17:44:18Z","abstract_excerpt":"Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy. While recent works equip reinforcement learning (RL)-based LRMs with retrieval capabilities, they suffer from overthinking and lack robustness in reasoning, reducing their effectiveness in question answering (QA) tasks. To address this, we propose ReaRAG, a factuality-enhanced reasoning model that explores diverse queries without excessive iterations. Our solution includes a novel data construction framework with an upper bound on the reasoning chain lengt"},"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":"2503.21729","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-27T17:44:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"243a81790f2cf51ca5f9db8e686d7d120cad09f5c019fb33cf91f214de27dd11","abstract_canon_sha256":"d0a5494051c163f16d57baf2b45bc4c5085fa129bb536795f87873e175f76358"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:48.025183Z","signature_b64":"v/jSRy8btQn8lvAiqqvWIvpTxtk29J06pa8FsXmJUwfBSgHJzzBzuQ+Y24u4/9MIzgISQ9+Et3XAvMspXbDwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cbb30e5c5ee391fad376d3e7e7e150ab3ed858860fda5f4795bee4d25c28ea6","last_reissued_at":"2026-07-05T11:04:48.024549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:48.024549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiajie Zhang, Jinxin Liu, Juanzi Li, Lei Hou, Shulin Cao, Weichuan Liu, Xiaoyin Che, Zhicheng Lee","submitted_at":"2025-03-27T17:44:18Z","abstract_excerpt":"Large Reasoning Models (LRMs) exhibit remarkable reasoning abilities but rely primarily on parametric knowledge, limiting factual accuracy. While recent works equip reinforcement learning (RL)-based LRMs with retrieval capabilities, they suffer from overthinking and lack robustness in reasoning, reducing their effectiveness in question answering (QA) tasks. To address this, we propose ReaRAG, a factuality-enhanced reasoning model that explores diverse queries without excessive iterations. Our solution includes a novel data construction framework with an upper bound on the reasoning chain lengt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21729","kind":"arxiv","version":3},"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/2503.21729/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":"2503.21729","created_at":"2026-07-05T11:04:48.024628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21729v3","created_at":"2026-07-05T11:04:48.024628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21729","created_at":"2026-07-05T11:04:48.024628+00:00"},{"alias_kind":"pith_short_12","alias_value":"TS5TBZOF5Y4R","created_at":"2026-07-05T11:04:48.024628+00:00"},{"alias_kind":"pith_short_16","alias_value":"TS5TBZOF5Y4R7LJX","created_at":"2026-07-05T11:04:48.024628+00:00"},{"alias_kind":"pith_short_8","alias_value":"TS5TBZOF","created_at":"2026-07-05T11:04:48.024628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03540","citing_title":"Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04969","citing_title":"MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK","json":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK.json","graph_json":"https://pith.science/api/pith-number/TS5TBZOF5Y4R7LJXNU7H47QVBK/graph.json","events_json":"https://pith.science/api/pith-number/TS5TBZOF5Y4R7LJXNU7H47QVBK/events.json","paper":"https://pith.science/paper/TS5TBZOF"},"agent_actions":{"view_html":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK","download_json":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK.json","view_paper":"https://pith.science/paper/TS5TBZOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21729&json=true","fetch_graph":"https://pith.science/api/pith-number/TS5TBZOF5Y4R7LJXNU7H47QVBK/graph.json","fetch_events":"https://pith.science/api/pith-number/TS5TBZOF5Y4R7LJXNU7H47QVBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK/action/storage_attestation","attest_author":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK/action/author_attestation","sign_citation":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK/action/citation_signature","submit_replication":"https://pith.science/pith/TS5TBZOF5Y4R7LJXNU7H47QVBK/action/replication_record"}},"created_at":"2026-07-05T11:04:48.024628+00:00","updated_at":"2026-07-05T11:04:48.024628+00:00"}