{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TSPV5ARU3L65FQ4T2MW4AN6TLP","short_pith_number":"pith:TSPV5ARU","schema_version":"1.0","canonical_sha256":"9c9f5e8234dafdd2c393d32dc037d35bfe498dab46671fc56b2a61ee0078e49d","source":{"kind":"arxiv","id":"2506.19466","version":2},"attestation_state":"computed","paper":{"title":"KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Li, Jiexiong Liu, KunLun Meta, Qihang Zhou, Yixuan Chen","submitted_at":"2025-06-24T09:48:01Z","abstract_excerpt":"This paper introduces KunLunBaizeRAG, a reinforcement learning-driven reasoning framework designed to enhance the reasoning capabilities of large language models (LLMs) in complex multi-hop question-answering tasks. The framework addresses key limitations of traditional RAG, such as retrieval drift, information redundancy, and strategy rigidity. Key innovations include the RAG-driven Reasoning Alignment (RDRA) mechanism, the Search-Think Iterative Enhancement (STIE) mechanism, the Network-Local Intelligent Routing (NLR) mechanism, and a progressive hybrid training strategy. Experimental result"},"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":"2506.19466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-24T09:48:01Z","cross_cats_sorted":[],"title_canon_sha256":"3ff1fc2385fc403187b07ca3a10a3ccc88abda5368f5b90a3fd707815ba371a3","abstract_canon_sha256":"fb7f3f1487ec76c17b5691b25c744e87ebea1a2f1bd60a1cae5263f1d83d2b42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:17.932254Z","signature_b64":"pFV+4P9xByTSseJwvNWDl+1yjIAQXutS7a8j5cg/2J53IM2sjuS4QhdTztyl0nHGaDrDFyWINl7S/Ci8nsogDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c9f5e8234dafdd2c393d32dc037d35bfe498dab46671fc56b2a61ee0078e49d","last_reissued_at":"2026-07-05T11:28:17.931729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:17.931729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Li, Jiexiong Liu, KunLun Meta, Qihang Zhou, Yixuan Chen","submitted_at":"2025-06-24T09:48:01Z","abstract_excerpt":"This paper introduces KunLunBaizeRAG, a reinforcement learning-driven reasoning framework designed to enhance the reasoning capabilities of large language models (LLMs) in complex multi-hop question-answering tasks. The framework addresses key limitations of traditional RAG, such as retrieval drift, information redundancy, and strategy rigidity. Key innovations include the RAG-driven Reasoning Alignment (RDRA) mechanism, the Search-Think Iterative Enhancement (STIE) mechanism, the Network-Local Intelligent Routing (NLR) mechanism, and a progressive hybrid training strategy. Experimental result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19466","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/2506.19466/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":"2506.19466","created_at":"2026-07-05T11:28:17.931783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19466v2","created_at":"2026-07-05T11:28:17.931783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19466","created_at":"2026-07-05T11:28:17.931783+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSPV5ARU3L65","created_at":"2026-07-05T11:28:17.931783+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSPV5ARU3L65FQ4T","created_at":"2026-07-05T11:28:17.931783+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSPV5ARU","created_at":"2026-07-05T11:28:17.931783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP","json":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP.json","graph_json":"https://pith.science/api/pith-number/TSPV5ARU3L65FQ4T2MW4AN6TLP/graph.json","events_json":"https://pith.science/api/pith-number/TSPV5ARU3L65FQ4T2MW4AN6TLP/events.json","paper":"https://pith.science/paper/TSPV5ARU"},"agent_actions":{"view_html":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP","download_json":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP.json","view_paper":"https://pith.science/paper/TSPV5ARU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19466&json=true","fetch_graph":"https://pith.science/api/pith-number/TSPV5ARU3L65FQ4T2MW4AN6TLP/graph.json","fetch_events":"https://pith.science/api/pith-number/TSPV5ARU3L65FQ4T2MW4AN6TLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP/action/storage_attestation","attest_author":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP/action/author_attestation","sign_citation":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP/action/citation_signature","submit_replication":"https://pith.science/pith/TSPV5ARU3L65FQ4T2MW4AN6TLP/action/replication_record"}},"created_at":"2026-07-05T11:28:17.931783+00:00","updated_at":"2026-07-05T11:28:17.931783+00:00"}