{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LPZ4WYNBNY5UHXTZLOILHDP3A3","short_pith_number":"pith:LPZ4WYNB","schema_version":"1.0","canonical_sha256":"5bf3cb61a16e3b43de795b90b38dfb06f97470dfec9f3c26a6d10e32b206fa84","source":{"kind":"arxiv","id":"2412.12881","version":1},"attestation_state":"computed","paper":{"title":"RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiayi Chen, Jinhao Jiang, Junyi Li, Ruiyang Ren, Shijie Wang, Tao Zhang, Wayne Xin Zhao, Yang Song","submitted_at":"2024-12-17T13:05:36Z","abstract_excerpt":"Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. Despite the successes of chain-of-thought and tree-based search methods, they mainly depend on the internal knowledge of LLMs to search over intermediate reasoning steps, limited to dealing with simple tasks involving fewer reasoning steps. In this paper, we propose \\textbf{RAG-Star}, a novel RAG approach that integrates the retrieved information to guide the tree-based deliberative reasoning process that relies on the inherent knowledge of LLMs. By leveraging Mo"},"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":"2412.12881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T13:05:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1cb35f2889adaf15231bc90bf03572787c7134c5396d8745dfd2007890267693","abstract_canon_sha256":"962631d1b7d10f6a8e219bd1cea4a51c9807e7c26af8764df9adb8c66ada6f0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:22.116154Z","signature_b64":"U9+d6r5Bl8UTZQJrf6bnaFQziUETbS7pqL1aOY9Tx3mZkDQ7cNkPut0YoODWCa4qO+E2d3wdbutwE04m4HRwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf3cb61a16e3b43de795b90b38dfb06f97470dfec9f3c26a6d10e32b206fa84","last_reissued_at":"2026-07-05T09:50:22.115458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:22.115458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiayi Chen, Jinhao Jiang, Junyi Li, Ruiyang Ren, Shijie Wang, Tao Zhang, Wayne Xin Zhao, Yang Song","submitted_at":"2024-12-17T13:05:36Z","abstract_excerpt":"Existing large language models (LLMs) show exceptional problem-solving capabilities but might struggle with complex reasoning tasks. Despite the successes of chain-of-thought and tree-based search methods, they mainly depend on the internal knowledge of LLMs to search over intermediate reasoning steps, limited to dealing with simple tasks involving fewer reasoning steps. In this paper, we propose \\textbf{RAG-Star}, a novel RAG approach that integrates the retrieved information to guide the tree-based deliberative reasoning process that relies on the inherent knowledge of LLMs. By leveraging Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12881","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/2412.12881/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":"2412.12881","created_at":"2026-07-05T09:50:22.115514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12881v1","created_at":"2026-07-05T09:50:22.115514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12881","created_at":"2026-07-05T09:50:22.115514+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPZ4WYNBNY5U","created_at":"2026-07-05T09:50:22.115514+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPZ4WYNBNY5UHXTZ","created_at":"2026-07-05T09:50:22.115514+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPZ4WYNB","created_at":"2026-07-05T09:50:22.115514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07299","citing_title":"DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00798","citing_title":"Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2503.05592","citing_title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3","json":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3.json","graph_json":"https://pith.science/api/pith-number/LPZ4WYNBNY5UHXTZLOILHDP3A3/graph.json","events_json":"https://pith.science/api/pith-number/LPZ4WYNBNY5UHXTZLOILHDP3A3/events.json","paper":"https://pith.science/paper/LPZ4WYNB"},"agent_actions":{"view_html":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3","download_json":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3.json","view_paper":"https://pith.science/paper/LPZ4WYNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12881&json=true","fetch_graph":"https://pith.science/api/pith-number/LPZ4WYNBNY5UHXTZLOILHDP3A3/graph.json","fetch_events":"https://pith.science/api/pith-number/LPZ4WYNBNY5UHXTZLOILHDP3A3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3/action/storage_attestation","attest_author":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3/action/author_attestation","sign_citation":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3/action/citation_signature","submit_replication":"https://pith.science/pith/LPZ4WYNBNY5UHXTZLOILHDP3A3/action/replication_record"}},"created_at":"2026-07-05T09:50:22.115514+00:00","updated_at":"2026-07-05T09:50:22.115514+00:00"}