{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2J7222LPMVE23XFX6EUF5WM2HD","short_pith_number":"pith:2J7222LP","schema_version":"1.0","canonical_sha256":"d27fad696f6549addcb7f1285ed99a38fb4ae5d94c167aa7c302f40ce8cc4c81","source":{"kind":"arxiv","id":"2411.00142","version":1},"attestation_state":"computed","paper":{"title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Semih Yavuz, Shafiq Joty, Tong Niu, Ye Liu, Yingbo Zhou","submitted_at":"2024-10-31T18:43:12Z","abstract_excerpt":"Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense encoders or listwise rerankers in RAG systems, they often struggle with reasoning-intensive tasks because they lack nuanced analysis when judging document relevance. To address this limitation, we introduce JudgeRank, a novel agentic reranker that emulates human cognitive processes when assessing document relevance. Our approach consists of three key steps: (1) qu"},"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":"2411.00142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T18:43:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"529c51b8f93365309330604364e4a02d7488fe1af248195ae3204f9419ab3859","abstract_canon_sha256":"4fcf35163d60d6165dbe8a792624833a2b378f35ea8feca355de62995e840f33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:38.138706Z","signature_b64":"tPwN0VJ8EdzbJa2b37PF0D1RZxUAvskFuDgYkuYKpwE+9/Mrx9yGtZG2tmGlmwcHXTkQs2y889LcGd4wHbD/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d27fad696f6549addcb7f1285ed99a38fb4ae5d94c167aa7c302f40ce8cc4c81","last_reissued_at":"2026-07-05T09:29:38.138236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:38.138236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Semih Yavuz, Shafiq Joty, Tong Niu, Ye Liu, Yingbo Zhou","submitted_at":"2024-10-31T18:43:12Z","abstract_excerpt":"Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense encoders or listwise rerankers in RAG systems, they often struggle with reasoning-intensive tasks because they lack nuanced analysis when judging document relevance. To address this limitation, we introduce JudgeRank, a novel agentic reranker that emulates human cognitive processes when assessing document relevance. Our approach consists of three key steps: (1) qu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00142","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/2411.00142/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":"2411.00142","created_at":"2026-07-05T09:29:38.138291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00142v1","created_at":"2026-07-05T09:29:38.138291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00142","created_at":"2026-07-05T09:29:38.138291+00:00"},{"alias_kind":"pith_short_12","alias_value":"2J7222LPMVE2","created_at":"2026-07-05T09:29:38.138291+00:00"},{"alias_kind":"pith_short_16","alias_value":"2J7222LPMVE23XFX","created_at":"2026-07-05T09:29:38.138291+00:00"},{"alias_kind":"pith_short_8","alias_value":"2J7222LP","created_at":"2026-07-05T09:29:38.138291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.29002","citing_title":"Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27852","citing_title":"NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00063","citing_title":"A Survey of Reasoning-Intensive Retrieval: Progress and Challenges","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD","json":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD.json","graph_json":"https://pith.science/api/pith-number/2J7222LPMVE23XFX6EUF5WM2HD/graph.json","events_json":"https://pith.science/api/pith-number/2J7222LPMVE23XFX6EUF5WM2HD/events.json","paper":"https://pith.science/paper/2J7222LP"},"agent_actions":{"view_html":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD","download_json":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD.json","view_paper":"https://pith.science/paper/2J7222LP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00142&json=true","fetch_graph":"https://pith.science/api/pith-number/2J7222LPMVE23XFX6EUF5WM2HD/graph.json","fetch_events":"https://pith.science/api/pith-number/2J7222LPMVE23XFX6EUF5WM2HD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD/action/storage_attestation","attest_author":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD/action/author_attestation","sign_citation":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD/action/citation_signature","submit_replication":"https://pith.science/pith/2J7222LPMVE23XFX6EUF5WM2HD/action/replication_record"}},"created_at":"2026-07-05T09:29:38.138291+00:00","updated_at":"2026-07-05T09:29:38.138291+00:00"}