{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KJNDD37QHLPEUMNVFOQF2EP5F6","short_pith_number":"pith:KJNDD37Q","schema_version":"1.0","canonical_sha256":"525a31eff03ade4a31b52ba05d11fd2fb695b55df885be87502ff4d57fd4fdd7","source":{"kind":"arxiv","id":"2403.19181","version":3},"attestation_state":"computed","paper":{"title":"Make Large Language Model a Better Ranker","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Hao Liu, Hengshu Zhu, Wen-Shuo Chao, Zhi Zheng","submitted_at":"2024-03-28T07:22:16Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate robust capabilities across various fields, leading to a paradigm shift in LLM-enhanced Recommender System (RS). Research to date focuses on point-wise and pair-wise recommendation paradigms, which are inefficient for LLM-based recommenders due to high computational costs. However, existing list-wise approaches also fall short in ranking tasks due to misalignment between ranking objectives and next-token prediction. Moreover, these LLM-based methods struggle to effectively address the order relation among candidates, particularly given the scale of ratin"},"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":"2403.19181","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-03-28T07:22:16Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"f16ebae15c49e4366f0062f02646e260a0da9c22a8849661c7a74bd26e23dd18","abstract_canon_sha256":"1de16ac6810f727d7904aa637a7ca79e1c8abad29e4896193e5d36cab3dabfc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:26.922118Z","signature_b64":"sahBkJgT7xIG0bBIRJH/tFllyg4fPhmoh4RYcp9k1QExLyqjbYTk8QPgDIWaQ93C1rWEfxReQ1VewxkuWmWYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"525a31eff03ade4a31b52ba05d11fd2fb695b55df885be87502ff4d57fd4fdd7","last_reissued_at":"2026-07-05T09:12:26.921640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:26.921640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make Large Language Model a Better Ranker","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Hao Liu, Hengshu Zhu, Wen-Shuo Chao, Zhi Zheng","submitted_at":"2024-03-28T07:22:16Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate robust capabilities across various fields, leading to a paradigm shift in LLM-enhanced Recommender System (RS). Research to date focuses on point-wise and pair-wise recommendation paradigms, which are inefficient for LLM-based recommenders due to high computational costs. However, existing list-wise approaches also fall short in ranking tasks due to misalignment between ranking objectives and next-token prediction. Moreover, these LLM-based methods struggle to effectively address the order relation among candidates, particularly given the scale of ratin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19181","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/2403.19181/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":"2403.19181","created_at":"2026-07-05T09:12:26.921697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19181v3","created_at":"2026-07-05T09:12:26.921697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19181","created_at":"2026-07-05T09:12:26.921697+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJNDD37QHLPE","created_at":"2026-07-05T09:12:26.921697+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJNDD37QHLPEUMNV","created_at":"2026-07-05T09:12:26.921697+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJNDD37Q","created_at":"2026-07-05T09:12:26.921697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27599","citing_title":"One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04559","citing_title":"Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6","json":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6.json","graph_json":"https://pith.science/api/pith-number/KJNDD37QHLPEUMNVFOQF2EP5F6/graph.json","events_json":"https://pith.science/api/pith-number/KJNDD37QHLPEUMNVFOQF2EP5F6/events.json","paper":"https://pith.science/paper/KJNDD37Q"},"agent_actions":{"view_html":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6","download_json":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6.json","view_paper":"https://pith.science/paper/KJNDD37Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19181&json=true","fetch_graph":"https://pith.science/api/pith-number/KJNDD37QHLPEUMNVFOQF2EP5F6/graph.json","fetch_events":"https://pith.science/api/pith-number/KJNDD37QHLPEUMNVFOQF2EP5F6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6/action/storage_attestation","attest_author":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6/action/author_attestation","sign_citation":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6/action/citation_signature","submit_replication":"https://pith.science/pith/KJNDD37QHLPEUMNVFOQF2EP5F6/action/replication_record"}},"created_at":"2026-07-05T09:12:26.921697+00:00","updated_at":"2026-07-05T09:12:26.921697+00:00"}