{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MC5IT5HOWTF4GDJJ5Y4YYFLCGW","short_pith_number":"pith:MC5IT5HO","schema_version":"1.0","canonical_sha256":"60ba89f4eeb4cbc30d29ee398c156235b96a46d667a936f082add91c91acb606","source":{"kind":"arxiv","id":"2404.11791","version":1},"attestation_state":"computed","paper":{"title":"Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Harrie Oosterhuis, Honglei Zhuang, Le Yan, Michael Bendersky, Rolf Jagerman, Xuanhui Wang, Zhen Qin","submitted_at":"2024-04-17T22:57:30Z","abstract_excerpt":"The powerful generative abilities of large language models (LLMs) show potential in generating relevance labels for search applications. Previous work has found that directly asking about relevancy, such as ``How relevant is document A to query Q?\", results in sub-optimal ranking. Instead, the pairwise ranking prompting (PRP) approach produces promising ranking performance through asking about pairwise comparisons, e.g., ``Is document A more relevant than document B to query Q?\". Thus, while LLMs are effective at their ranking ability, this is not reflected in their relevance label generation."},"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":"2404.11791","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-04-17T22:57:30Z","cross_cats_sorted":[],"title_canon_sha256":"23aca9db528992a4beda635a8c516fe943b6fd418c41caafe15209333c21a7fc","abstract_canon_sha256":"d5a99fcf64fe24628b10a249c6b6866a535ee2bb03b6ea1d12c9ff99cb82c8b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:15.940550Z","signature_b64":"h9HeluMstZA+I7QvYEz/kM3nnvAXXnUrh59bbiVgPetRfMwD0W/ucGFdjtkdFP9M0dsHssVuGqe3HQdmr89FCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60ba89f4eeb4cbc30d29ee398c156235b96a46d667a936f082add91c91acb606","last_reissued_at":"2026-07-05T08:09:15.940074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:15.940074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Harrie Oosterhuis, Honglei Zhuang, Le Yan, Michael Bendersky, Rolf Jagerman, Xuanhui Wang, Zhen Qin","submitted_at":"2024-04-17T22:57:30Z","abstract_excerpt":"The powerful generative abilities of large language models (LLMs) show potential in generating relevance labels for search applications. Previous work has found that directly asking about relevancy, such as ``How relevant is document A to query Q?\", results in sub-optimal ranking. Instead, the pairwise ranking prompting (PRP) approach produces promising ranking performance through asking about pairwise comparisons, e.g., ``Is document A more relevant than document B to query Q?\". Thus, while LLMs are effective at their ranking ability, this is not reflected in their relevance label generation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11791","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/2404.11791/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":"2404.11791","created_at":"2026-07-05T08:09:15.940130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11791v1","created_at":"2026-07-05T08:09:15.940130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11791","created_at":"2026-07-05T08:09:15.940130+00:00"},{"alias_kind":"pith_short_12","alias_value":"MC5IT5HOWTF4","created_at":"2026-07-05T08:09:15.940130+00:00"},{"alias_kind":"pith_short_16","alias_value":"MC5IT5HOWTF4GDJJ","created_at":"2026-07-05T08:09:15.940130+00:00"},{"alias_kind":"pith_short_8","alias_value":"MC5IT5HO","created_at":"2026-07-05T08:09:15.940130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":271,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW","json":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW.json","graph_json":"https://pith.science/api/pith-number/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/graph.json","events_json":"https://pith.science/api/pith-number/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/events.json","paper":"https://pith.science/paper/MC5IT5HO"},"agent_actions":{"view_html":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW","download_json":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW.json","view_paper":"https://pith.science/paper/MC5IT5HO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11791&json=true","fetch_graph":"https://pith.science/api/pith-number/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/graph.json","fetch_events":"https://pith.science/api/pith-number/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/action/storage_attestation","attest_author":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/action/author_attestation","sign_citation":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/action/citation_signature","submit_replication":"https://pith.science/pith/MC5IT5HOWTF4GDJJ5Y4YYFLCGW/action/replication_record"}},"created_at":"2026-07-05T08:09:15.940130+00:00","updated_at":"2026-07-05T08:09:15.940130+00:00"}