{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IETDEUVIITI6SUJJVXN7DDVHOH","short_pith_number":"pith:IETDEUVI","schema_version":"1.0","canonical_sha256":"41263252a844d1e95129addbf18ea771c7718639ac15c501d23c85f88a3b863d","source":{"kind":"arxiv","id":"2312.02724","version":1},"attestation_state":"computed","paper":{"title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An open-source LLM for listwise zero-shot reranking matches or surpasses GPT-4 on multiple retrieval benchmarks.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Ronak Pradeep, Sahel Sharifymoghaddam","submitted_at":"2023-12-05T12:39:00Z","abstract_excerpt":"In information retrieval, proprietary large language models (LLMs) such as GPT-4 and open-source counterparts such as LLaMA and Vicuna have played a vital role in reranking. However, the gap between open-source and closed models persists, with reliance on proprietary, non-transparent models constraining reproducibility. Addressing this gap, we introduce RankZephyr, a state-of-the-art, open-source LLM for listwise zero-shot reranking. RankZephyr not only bridges the effectiveness gap with GPT-4 but in some cases surpasses the proprietary model. Our comprehensive evaluations across several datas"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.02724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-05T12:39:00Z","cross_cats_sorted":[],"title_canon_sha256":"7c9305e0dd384640ff8818643ff60e7641a95c68dde202c7fa51bf54f9435d63","abstract_canon_sha256":"a1764aefe86bc9a17300c6cb55a7b0430df1adeed4cd013070a656f3e56ba22b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.742986Z","signature_b64":"vSSKi+04x/LSuq/+J2k4aT2Yl7kOkdXMMYcj7sr2bTmlt8GhfoyQnFoyo5AYbmQIKNF9jmAZR1/eRnMIny2YAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41263252a844d1e95129addbf18ea771c7718639ac15c501d23c85f88a3b863d","last_reissued_at":"2026-05-17T23:38:49.741805Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.741805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An open-source LLM for listwise zero-shot reranking matches or surpasses GPT-4 on multiple retrieval benchmarks.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jimmy Lin, Ronak Pradeep, Sahel Sharifymoghaddam","submitted_at":"2023-12-05T12:39:00Z","abstract_excerpt":"In information retrieval, proprietary large language models (LLMs) such as GPT-4 and open-source counterparts such as LLaMA and Vicuna have played a vital role in reranking. However, the gap between open-source and closed models persists, with reliance on proprietary, non-transparent models constraining reproducibility. Addressing this gap, we introduce RankZephyr, a state-of-the-art, open-source LLM for listwise zero-shot reranking. RankZephyr not only bridges the effectiveness gap with GPT-4 but in some cases surpasses the proprietary model. Our comprehensive evaluations across several datas"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"RankZephyr not only bridges the effectiveness gap with GPT-4 but in some cases surpasses the proprietary model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the NovelEval test set truly contains only queries and passages created after the model's training cutoff and that no leakage occurred during fine-tuning or evaluation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RankZephyr is a new open-source LLM that closes the effectiveness gap with GPT-4 for zero-shot listwise reranking while showing robustness to input ordering and document count.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An open-source LLM for listwise zero-shot reranking matches or surpasses GPT-4 on multiple retrieval benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f473119540cb2855e43226b0423a89f1c9c9e6a26b336dddd63688b2e7f416f4"},"source":{"id":"2312.02724","kind":"arxiv","version":1},"verdict":{"id":"60b5ed54-f5fe-4bea-8172-5d0e845236b7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T23:36:55.601641Z","strongest_claim":"RankZephyr not only bridges the effectiveness gap with GPT-4 but in some cases surpasses the proprietary model.","one_line_summary":"RankZephyr is a new open-source LLM that closes the effectiveness gap with GPT-4 for zero-shot listwise reranking while showing robustness to input ordering and document count.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the NovelEval test set truly contains only queries and passages created after the model's training cutoff and that no leakage occurred during fine-tuning or evaluation.","pith_extraction_headline":"An open-source LLM for listwise zero-shot reranking matches or surpasses GPT-4 on multiple retrieval benchmarks."},"references":{"count":42,"sample":[{"doi":"","year":2016,"title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","work_id":"78d498ce-11db-4f88-8eb0-40e0f86af615","ref_index":1,"cited_arxiv_id":"1611.09268","is_internal_anchor":true},{"doi":"","year":2022,"title":"Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee, and Rodrigo Nogueira. 2022. InPars : Unsupervised dataset generation for information retrieval. In Proceedings of the 45th International ACM SIGIR Confer","work_id":"f57f0193-e00a-485d-9e96-2256c1f2509e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Leonid Boytsov, Preksha Patel, Vivek Sourabh, Riddhi Nisar, Sayani Kundu, Ramya Ramanathan, and Eric Nyberg. 2023. InPars-Light : Cost-effective unsupervised training of efficient rankers. arXiv:2301.","work_id":"c983ce83-cafd-4482-a355-da0aa94208c0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"Barla Cambazoglu, Hugo Zaragoza, Olivier Chapelle, Jiang Chen, Ciya Liao, Zhaohui Zheng, and Jon Degenhardt","work_id":"ed02f770-7aac-4f93-83a0-1b54059ea148","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Nick Craswell, Bhaskar Mitra, Emine Yilmaz, and Daniel Campos. 2020. Overview of the TREC 2020 deep learning track. In Proceedings of the Twenty-Ninth Text REtrieval Conference Proceedings (TREC 2020)","work_id":"d1e2aca6-6446-49d3-8c67-f02af05fb24d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":42,"snapshot_sha256":"4bc1177d4cbd6c3944f4c5932af6026b65d9b618c93f50832041417b79a2984a","internal_anchors":5},"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":"2312.02724","created_at":"2026-05-17T23:38:49.741895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02724v1","created_at":"2026-05-17T23:38:49.741895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02724","created_at":"2026-05-17T23:38:49.741895+00:00"},{"alias_kind":"pith_short_12","alias_value":"IETDEUVIITI6","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"IETDEUVIITI6SUJJ","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"IETDEUVI","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2502.00709","citing_title":"RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20683","citing_title":"Layer-wise Token Compression for Efficient Document Reranking","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21948","citing_title":"SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20683","citing_title":"Layer-wise Token Compression for Efficient Document Reranking","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2511.11653","citing_title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22591","citing_title":"Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06132","citing_title":"MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12995","citing_title":"F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12755","citing_title":"State-Centric Decision Process","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11864","citing_title":"Very Efficient Listwise Multimodal Reranking for Long Documents","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27577","citing_title":"Reproducing Adaptive Reranking for Reasoning-Intensive IR","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26483","citing_title":"Efficient Listwise Reranking with Compressed Document Representations","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08737","citing_title":"The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23734","citing_title":"Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22180","citing_title":"ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06132","citing_title":"MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01399","citing_title":"Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01591","citing_title":"Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00400","citing_title":"FollowTable: A Benchmark for Instruction-Following Table Retrieval","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19899","citing_title":"A Reproducibility Study of Metacognitive Retrieval-Augmented Generation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09492","citing_title":"Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05204","citing_title":"Entities as Retrieval Signals: A Systematic Study of Coverage, Supervision, and Evaluation in Entity-Oriented Ranking","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17738","citing_title":"Mira-Embeddings-V1: Domain-Adapted Semantic Reranking for Recruitment via LLM-Synthesized Data","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15621","citing_title":"Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH","json":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH.json","graph_json":"https://pith.science/api/pith-number/IETDEUVIITI6SUJJVXN7DDVHOH/graph.json","events_json":"https://pith.science/api/pith-number/IETDEUVIITI6SUJJVXN7DDVHOH/events.json","paper":"https://pith.science/paper/IETDEUVI"},"agent_actions":{"view_html":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH","download_json":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH.json","view_paper":"https://pith.science/paper/IETDEUVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02724&json=true","fetch_graph":"https://pith.science/api/pith-number/IETDEUVIITI6SUJJVXN7DDVHOH/graph.json","fetch_events":"https://pith.science/api/pith-number/IETDEUVIITI6SUJJVXN7DDVHOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH/action/storage_attestation","attest_author":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH/action/author_attestation","sign_citation":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH/action/citation_signature","submit_replication":"https://pith.science/pith/IETDEUVIITI6SUJJVXN7DDVHOH/action/replication_record"}},"created_at":"2026-05-17T23:38:49.741895+00:00","updated_at":"2026-05-17T23:38:49.741895+00:00"}