{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IETDEUVIITI6SUJJVXN7DDVHOH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a1764aefe86bc9a17300c6cb55a7b0430df1adeed4cd013070a656f3e56ba22b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-05T12:39:00Z","title_canon_sha256":"7c9305e0dd384640ff8818643ff60e7641a95c68dde202c7fa51bf54f9435d63"},"schema_version":"1.0","source":{"id":"2312.02724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02724","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02724v1","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02724","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"IETDEUVIITI6","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"IETDEUVIITI6SUJJ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"IETDEUVI","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:66f0fc69855ae8481a9f8947083ae9a3d233fc008ad4db7d5cbe470c7305b074","target":"graph","created_at":"2026-05-17T23:38:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"RankZephyr not only bridges the effectiveness gap with GPT-4 but in some cases surpasses the proprietary model."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"An open-source LLM for listwise zero-shot reranking matches or surpasses GPT-4 on multiple retrieval benchmarks."}],"snapshot_sha256":"f473119540cb2855e43226b0423a89f1c9c9e6a26b336dddd63688b2e7f416f4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Jimmy Lin, Ronak Pradeep, Sahel Sharifymoghaddam","cross_cats":[],"headline":"An open-source LLM for listwise zero-shot reranking matches or surpasses GPT-4 on multiple retrieval benchmarks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-05T12:39:00Z","title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!"},"references":{"count":42,"internal_anchors":5,"resolved_work":42,"sample":[{"cited_arxiv_id":"1611.09268","doi":"","is_internal_anchor":true,"ref_index":1,"title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","work_id":"78d498ce-11db-4f88-8eb0-40e0f86af615","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"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","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"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","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Barla Cambazoglu, Hugo Zaragoza, Olivier Chapelle, Jiang Chen, Ciya Liao, Zhaohui Zheng, and Jon Degenhardt","work_id":"ed02f770-7aac-4f93-83a0-1b54059ea148","year":2010},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"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","year":2020}],"snapshot_sha256":"4bc1177d4cbd6c3944f4c5932af6026b65d9b618c93f50832041417b79a2984a"},"source":{"id":"2312.02724","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T23:36:55.601641Z","id":"60b5ed54-f5fe-4bea-8172-5d0e845236b7","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"An open-source LLM for listwise zero-shot reranking matches or surpasses GPT-4 on multiple retrieval benchmarks.","strongest_claim":"RankZephyr not only bridges the effectiveness gap with GPT-4 but in some cases surpasses the proprietary model.","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."}},"verdict_id":"60b5ed54-f5fe-4bea-8172-5d0e845236b7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:441e58b74a9350d56564d2a155d0b5bb423c96aa2386bd01837940858d7ac19d","target":"record","created_at":"2026-05-17T23:38:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a1764aefe86bc9a17300c6cb55a7b0430df1adeed4cd013070a656f3e56ba22b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-12-05T12:39:00Z","title_canon_sha256":"7c9305e0dd384640ff8818643ff60e7641a95c68dde202c7fa51bf54f9435d63"},"schema_version":"1.0","source":{"id":"2312.02724","kind":"arxiv","version":1}},"canonical_sha256":"41263252a844d1e95129addbf18ea771c7718639ac15c501d23c85f88a3b863d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41263252a844d1e95129addbf18ea771c7718639ac15c501d23c85f88a3b863d","first_computed_at":"2026-05-17T23:38:49.741805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.741805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vSSKi+04x/LSuq/+J2k4aT2Yl7kOkdXMMYcj7sr2bTmlt8GhfoyQnFoyo5AYbmQIKNF9jmAZR1/eRnMIny2YAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.742986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:441e58b74a9350d56564d2a155d0b5bb423c96aa2386bd01837940858d7ac19d","sha256:66f0fc69855ae8481a9f8947083ae9a3d233fc008ad4db7d5cbe470c7305b074"],"state_sha256":"2901ceb9cf61da2f103cf4007327180d41a13c644ef713ed07fe85c32f3cfb86"}