{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R3VME7IBMCYVF74YOLNGA73IFT","short_pith_number":"pith:R3VME7IB","schema_version":"1.0","canonical_sha256":"8eeac27d0160b152ff9872da607f682cf9ea379fead8ad847e87607d768fa2f0","source":{"kind":"arxiv","id":"2210.10634","version":1},"attestation_state":"computed","paper":{"title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Honglei Zhuang, Jianmo Ni, Ji Ma, Jing Lu, Kai Hui, Michael Bendersky, Rolf Jagerman, Xuanhui Wang, Zhen Qin","submitted_at":"2022-10-12T20:51:49Z","abstract_excerpt":"Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT. However, there are limited studies on how to leverage more powerful sequence-to-sequence models such as T5. Existing attempts usually formulate text ranking as classification and rely on postprocessing to obtain a ranked list. In this paper, we propose RankT5 and study two T5-based ranking model structures, an encoder-decoder and an encoder-only one, so that they not only can directly output ranking scores for each query-document pair, but also can be fine-tuned with \"pairwise\" or \"li"},"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":"2210.10634","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-10-12T20:51:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"79b442d36a4891d45add4c4055ac10fd2a21dd04d0153f2affb19519cd070108","abstract_canon_sha256":"6dd9dba10c02ebc4c191c6a128f59b5b78b3fe323c758675edb1c0cfb0405407"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:22.003827Z","signature_b64":"/JACRUXd/ObQScDV8lXyNTk/H2P1D31SW9Yw+i0OYqnygrSC/kNR/d/LejY64BiOleUPIZ11Qm7WDNrrcRyIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eeac27d0160b152ff9872da607f682cf9ea379fead8ad847e87607d768fa2f0","last_reissued_at":"2026-07-05T05:08:22.003280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:22.003280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Honglei Zhuang, Jianmo Ni, Ji Ma, Jing Lu, Kai Hui, Michael Bendersky, Rolf Jagerman, Xuanhui Wang, Zhen Qin","submitted_at":"2022-10-12T20:51:49Z","abstract_excerpt":"Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT. However, there are limited studies on how to leverage more powerful sequence-to-sequence models such as T5. Existing attempts usually formulate text ranking as classification and rely on postprocessing to obtain a ranked list. In this paper, we propose RankT5 and study two T5-based ranking model structures, an encoder-decoder and an encoder-only one, so that they not only can directly output ranking scores for each query-document pair, but also can be fine-tuned with \"pairwise\" or \"li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10634","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/2210.10634/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":"2210.10634","created_at":"2026-07-05T05:08:22.003344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10634v1","created_at":"2026-07-05T05:08:22.003344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10634","created_at":"2026-07-05T05:08:22.003344+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3VME7IBMCYV","created_at":"2026-07-05T05:08:22.003344+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3VME7IBMCYVF74Y","created_at":"2026-07-05T05:08:22.003344+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3VME7IB","created_at":"2026-07-05T05:08:22.003344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03728","citing_title":"Re-Ranking Through an Attribution Lens for Citation Quality in Legal QA","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11653","citing_title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2312.02724","citing_title":"RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT","json":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT.json","graph_json":"https://pith.science/api/pith-number/R3VME7IBMCYVF74YOLNGA73IFT/graph.json","events_json":"https://pith.science/api/pith-number/R3VME7IBMCYVF74YOLNGA73IFT/events.json","paper":"https://pith.science/paper/R3VME7IB"},"agent_actions":{"view_html":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT","download_json":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT.json","view_paper":"https://pith.science/paper/R3VME7IB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10634&json=true","fetch_graph":"https://pith.science/api/pith-number/R3VME7IBMCYVF74YOLNGA73IFT/graph.json","fetch_events":"https://pith.science/api/pith-number/R3VME7IBMCYVF74YOLNGA73IFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT/action/storage_attestation","attest_author":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT/action/author_attestation","sign_citation":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT/action/citation_signature","submit_replication":"https://pith.science/pith/R3VME7IBMCYVF74YOLNGA73IFT/action/replication_record"}},"created_at":"2026-07-05T05:08:22.003344+00:00","updated_at":"2026-07-05T05:08:22.003344+00:00"}