{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FKOUJ3TYBG3OF5NHXC3LROX6PP","short_pith_number":"pith:FKOUJ3TY","schema_version":"1.0","canonical_sha256":"2a9d44ee7809b6e2f5a7b8b6b8bafe7bf1c1bba2ee16708ad845b72ef380c059","source":{"kind":"arxiv","id":"2206.08063","version":1},"attestation_state":"computed","paper":{"title":"Towards Robust Ranker for Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Binxing Jiao, Can Xu, Chongyang Tao, Daxin Jiang, Guodong Long, Tao Shen, Xiubo Geng, Yucheng Zhou","submitted_at":"2022-06-16T10:27:46Z","abstract_excerpt":"A ranker plays an indispensable role in the de facto 'retrieval & rerank' pipeline, but its training still lags behind -- learning from moderate negatives or/and serving as an auxiliary module for a retriever. In this work, we first identify two major barriers to a robust ranker, i.e., inherent label noises caused by a well-trained retriever and non-ideal negatives sampled for a high-capable ranker. Thereby, we propose multiple retrievers as negative generators improve the ranker's robustness, where i) involving extensive out-of-distribution label noises renders the ranker against each noise d"},"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":"2206.08063","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-06-16T10:27:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"79badaeb3f713fc4d0e8493a5bb6eff5852be1928644d7b91694c6def1d1709d","abstract_canon_sha256":"a4053fce101380277acc40ad3593ba6d76ff65ca0d520a02f29b934b607dc0d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:21.771779Z","signature_b64":"7BEH2zjFjawKpUJyzoHy9qYLEEPMtWnULyfEUClYZZFv9gBvP7QTeQnpT1+dAFowG6Z6QxDOiKizH6ZNKFYXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a9d44ee7809b6e2f5a7b8b6b8bafe7bf1c1bba2ee16708ad845b72ef380c059","last_reissued_at":"2026-07-05T04:32:21.771233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:21.771233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Robust Ranker for Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Binxing Jiao, Can Xu, Chongyang Tao, Daxin Jiang, Guodong Long, Tao Shen, Xiubo Geng, Yucheng Zhou","submitted_at":"2022-06-16T10:27:46Z","abstract_excerpt":"A ranker plays an indispensable role in the de facto 'retrieval & rerank' pipeline, but its training still lags behind -- learning from moderate negatives or/and serving as an auxiliary module for a retriever. In this work, we first identify two major barriers to a robust ranker, i.e., inherent label noises caused by a well-trained retriever and non-ideal negatives sampled for a high-capable ranker. Thereby, we propose multiple retrievers as negative generators improve the ranker's robustness, where i) involving extensive out-of-distribution label noises renders the ranker against each noise d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08063","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/2206.08063/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":"2206.08063","created_at":"2026-07-05T04:32:21.771299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08063v1","created_at":"2026-07-05T04:32:21.771299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08063","created_at":"2026-07-05T04:32:21.771299+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKOUJ3TYBG3O","created_at":"2026-07-05T04:32:21.771299+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKOUJ3TYBG3OF5NH","created_at":"2026-07-05T04:32:21.771299+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKOUJ3TY","created_at":"2026-07-05T04:32:21.771299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22584","citing_title":"DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP","json":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP.json","graph_json":"https://pith.science/api/pith-number/FKOUJ3TYBG3OF5NHXC3LROX6PP/graph.json","events_json":"https://pith.science/api/pith-number/FKOUJ3TYBG3OF5NHXC3LROX6PP/events.json","paper":"https://pith.science/paper/FKOUJ3TY"},"agent_actions":{"view_html":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP","download_json":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP.json","view_paper":"https://pith.science/paper/FKOUJ3TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08063&json=true","fetch_graph":"https://pith.science/api/pith-number/FKOUJ3TYBG3OF5NHXC3LROX6PP/graph.json","fetch_events":"https://pith.science/api/pith-number/FKOUJ3TYBG3OF5NHXC3LROX6PP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP/action/storage_attestation","attest_author":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP/action/author_attestation","sign_citation":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP/action/citation_signature","submit_replication":"https://pith.science/pith/FKOUJ3TYBG3OF5NHXC3LROX6PP/action/replication_record"}},"created_at":"2026-07-05T04:32:21.771299+00:00","updated_at":"2026-07-05T04:32:21.771299+00:00"}