{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DYHENKXBXMC2QARNPZCNCAWOQD","short_pith_number":"pith:DYHENKXB","schema_version":"1.0","canonical_sha256":"1e0e46aae1bb05a8022d7e44d102ce80df1f727e4c2855d95682152f35fe0eb7","source":{"kind":"arxiv","id":"2101.00294","version":3},"attestation_state":"computed","paper":{"title":"Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Jiawei Han, Pengcheng He, Weizhu Chen, XiaoDong Liu, Yelong Shen, Yuning Mao","submitted_at":"2021-01-01T18:54:19Z","abstract_excerpt":"Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose a simple and effective passage reranking method, named Reader-guIDEd Reranker (RIDER), which does not involve training and reranks the retrieved passages solely based on the top predictions of the reader before reranking. We show that RIDER, despite its simplicity, achieves 10 to 20 absolute gains in top-1 retrieval accuracy and 1 to 4 Exact Match (EM) gain"},"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":"2101.00294","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-01T18:54:19Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"72a778f69906a0b1e28bcd01cda413bfc562a9280b6d0ba48919c87f24dd9d20","abstract_canon_sha256":"137ff4d63409a7deb57c7c5cae48004aa9fb701266b34b11be82d63323cf9751"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:49.513195Z","signature_b64":"9Wal7x+HLmZPgltVySd2pT9z+cuAyElj/jxPmDesjlH5IMuoYDfaKVaKrYCqVbPEVt0ojzpm3ZpvHUr4n2QuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e0e46aae1bb05a8022d7e44d102ce80df1f727e4c2855d95682152f35fe0eb7","last_reissued_at":"2026-07-05T03:03:49.512789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:49.512789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Jiawei Han, Pengcheng He, Weizhu Chen, XiaoDong Liu, Yelong Shen, Yuning Mao","submitted_at":"2021-01-01T18:54:19Z","abstract_excerpt":"Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose a simple and effective passage reranking method, named Reader-guIDEd Reranker (RIDER), which does not involve training and reranks the retrieved passages solely based on the top predictions of the reader before reranking. We show that RIDER, despite its simplicity, achieves 10 to 20 absolute gains in top-1 retrieval accuracy and 1 to 4 Exact Match (EM) gain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.00294","kind":"arxiv","version":3},"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/2101.00294/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":"2101.00294","created_at":"2026-07-05T03:03:49.512847+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.00294v3","created_at":"2026-07-05T03:03:49.512847+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.00294","created_at":"2026-07-05T03:03:49.512847+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYHENKXBXMC2","created_at":"2026-07-05T03:03:49.512847+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYHENKXBXMC2QARN","created_at":"2026-07-05T03:03:49.512847+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYHENKXB","created_at":"2026-07-05T03:03:49.512847+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12610","citing_title":"Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD","json":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD.json","graph_json":"https://pith.science/api/pith-number/DYHENKXBXMC2QARNPZCNCAWOQD/graph.json","events_json":"https://pith.science/api/pith-number/DYHENKXBXMC2QARNPZCNCAWOQD/events.json","paper":"https://pith.science/paper/DYHENKXB"},"agent_actions":{"view_html":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD","download_json":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD.json","view_paper":"https://pith.science/paper/DYHENKXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.00294&json=true","fetch_graph":"https://pith.science/api/pith-number/DYHENKXBXMC2QARNPZCNCAWOQD/graph.json","fetch_events":"https://pith.science/api/pith-number/DYHENKXBXMC2QARNPZCNCAWOQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD/action/storage_attestation","attest_author":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD/action/author_attestation","sign_citation":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD/action/citation_signature","submit_replication":"https://pith.science/pith/DYHENKXBXMC2QARNPZCNCAWOQD/action/replication_record"}},"created_at":"2026-07-05T03:03:49.512847+00:00","updated_at":"2026-07-05T03:03:49.512847+00:00"}