{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YL3UL7NEU4SM5Z3OIPVBPZRKI3","short_pith_number":"pith:YL3UL7NE","schema_version":"1.0","canonical_sha256":"c2f745fda4a724cee76e43ea17e62a46f356a6af2336ba160c2380911c1c5508","source":{"kind":"arxiv","id":"2311.07994","version":1},"attestation_state":"computed","paper":{"title":"Text Retrieval with Multi-Stage Re-Ranking Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Kenichi Yokote, Osamu Imaichi, Yasuhiro Sogawa, Yuichi Sasazawa","submitted_at":"2023-11-14T08:47:51Z","abstract_excerpt":"The text retrieval is the task of retrieving similar documents to a search query, and it is important to improve retrieval accuracy while maintaining a certain level of retrieval speed. Existing studies have reported accuracy improvements using language models, but many of these do not take into account the reduction in search speed that comes with increased performance. In this study, we propose three-stage re-ranking model using model ensembles or larger language models to improve search accuracy while minimizing the search delay. We ranked the documents by BM25 and language models, and then"},"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":"2311.07994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-11-14T08:47:51Z","cross_cats_sorted":[],"title_canon_sha256":"152ecf63bc6238fa12139b27cbb3d914beb280eda4250b98bef04e3a59ca6e94","abstract_canon_sha256":"b3e6244c47d34939a5ca2ac1aedd3c00cfca99e68378b7fbd9b6392c06b334d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:26.887878Z","signature_b64":"+HaiC3aCOFZcuGUQQ2EC2SepJPgWY+8J5ppIBtTT9IuYwgp3He6hveHUCQc5i4mG07RG6cF2JwZUmZjB3WMWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2f745fda4a724cee76e43ea17e62a46f356a6af2336ba160c2380911c1c5508","last_reissued_at":"2026-07-05T07:12:26.887432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:26.887432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text Retrieval with Multi-Stage Re-Ranking Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Kenichi Yokote, Osamu Imaichi, Yasuhiro Sogawa, Yuichi Sasazawa","submitted_at":"2023-11-14T08:47:51Z","abstract_excerpt":"The text retrieval is the task of retrieving similar documents to a search query, and it is important to improve retrieval accuracy while maintaining a certain level of retrieval speed. Existing studies have reported accuracy improvements using language models, but many of these do not take into account the reduction in search speed that comes with increased performance. In this study, we propose three-stage re-ranking model using model ensembles or larger language models to improve search accuracy while minimizing the search delay. We ranked the documents by BM25 and language models, and then"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07994","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/2311.07994/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":"2311.07994","created_at":"2026-07-05T07:12:26.887491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07994v1","created_at":"2026-07-05T07:12:26.887491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07994","created_at":"2026-07-05T07:12:26.887491+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL3UL7NEU4SM","created_at":"2026-07-05T07:12:26.887491+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL3UL7NEU4SM5Z3O","created_at":"2026-07-05T07:12:26.887491+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL3UL7NE","created_at":"2026-07-05T07:12:26.887491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19265","citing_title":"Optimizing Multi-Stage Language Models for Effective Text Retrieval","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3","json":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3.json","graph_json":"https://pith.science/api/pith-number/YL3UL7NEU4SM5Z3OIPVBPZRKI3/graph.json","events_json":"https://pith.science/api/pith-number/YL3UL7NEU4SM5Z3OIPVBPZRKI3/events.json","paper":"https://pith.science/paper/YL3UL7NE"},"agent_actions":{"view_html":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3","download_json":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3.json","view_paper":"https://pith.science/paper/YL3UL7NE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07994&json=true","fetch_graph":"https://pith.science/api/pith-number/YL3UL7NEU4SM5Z3OIPVBPZRKI3/graph.json","fetch_events":"https://pith.science/api/pith-number/YL3UL7NEU4SM5Z3OIPVBPZRKI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3/action/storage_attestation","attest_author":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3/action/author_attestation","sign_citation":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3/action/citation_signature","submit_replication":"https://pith.science/pith/YL3UL7NEU4SM5Z3OIPVBPZRKI3/action/replication_record"}},"created_at":"2026-07-05T07:12:26.887491+00:00","updated_at":"2026-07-05T07:12:26.887491+00:00"}