{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WBE3VZJFTCXFQHPSOAVLZHAXJB","short_pith_number":"pith:WBE3VZJF","schema_version":"1.0","canonical_sha256":"b049bae52598ae581df2702abc9c17486a1db1f5136c70da043517a0185dddb4","source":{"kind":"arxiv","id":"2501.16302","version":1},"attestation_state":"computed","paper":{"title":"Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaofan Li, Chaozhuo Li, Defu Lian, Shitao Xiao, Yingxia Shao, Zheng Liu","submitted_at":"2025-01-27T18:42:48Z","abstract_excerpt":"Large language models (LLMs) provide powerful foundations to perform fine-grained text re-ranking. However, they are often prohibitive in reality due to constraints on computation bandwidth. In this work, we propose a \\textbf{flexible} architecture called \\textbf{Matroyshka Re-Ranker}, which is designed to facilitate \\textbf{runtime customization} of model layers and sequence lengths at each layer based on users' configurations. Consequently, the LLM-based re-rankers can be made applicable across various real-world situations. The increased flexibility may come at the cost of precision loss. T"},"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":"2501.16302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T18:42:48Z","cross_cats_sorted":[],"title_canon_sha256":"18a1aad8e019c919ad6d0a56f829a2f045a957f29b862b29c2a6eb3d2d9f60d4","abstract_canon_sha256":"a1e7664adcf8c932ebf5e59bab9ffe7f194bf81518013906a0f15a6a452127a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:58.259403Z","signature_b64":"uBNbkcwjdR/ilmJ2DMRkb2tAfN1L4PR+/F53yW9uyoiBUKeOuWXMABA/DW5pwHSfO90+JAkhY/JkcUOneS67Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b049bae52598ae581df2702abc9c17486a1db1f5136c70da043517a0185dddb4","last_reissued_at":"2026-07-05T10:05:58.258854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:58.258854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matryoshka Re-Ranker: A Flexible Re-Ranking Architecture With Configurable Depth and Width","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaofan Li, Chaozhuo Li, Defu Lian, Shitao Xiao, Yingxia Shao, Zheng Liu","submitted_at":"2025-01-27T18:42:48Z","abstract_excerpt":"Large language models (LLMs) provide powerful foundations to perform fine-grained text re-ranking. However, they are often prohibitive in reality due to constraints on computation bandwidth. In this work, we propose a \\textbf{flexible} architecture called \\textbf{Matroyshka Re-Ranker}, which is designed to facilitate \\textbf{runtime customization} of model layers and sequence lengths at each layer based on users' configurations. Consequently, the LLM-based re-rankers can be made applicable across various real-world situations. The increased flexibility may come at the cost of precision loss. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16302","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/2501.16302/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":"2501.16302","created_at":"2026-07-05T10:05:58.258912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16302v1","created_at":"2026-07-05T10:05:58.258912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16302","created_at":"2026-07-05T10:05:58.258912+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBE3VZJFTCXF","created_at":"2026-07-05T10:05:58.258912+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBE3VZJFTCXFQHPS","created_at":"2026-07-05T10:05:58.258912+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBE3VZJF","created_at":"2026-07-05T10:05:58.258912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.14558","citing_title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23386","citing_title":"Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26483","citing_title":"Efficient Listwise Reranking with Compressed Document Representations","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB","json":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB.json","graph_json":"https://pith.science/api/pith-number/WBE3VZJFTCXFQHPSOAVLZHAXJB/graph.json","events_json":"https://pith.science/api/pith-number/WBE3VZJFTCXFQHPSOAVLZHAXJB/events.json","paper":"https://pith.science/paper/WBE3VZJF"},"agent_actions":{"view_html":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB","download_json":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB.json","view_paper":"https://pith.science/paper/WBE3VZJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16302&json=true","fetch_graph":"https://pith.science/api/pith-number/WBE3VZJFTCXFQHPSOAVLZHAXJB/graph.json","fetch_events":"https://pith.science/api/pith-number/WBE3VZJFTCXFQHPSOAVLZHAXJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB/action/storage_attestation","attest_author":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB/action/author_attestation","sign_citation":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB/action/citation_signature","submit_replication":"https://pith.science/pith/WBE3VZJFTCXFQHPSOAVLZHAXJB/action/replication_record"}},"created_at":"2026-07-05T10:05:58.258912+00:00","updated_at":"2026-07-05T10:05:58.258912+00:00"}