{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OGAI753BYCPWZFQCKNL3XZ7VM7","short_pith_number":"pith:OGAI753B","schema_version":"1.0","canonical_sha256":"71808ff761c09f6c96025357bbe7f567f25c57e692cdc0de1bd426ddb1e03268","source":{"kind":"arxiv","id":"2502.18418","version":2},"attestation_state":"computed","paper":{"title":"Rank1: Test-Time Compute for Reranking in Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Benjamin Van Durme, Dawn Lawrie, Eugene Yang, Kathryn Ricci, Orion Weller","submitted_at":"2025-02-25T18:14:06Z","abstract_excerpt":"We introduce Rank1, the first reranking model trained to take advantage of test-time compute. Rank1 demonstrates the applicability within retrieval of using a reasoning language model (i.e. OpenAI's o1, Deepseek's R1, etc.) for distillation in order to rapidly improve the performance of a smaller model. We gather and open-source a dataset of more than 600,000 examples of R1 reasoning traces from queries and passages in MS MARCO. Models trained on this dataset show: (1) state-of-the-art performance on advanced reasoning and instruction following datasets; (2) work remarkably well out of distrib"},"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":"2502.18418","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-25T18:14:06Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c56b4e3ab97083fa606a9125a85555db446dc471337ca0294fad20ec1635d46b","abstract_canon_sha256":"39673c0940d78869722606661d5e64bfbac5b2b0a39ab83fc3d7777d5864fdeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:31.749951Z","signature_b64":"eN+UI+jKh8iqRlMAlCi62lbKt1q0KIdZxpOQul6VyUwzhSiaCtuw0Uj1FDiQ0EyNd2rpHP/hYFngjIkwmWOiBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71808ff761c09f6c96025357bbe7f567f25c57e692cdc0de1bd426ddb1e03268","last_reissued_at":"2026-07-05T11:50:31.749335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:31.749335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rank1: Test-Time Compute for Reranking in Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Andrew Yates, Benjamin Van Durme, Dawn Lawrie, Eugene Yang, Kathryn Ricci, Orion Weller","submitted_at":"2025-02-25T18:14:06Z","abstract_excerpt":"We introduce Rank1, the first reranking model trained to take advantage of test-time compute. Rank1 demonstrates the applicability within retrieval of using a reasoning language model (i.e. OpenAI's o1, Deepseek's R1, etc.) for distillation in order to rapidly improve the performance of a smaller model. We gather and open-source a dataset of more than 600,000 examples of R1 reasoning traces from queries and passages in MS MARCO. Models trained on this dataset show: (1) state-of-the-art performance on advanced reasoning and instruction following datasets; (2) work remarkably well out of distrib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18418","kind":"arxiv","version":2},"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/2502.18418/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":"2502.18418","created_at":"2026-07-05T11:50:31.749405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18418v2","created_at":"2026-07-05T11:50:31.749405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18418","created_at":"2026-07-05T11:50:31.749405+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGAI753BYCPW","created_at":"2026-07-05T11:50:31.749405+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGAI753BYCPWZFQC","created_at":"2026-07-05T11:50:31.749405+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGAI753B","created_at":"2026-07-05T11:50:31.749405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01070","citing_title":"Test-Time Training for Zero-Resource Dense Retrieval Reranking","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22478","citing_title":"DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26352","citing_title":"RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20683","citing_title":"Layer-wise Token Compression for Efficient Document Reranking","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22478","citing_title":"DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20683","citing_title":"Layer-wise Token Compression for Efficient Document Reranking","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18767","citing_title":"DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03487","citing_title":"ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08819","citing_title":"Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13137","citing_title":"LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13137","citing_title":"LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27577","citing_title":"Reproducing Adaptive Reranking for Reasoning-Intensive IR","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04018","citing_title":"Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01399","citing_title":"Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00063","citing_title":"A Survey of Reasoning-Intensive Retrieval: Progress and Challenges","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11025","citing_title":"Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with Images","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07220","citing_title":"HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07079","citing_title":"MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00400","citing_title":"FollowTable: A Benchmark for Instruction-Following Table Retrieval","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7","json":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7.json","graph_json":"https://pith.science/api/pith-number/OGAI753BYCPWZFQCKNL3XZ7VM7/graph.json","events_json":"https://pith.science/api/pith-number/OGAI753BYCPWZFQCKNL3XZ7VM7/events.json","paper":"https://pith.science/paper/OGAI753B"},"agent_actions":{"view_html":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7","download_json":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7.json","view_paper":"https://pith.science/paper/OGAI753B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18418&json=true","fetch_graph":"https://pith.science/api/pith-number/OGAI753BYCPWZFQCKNL3XZ7VM7/graph.json","fetch_events":"https://pith.science/api/pith-number/OGAI753BYCPWZFQCKNL3XZ7VM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7/action/storage_attestation","attest_author":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7/action/author_attestation","sign_citation":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7/action/citation_signature","submit_replication":"https://pith.science/pith/OGAI753BYCPWZFQCKNL3XZ7VM7/action/replication_record"}},"created_at":"2026-07-05T11:50:31.749405+00:00","updated_at":"2026-07-05T11:50:31.749405+00:00"}