{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D4QAPYCOOEAL63FKVFO5C6G6KF","short_pith_number":"pith:D4QAPYCO","schema_version":"1.0","canonical_sha256":"1f2007e04e7100bf6caaa95dd178de5157f7a4261f0a0f1ca75e51da0f3c7fec","source":{"kind":"arxiv","id":"2407.12883","version":4},"attestation_state":"computed","paper":{"title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Danqi Chen, Haisu Liu, Han-yu Wang, Hongjin Su, Howard Yen, Jinsung Yoon, Mengzhou Xia, Michael Tang, Niklas Muennighoff, Quan Shi, Ruoxi Sun, Sercan O. Arik, Tao Yu, Weijia Shi, Zachary S. Siegel","submitted_at":"2024-07-16T17:58:27Z","abstract_excerpt":"Existing retrieval benchmarks primarily consist of information-seeking queries (e.g., aggregated questions from search engines) where keyword or semantic-based retrieval is usually sufficient. However, many complex real-world queries require in-depth reasoning to identify relevant documents that go beyond surface form matching. For example, finding documentation for a coding question requires understanding the logic and syntax of the functions involved. To better benchmark retrieval on such challenging queries, we introduce BRIGHT, the first text retrieval benchmark that requires intensive rea"},"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":"2407.12883","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-16T17:58:27Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"c0e2ebd8cd2c808aa06024954e84cb39b77dbd7b7c5177583d89e6ba3ffac78f","abstract_canon_sha256":"45d9c8bcfff46977828c2f75352d93ffadd511a88759cf5c91479a546f39cb3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:19.988159Z","signature_b64":"g+dLSqBow0LQHbD00S3m2zrXbK2U49E1u07sbkO8iVD6h/7soLfH2m6NyG4pPJ5DY7NuJc95PJFWU61HGCscCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f2007e04e7100bf6caaa95dd178de5157f7a4261f0a0f1ca75e51da0f3c7fec","last_reissued_at":"2026-07-05T10:39:19.987746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:19.987746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Danqi Chen, Haisu Liu, Han-yu Wang, Hongjin Su, Howard Yen, Jinsung Yoon, Mengzhou Xia, Michael Tang, Niklas Muennighoff, Quan Shi, Ruoxi Sun, Sercan O. Arik, Tao Yu, Weijia Shi, Zachary S. Siegel","submitted_at":"2024-07-16T17:58:27Z","abstract_excerpt":"Existing retrieval benchmarks primarily consist of information-seeking queries (e.g., aggregated questions from search engines) where keyword or semantic-based retrieval is usually sufficient. However, many complex real-world queries require in-depth reasoning to identify relevant documents that go beyond surface form matching. For example, finding documentation for a coding question requires understanding the logic and syntax of the functions involved. To better benchmark retrieval on such challenging queries, we introduce BRIGHT, the first text retrieval benchmark that requires intensive rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12883","kind":"arxiv","version":4},"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/2407.12883/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":"2407.12883","created_at":"2026-07-05T10:39:19.987804+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12883v4","created_at":"2026-07-05T10:39:19.987804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12883","created_at":"2026-07-05T10:39:19.987804+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4QAPYCOOEAL","created_at":"2026-07-05T10:39:19.987804+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4QAPYCOOEAL63FK","created_at":"2026-07-05T10:39:19.987804+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4QAPYCO","created_at":"2026-07-05T10:39:19.987804+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18520","citing_title":"Compact Geometric Representations of Hierarchies","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28365","citing_title":"CAMI: Cost-Aware Agent-Guided Multi-Indexing for Semantic Retrieval","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26352","citing_title":"RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29507","citing_title":"Xetrieval: Mechanistically Explaining Dense Retrieval","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14558","citing_title":"R2MED: A Benchmark for Reasoning-Driven Medical Retrieval","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11653","citing_title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22591","citing_title":"Where Relevance Emerges: A Layer-Wise Study of Internal Attention for Zero-Shot Re-Ranking","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13137","citing_title":"LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13137","citing_title":"LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03676","citing_title":"Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":300,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05538","citing_title":"AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases","ref_index":9,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07201","citing_title":"BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07079","citing_title":"MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20144","citing_title":"An Agentic Approach to Metadata Reasoning","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF","json":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF.json","graph_json":"https://pith.science/api/pith-number/D4QAPYCOOEAL63FKVFO5C6G6KF/graph.json","events_json":"https://pith.science/api/pith-number/D4QAPYCOOEAL63FKVFO5C6G6KF/events.json","paper":"https://pith.science/paper/D4QAPYCO"},"agent_actions":{"view_html":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF","download_json":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF.json","view_paper":"https://pith.science/paper/D4QAPYCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12883&json=true","fetch_graph":"https://pith.science/api/pith-number/D4QAPYCOOEAL63FKVFO5C6G6KF/graph.json","fetch_events":"https://pith.science/api/pith-number/D4QAPYCOOEAL63FKVFO5C6G6KF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF/action/storage_attestation","attest_author":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF/action/author_attestation","sign_citation":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF/action/citation_signature","submit_replication":"https://pith.science/pith/D4QAPYCOOEAL63FKVFO5C6G6KF/action/replication_record"}},"created_at":"2026-07-05T10:39:19.987804+00:00","updated_at":"2026-07-05T10:39:19.987804+00:00"}