{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K4TXAHQZV35BL3VVAS5ZTP7Y3C","short_pith_number":"pith:K4TXAHQZ","schema_version":"1.0","canonical_sha256":"5727701e19aefa15eeb504bb99bff8d892c4403af89ed417520ed30d5a7cbacf","source":{"kind":"arxiv","id":"2402.14151","version":2},"attestation_state":"computed","paper":{"title":"BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Jianyou Wang, Kaicheng Wang, Leon Bergen, Ramamohan Paturi, Weili Cao, Xiaoyue Wang","submitted_at":"2024-02-21T22:22:30Z","abstract_excerpt":"We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO). BIRCO evaluates the ability of IR systems to retrieve documents given multi-faceted user objectives. The benchmark's complexity and compact size make it suitable for evaluating large language model (LLM)-based information retrieval systems. We present a modular framework for investigating factors that may influence LLM performance on retrieval tasks, and identify a simple baseline model which matches or outperforms existing approaches and more complex alternatives. No approach achieves satisfactory pe"},"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":"2402.14151","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-21T22:22:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"070b21d0ff9c002864334fccf68f97e33b2040bb3b6bca9f39f705035577dd24","abstract_canon_sha256":"690afd834db0c38d1c4cfb2c3e7e500f277ce89f382bdb6fe0cddb94d54dc497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:18.193213Z","signature_b64":"tiB5SR+q7GOIi1o9i2W9jdgnPrw5oJfz/mBbRGbpxIaSqDHFXlrP87SQa3jQp83q2YcKkfkdWEyQQrQ3MvFaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5727701e19aefa15eeb504bb99bff8d892c4403af89ed417520ed30d5a7cbacf","last_reissued_at":"2026-07-05T08:04:18.192738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:18.192738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BIRCO: A Benchmark of Information Retrieval Tasks with Complex Objectives","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Jianyou Wang, Kaicheng Wang, Leon Bergen, Ramamohan Paturi, Weili Cao, Xiaoyue Wang","submitted_at":"2024-02-21T22:22:30Z","abstract_excerpt":"We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO). BIRCO evaluates the ability of IR systems to retrieve documents given multi-faceted user objectives. The benchmark's complexity and compact size make it suitable for evaluating large language model (LLM)-based information retrieval systems. We present a modular framework for investigating factors that may influence LLM performance on retrieval tasks, and identify a simple baseline model which matches or outperforms existing approaches and more complex alternatives. No approach achieves satisfactory pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14151","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/2402.14151/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":"2402.14151","created_at":"2026-07-05T08:04:18.192784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14151v2","created_at":"2026-07-05T08:04:18.192784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14151","created_at":"2026-07-05T08:04:18.192784+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4TXAHQZV35B","created_at":"2026-07-05T08:04:18.192784+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4TXAHQZV35BL3VV","created_at":"2026-07-05T08:04:18.192784+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4TXAHQZ","created_at":"2026-07-05T08:04:18.192784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06641","citing_title":"Healthier LLMs: Retrieval-Augmented Generation for Public Health Question Answering","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":137,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C","json":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C.json","graph_json":"https://pith.science/api/pith-number/K4TXAHQZV35BL3VVAS5ZTP7Y3C/graph.json","events_json":"https://pith.science/api/pith-number/K4TXAHQZV35BL3VVAS5ZTP7Y3C/events.json","paper":"https://pith.science/paper/K4TXAHQZ"},"agent_actions":{"view_html":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C","download_json":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C.json","view_paper":"https://pith.science/paper/K4TXAHQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14151&json=true","fetch_graph":"https://pith.science/api/pith-number/K4TXAHQZV35BL3VVAS5ZTP7Y3C/graph.json","fetch_events":"https://pith.science/api/pith-number/K4TXAHQZV35BL3VVAS5ZTP7Y3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C/action/storage_attestation","attest_author":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C/action/author_attestation","sign_citation":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C/action/citation_signature","submit_replication":"https://pith.science/pith/K4TXAHQZV35BL3VVAS5ZTP7Y3C/action/replication_record"}},"created_at":"2026-07-05T08:04:18.192784+00:00","updated_at":"2026-07-05T08:04:18.192784+00:00"}