{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LD73EV73SNEXEOR6QKEWVA47DC","short_pith_number":"pith:LD73EV73","schema_version":"1.0","canonical_sha256":"58ffb257fb9349723a3e82896a839f18a4ce5e3dc24cb4c697a3bd507679495f","source":{"kind":"arxiv","id":"2503.04644","version":1},"attestation_state":"computed","paper":{"title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Guo Gan, Mingsheng Shang, Tingyu Song, Yilun Zhao","submitted_at":"2025-03-06T17:32:22Z","abstract_excerpt":"We introduce IFIR, the first comprehensive benchmark designed to evaluate instruction-following information retrieval (IR) in expert domains. IFIR includes 2,426 high-quality examples and covers eight subsets across four specialized domains: finance, law, healthcare, and science literature. Each subset addresses one or more domain-specific retrieval tasks, replicating real-world scenarios where customized instructions are critical. IFIR enables a detailed analysis of instruction-following retrieval capabilities by incorporating instructions at different levels of complexity. We also propose a "},"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":"2503.04644","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T17:32:22Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"56e1a18a53cd8b946c2739b48399b7e5d3d6bfbf764b52bf065fdc2993c10521","abstract_canon_sha256":"c78c943e7041133bf002a7a0bed4a73417c370c955dd424e1205b94accdbe183"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:44.090890Z","signature_b64":"j0G2sZ9oJ63ErsRRNjUZZGj0csO9i9CTpVQAss+jcDswQqhyDQdGwNKSwWfaC1+WWeuR3ohsw2VN402XemOJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ffb257fb9349723a3e82896a839f18a4ce5e3dc24cb4c697a3bd507679495f","last_reissued_at":"2026-07-05T10:25:44.090376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:44.090376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Guo Gan, Mingsheng Shang, Tingyu Song, Yilun Zhao","submitted_at":"2025-03-06T17:32:22Z","abstract_excerpt":"We introduce IFIR, the first comprehensive benchmark designed to evaluate instruction-following information retrieval (IR) in expert domains. IFIR includes 2,426 high-quality examples and covers eight subsets across four specialized domains: finance, law, healthcare, and science literature. Each subset addresses one or more domain-specific retrieval tasks, replicating real-world scenarios where customized instructions are critical. IFIR enables a detailed analysis of instruction-following retrieval capabilities by incorporating instructions at different levels of complexity. We also propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04644","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/2503.04644/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":"2503.04644","created_at":"2026-07-05T10:25:44.090437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04644v1","created_at":"2026-07-05T10:25:44.090437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04644","created_at":"2026-07-05T10:25:44.090437+00:00"},{"alias_kind":"pith_short_12","alias_value":"LD73EV73SNEX","created_at":"2026-07-05T10:25:44.090437+00:00"},{"alias_kind":"pith_short_16","alias_value":"LD73EV73SNEXEOR6","created_at":"2026-07-05T10:25:44.090437+00:00"},{"alias_kind":"pith_short_8","alias_value":"LD73EV73","created_at":"2026-07-05T10:25:44.090437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15045","citing_title":"Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC","json":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC.json","graph_json":"https://pith.science/api/pith-number/LD73EV73SNEXEOR6QKEWVA47DC/graph.json","events_json":"https://pith.science/api/pith-number/LD73EV73SNEXEOR6QKEWVA47DC/events.json","paper":"https://pith.science/paper/LD73EV73"},"agent_actions":{"view_html":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC","download_json":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC.json","view_paper":"https://pith.science/paper/LD73EV73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04644&json=true","fetch_graph":"https://pith.science/api/pith-number/LD73EV73SNEXEOR6QKEWVA47DC/graph.json","fetch_events":"https://pith.science/api/pith-number/LD73EV73SNEXEOR6QKEWVA47DC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC/action/storage_attestation","attest_author":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC/action/author_attestation","sign_citation":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC/action/citation_signature","submit_replication":"https://pith.science/pith/LD73EV73SNEXEOR6QKEWVA47DC/action/replication_record"}},"created_at":"2026-07-05T10:25:44.090437+00:00","updated_at":"2026-07-05T10:25:44.090437+00:00"}