{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "thakur-et-al-beir-2021", "title": "BEIR: heterogeneous zero-shot retrieval evaluation", "summary": "Standardized cross-domain retrieval evaluation over diverse query/document forms, relevance labels and tasks, comparing lexical, dense and reranking approaches beyond their training domains.", "boundary": "Original v1 has17evaluation datasets and reports MS-MARCO separately, excluding it from the zero-shot comparison; later dataset counts are not substituted. General benchmark/protocol contribution only: included biomedical corpora do not become biological or medical achievements. Dataset selection and source-reported scores are not a guarantee of all-domain robustness.", "area": "Information retrieval evaluation", "topic": "Artificial intelligence", "year": 2021, "lane": "HUMAN", "result": "BENCHMARK", "contribution_kind": "EVALUATION_RESOURCE_DESIGN", "package_id": "thakur-et-al-beir-2021", "target": { "record_id": "urn:uuid:808a7894-3f6c-4158-a969-e75dd381fce7", "version": 1, "content_hash": "sha256:c61d20c0f433b567719d2929f7c9f5eb26f723965e17818b9725676cbd544471" }, "humans": [ "Nandan Thakur", "Nils Reimers", "Andreas Rücklé", "Abhishek Srivastava", "Iryna Gurevych" ], "authors_complete": true, "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "cur20261015-arxiv-2104-08663v1", "title": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1" } ], "points": "140000", "published_grade": { "id": "thakur-et-al-beir-2021", "entry_id": "thakur-et-al-beir-2021", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:808a7894-3f6c-4158-a969-e75dd381fce7", "version": 1, "content_hash": "sha256:c61d20c0f433b567719d2929f7c9f5eb26f723965e17818b9725676cbd544471" }, "what_changed": "Standardized cross-domain retrieval evaluation over diverse query/document forms, relevance labels and tasks, comparing lexical, dense and reranking approaches beyond their training domains.", "scope": "Standardized cross-domain retrieval evaluation over diverse query/document forms, relevance labels and tasks, comparing lexical, dense and reranking approaches beyond their training domains. Original v1 has17evaluation datasets and reports MS-MARCO separately, excluding it from the zero-shot comparison; later dataset counts are not substituted. General benchmark/protocol contribution only: included biomedical corpora do not become biological or medical achievements. Dataset selection and source-reported scores are not a guarantee of all-domain robustness.", "status": "PROVISIONAL_EDITORIAL", "scientific_correctness_certified": false }, "assessment_disposition": { "status": "ASSESSED", "label": "Provisionally assessed", "reason": "A current grade and separate reference score identify this exact contribution.", "target": { "record_id": "urn:uuid:808a7894-3f6c-4158-a969-e75dd381fce7", "version": 1, "content_hash": "sha256:c61d20c0f433b567719d2929f7c9f5eb26f723965e17818b9725676cbd544471" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-10-16T00:00:00Z", "publisher": { "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33", "role": "WRS_EDITORIAL_PUBLICATION" }, "record": { "contributors": [ { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Nandan Thakur", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Nils Reimers", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Andreas Rücklé", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Abhishek Srivastava", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Iryna Gurevych", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Original v1 has17evaluation datasets and reports MS-MARCO separately, excluding it from the zero-shot comparison; later dataset counts are not substituted. General benchmark/protocol contribution only: included biomedical corpora do not become biological or medical achievements. Dataset selection and source-reported scores are not a guarantee of all-domain robustness.", "domain": "Information retrieval evaluation" }, "sources": [ { "citation": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1" } ], "statement": "# BEIR: heterogeneous zero-shot retrieval evaluation\n\nStandardized cross-domain retrieval evaluation over diverse query/document forms, relevance labels and tasks, comparing lexical, dense and reranking approaches beyond their training domains.\n\n## Scientific scope\n\nOriginal v1 has17evaluation datasets and reports MS-MARCO separately, excluding it from the zero-shot comparison; later dataset counts are not substituted. General benchmark/protocol contribution only: included biomedical corpora do not become biological or medical achievements. Dataset selection and source-reported scores are not a guarantee of all-domain robustness.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nNandan Thakur; Nils Reimers; Andreas Rücklé; Abhishek Srivastava; Iryna Gurevych\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://arxiv.org/abs/2104.08663v1)\n", "summary": "Standardized cross-domain retrieval evaluation over diverse query/document forms, relevance labels and tasks, comparing lexical, dense and reranking approaches beyond their training domains.", "title": "BEIR: heterogeneous zero-shot retrieval evaluation" }, "record_id": "urn:uuid:808a7894-3f6c-4158-a969-e75dd381fce7", "version": 1, "source_ref": { "record_id": "urn:uuid:808a7894-3f6c-4158-a969-e75dd381fce7", "version": 1, "content_hash": "sha256:c61d20c0f433b567719d2929f7c9f5eb26f723965e17818b9725676cbd544471" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:6f54bf3f06a408168c42770a65b43fcad1c498ccc62b9fe62742893e55e5a5a4" }, "target": { "record_id": "urn:uuid:808a7894-3f6c-4158-a969-e75dd381fce7", "version": 1, "content_hash": "sha256:c61d20c0f433b567719d2929f7c9f5eb26f723965e17818b9725676cbd544471" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "thakur-et-al-beir-2021", "entry_id": "thakur-et-al-beir-2021", "revision": 1, "title": "BEIR: heterogeneous zero-shot retrieval evaluation", "context": "Information retrieval evaluation", "track": "Evaluation resource design", "band": "A", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Standardized cross-domain retrieval evaluation over diverse query/document forms, relevance labels and tasks, comparing lexical, dense and reranking approaches beyond their training domains.", "scope": "Standardized cross-domain retrieval evaluation over diverse query/document forms, relevance labels and tasks, comparing lexical, dense and reranking approaches beyond their training domains. Original v1 has17evaluation datasets and reports MS-MARCO separately, excluding it from the zero-shot comparison; later dataset counts are not substituted. General benchmark/protocol contribution only: included biomedical corpora do not become biological or medical achievements. Dataset selection and source-reported scores are not a guarantee of all-domain robustness.", "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original v1 has17evaluation datasets and reports MS-MARCO separately, excluding it from the zero-shot comparison; later dataset counts are not substituted. General benchmark/protocol contribution only: included biomedical corpora do not become biological or medical achievements. Dataset selection and source-reported scores are not a guarantee of all-domain robustness.", "references": [ { "title": "BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models", "url": "https://arxiv.org/abs/2104.08663v1", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." } ], "roles": [ { "who": "Source-listed authors and technical contributors", "credit": "SCIENCE", "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities." } ], "target": { "record_id": "urn:uuid:808a7894-3f6c-4158-a969-e75dd381fce7", "version": 1, "content_hash": "sha256:c61d20c0f433b567719d2929f7c9f5eb26f723965e17818b9725676cbd544471" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "140000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }