{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "muennighoff-enevoldsen-et-al-mteb-family-2022", "title": "MTEB/MMTEB: multi-task multilingual embedding evaluation and efficient subsets", "summary": "Unified evaluation across embedding task types and extended it through community-reviewed multilingual tasks, caching and document/task downsampling to reduce repeated evaluation work.", "boundary": "MTEB v1 and MMTEB v1 have different task inventories and evaluation pipelines; original MTEB classification uses the stated kNN protocol. MMTEB reduced sets preserve rankings empirically for studied models, not universally for future models. Managing-team and source authorship points are not WRS effort/scoring. Incidental medical-domain texts do not constitute a medical achievement.", "area": "Text embedding evaluation", "topic": "Artificial intelligence", "year": 2022, "lane": "HUMAN", "result": "BENCHMARK", "contribution_kind": "EVALUATION_RESOURCE_DESIGN", "package_id": "muennighoff-enevoldsen-et-al-mteb-family-2022", "target": { "record_id": "urn:uuid:d882107e-e844-49ab-ae77-371c6c44b226", "version": 1, "content_hash": "sha256:bb8c27a1a3c2b193a4fd4feec894fae113e29fba3a0e667ccaea3382d4f88bba" }, "humans": [ "Niklas Muennighoff", "Nouamane Tazi", "Loïc Magne", "Nils Reimers", "Kenneth Enevoldsen", "Isaac Chung", "Imene Kerboua", "Márton Kardos", "Ashwin Mathur", "David Stap", "Jay Gala", "Wissam Siblini", "Dominik Krzemiński", "Genta Indra Winata", "Saba Sturua", "Saiteja Utpala", "Mathieu Ciancone", "Marion Schaeffer", "Gabriel Sequeira", "Diganta Misra", "Shreeya Dhakal", "Jonathan Rystrøm", "Roman Solomatin", "Ömer Çağatan", "Akash Kundu", "Martin Bernstorff", "Shitao Xiao", "Akshita Sukhlecha", "Bhavish Pahwa", "Rafał Poświata", "Kranthi Kiran GV", "Shawon Ashraf", "Daniel Auras", "Björn Plüster", "Jan Philipp Harries", "Isabelle Mohr", "Mariya Hendriksen", "Dawei Zhu", "Hippolyte Gisserot-Boukhlef", "Tom Aarsen", "Jan Kostkan", "Konrad Wojtasik", "Taemin Lee", "Marek Šuppa", "Crystina Zhang", "Roberta Rocca", "Mohammed Hamdy", "Andrianos Michail", "John Yang", "Manuel Faysse", "Aleksei Vatolin", "Nandan Thakur", "Manan Dey", "Dipam Vasani", "Pranjal Chitale", "Simone Tedeschi", "Nguyen Tai", "Artem Snegirev", "Michael Günther", "Mengzhou Xia", "Weijia Shi", "Xing Han Lù", "Jordan Clive", "Gayatri Krishnakumar", "Anna Maksimova", "Silvan Wehrli", "Maria Tikhonova", "Henil Panchal", "Aleksandr Abramov", "Malte Ostendorff", "Zheng Liu", "Simon Clematide", "Lester James Miranda", "Alena Fenogenova", "Guangyu Song", "Ruqiya Bin Safi", "Wen-Ding Li", "Alessia Borghini", "Federico Cassano", "Hongjin Su", "Jimmy Lin", "Howard Yen", "Lasse Hansen", "Sara Hooker", "Chenghao Xiao", "Vaibhav Adlakha", "Orion Weller", "Siva Reddy" ], "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-2210-07316v1", "title": "MTEB: Massive Text Embedding Benchmark", "url": "https://arxiv.org/abs/2210.07316v1" }, { "id": "cur20261015-arxiv-2502-13595v1", "title": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } ], "points": "140000", "published_grade": { "id": "muennighoff-enevoldsen-et-al-mteb-family-2022", "entry_id": "muennighoff-enevoldsen-et-al-mteb-family-2022", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:d882107e-e844-49ab-ae77-371c6c44b226", "version": 1, "content_hash": "sha256:bb8c27a1a3c2b193a4fd4feec894fae113e29fba3a0e667ccaea3382d4f88bba" }, "what_changed": "Unified evaluation across embedding task types and extended it through community-reviewed multilingual tasks, caching and document/task downsampling to reduce repeated evaluation work.", "scope": "Unified evaluation across embedding task types and extended it through community-reviewed multilingual tasks, caching and document/task downsampling to reduce repeated evaluation work. MTEB v1 and MMTEB v1 have different task inventories and evaluation pipelines; original MTEB classification uses the stated kNN protocol. MMTEB reduced sets preserve rankings empirically for studied models, not universally for future models. Managing-team and source authorship points are not WRS effort/scoring. Incidental medical-domain texts do not constitute a medical achievement.", "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:d882107e-e844-49ab-ae77-371c6c44b226", "version": 1, "content_hash": "sha256:bb8c27a1a3c2b193a4fd4feec894fae113e29fba3a0e667ccaea3382d4f88bba" }, "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": "Niklas Muennighoff", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MTEB: Massive Text Embedding Benchmark", "url": "https://arxiv.org/abs/2210.07316v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Nouamane Tazi", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MTEB: Massive Text Embedding Benchmark", "url": "https://arxiv.org/abs/2210.07316v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Loïc Magne", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MTEB: Massive Text Embedding Benchmark", "url": "https://arxiv.org/abs/2210.07316v1" } }, { "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": "MTEB: Massive Text Embedding Benchmark", "url": "https://arxiv.org/abs/2210.07316v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kenneth Enevoldsen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Isaac Chung", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Imene Kerboua", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Márton Kardos", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ashwin Mathur", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "David Stap", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jay Gala", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Wissam Siblini", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dominik Krzemiński", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Genta Indra Winata", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Saba Sturua", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Saiteja Utpala", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Mathieu Ciancone", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Marion Schaeffer", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Gabriel Sequeira", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Diganta Misra", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Shreeya Dhakal", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jonathan Rystrøm", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Roman Solomatin", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ömer Çağatan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Akash Kundu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Martin Bernstorff", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Shitao Xiao", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Akshita Sukhlecha", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Bhavish Pahwa", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Rafał Poświata", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kranthi Kiran GV", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "MTEB: Massive Text Embedding Benchmark", "url": "https://arxiv.org/abs/2210.07316v1" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "MTEB v1 and MMTEB v1 have different task inventories and evaluation pipelines; original MTEB classification uses the stated kNN protocol. MMTEB reduced sets preserve rankings empirically for studied models, not universally for future models. Managing-team and source authorship points are not WRS effort/scoring. Incidental medical-domain texts do not constitute a medical achievement.", "domain": "Text embedding evaluation" }, "sources": [ { "citation": "MTEB: Massive Text Embedding Benchmark", "url": "https://arxiv.org/abs/2210.07316v1" }, { "citation": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1" } ], "statement": "# MTEB/MMTEB: multi-task multilingual embedding evaluation and efficient subsets\n\nUnified evaluation across embedding task types and extended it through community-reviewed multilingual tasks, caching and document/task downsampling to reduce repeated evaluation work.\n\n## Scientific scope\n\nMTEB v1 and MMTEB v1 have different task inventories and evaluation pipelines; original MTEB classification uses the stated kNN protocol. MMTEB reduced sets preserve rankings empirically for studied models, not universally for future models. Managing-team and source authorship points are not WRS effort/scoring. Incidental medical-domain texts do not constitute a medical achievement.\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\nNiklas Muennighoff; Nouamane Tazi; Loïc Magne; Nils Reimers; Kenneth Enevoldsen; Isaac Chung; Imene Kerboua; Márton Kardos; Ashwin Mathur; David Stap; Jay Gala; Wissam Siblini; Dominik Krzemiński; Genta Indra Winata; Saba Sturua; Saiteja Utpala; Mathieu Ciancone; Marion Schaeffer; Gabriel Sequeira; Diganta Misra; Shreeya Dhakal; Jonathan Rystrøm; Roman Solomatin; Ömer Çağatan; Akash Kundu; Martin Bernstorff; Shitao Xiao; Akshita Sukhlecha; Bhavish Pahwa; Rafał Poświata; Kranthi Kiran GV; Shawon Ashraf; Daniel Auras; Björn Plüster; Jan Philipp Harries; Isabelle Mohr; Mariya Hendriksen; Dawei Zhu; Hippolyte Gisserot-Boukhlef; Tom Aarsen; Jan Kostkan; Konrad Wojtasik; Taemin Lee; Marek Šuppa; Crystina Zhang; Roberta Rocca; Mohammed Hamdy; Andrianos Michail; John Yang; Manuel Faysse; Aleksei Vatolin; Nandan Thakur; Manan Dey; Dipam Vasani; Pranjal Chitale; Simone Tedeschi; Nguyen Tai; Artem Snegirev; Michael Günther; Mengzhou Xia; Weijia Shi; Xing Han Lù; Jordan Clive; Gayatri Krishnakumar; Anna Maksimova; Silvan Wehrli; Maria Tikhonova; Henil Panchal; Aleksandr Abramov; Malte Ostendorff; Zheng Liu; Simon Clematide; Lester James Miranda; Alena Fenogenova; Guangyu Song; Ruqiya Bin Safi; Wen-Ding Li; Alessia Borghini; Federico Cassano; Hongjin Su; Jimmy Lin; Howard Yen; Lasse Hansen; Sara Hooker; Chenghao Xiao; Vaibhav Adlakha; Orion Weller; Siva Reddy\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- [MTEB: Massive Text Embedding Benchmark](https://arxiv.org/abs/2210.07316v1)\n- [MMTEB: Massive Multilingual Text Embedding Benchmark](https://arxiv.org/abs/2502.13595v1)\n", "summary": "Unified evaluation across embedding task types and extended it through community-reviewed multilingual tasks, caching and document/task downsampling to reduce repeated evaluation work.", "title": "MTEB/MMTEB: multi-task multilingual embedding evaluation and efficient subsets" }, "record_id": "urn:uuid:d882107e-e844-49ab-ae77-371c6c44b226", "version": 1, "source_ref": { "record_id": "urn:uuid:d882107e-e844-49ab-ae77-371c6c44b226", "version": 1, "content_hash": "sha256:bb8c27a1a3c2b193a4fd4feec894fae113e29fba3a0e667ccaea3382d4f88bba" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:8c387c4f02e021261cfc60a89b72cc0dbd085aff13cc05cd92081c083bb3b73e" }, "target": { "record_id": "urn:uuid:d882107e-e844-49ab-ae77-371c6c44b226", "version": 1, "content_hash": "sha256:bb8c27a1a3c2b193a4fd4feec894fae113e29fba3a0e667ccaea3382d4f88bba" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "muennighoff-enevoldsen-et-al-mteb-family-2022", "entry_id": "muennighoff-enevoldsen-et-al-mteb-family-2022", "revision": 1, "title": "MTEB/MMTEB: multi-task multilingual embedding evaluation and efficient subsets", "context": "Text embedding 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": "Unified evaluation across embedding task types and extended it through community-reviewed multilingual tasks, caching and document/task downsampling to reduce repeated evaluation work.", "scope": "Unified evaluation across embedding task types and extended it through community-reviewed multilingual tasks, caching and document/task downsampling to reduce repeated evaluation work. MTEB v1 and MMTEB v1 have different task inventories and evaluation pipelines; original MTEB classification uses the stated kNN protocol. MMTEB reduced sets preserve rankings empirically for studied models, not universally for future models. Managing-team and source authorship points are not WRS effort/scoring. Incidental medical-domain texts do not constitute a medical achievement.", "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. MTEB v1 and MMTEB v1 have different task inventories and evaluation pipelines; original MTEB classification uses the stated kNN protocol. MMTEB reduced sets preserve rankings empirically for studied models, not universally for future models. Managing-team and source authorship points are not WRS effort/scoring. Incidental medical-domain texts do not constitute a medical achievement.", "references": [ { "title": "MTEB: Massive Text Embedding Benchmark", "url": "https://arxiv.org/abs/2210.07316v1", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." }, { "title": "MMTEB: Massive Multilingual Text Embedding Benchmark", "url": "https://arxiv.org/abs/2502.13595v1", "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:d882107e-e844-49ab-ae77-371c6c44b226", "version": 1, "content_hash": "sha256:bb8c27a1a3c2b193a4fd4feec894fae113e29fba3a0e667ccaea3382d4f88bba" }, "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" }