{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "groeneveld-et-al-olmo-research-framework-2024", "title": "Groeneveld et al.: OLMo open language-model research framework", "summary": "Released language-model weights together with training data, training/evaluation code and intermediate research artifacts to enable inspectable studies of model development.", "boundary": "An open research infrastructure/resource contribution, not proof of general model superiority or that every dataset component is free of licensing, bias or contamination concerns. Separate Dolma corpus design may have its own contribution, but no duplicate data count is implicit here.", "area": "Language-model training and open research resources", "topic": "Artificial intelligence", "year": 2024, "lane": "HUMAN", "result": "EMPIRICAL", "package_id": "groeneveld-et-al-olmo-research-framework-2024", "target": { "record_id": "urn:uuid:e8a10812-12b5-4496-a8dd-bbc35b8ceaae", "version": 1, "content_hash": "sha256:2abc9f254458dca4d138a04d629e2db4991b974065eb19ddd3dcefeb9c8a8d64" }, "humans": [ "Dirk Groeneveld", "Iz Beltagy", "Pete Walsh", "Akshita Bhagia", "Rodney Kinney", "Oyvind Tafjord", "Ananya Harsh Jha", "Hamish Ivison", "Ian Magnusson", "Yizhong Wang", "Shane Arora", "David Atkinson", "Russell Authur", "Khyathi Raghavi Chandu", "Arman Cohan", "Jennifer Dumas", "Yanai Elazar", "Yuling Gu", "Jack Hessel", "Tushar Khot", "William Merrill", "Jacob Morrison", "Niklas Muennighoff", "Aakanksha Naik", "Crystal Nam", "Matthew E. Peters", "Valentina Pyatkin", "Abhilasha Ravichander", "Dustin Schwenk", "Saurabh Shah", "Will Smith", "Emma Strubell", "Nishant Subramani", "Mitchell Wortsman", "Pradeep Dasigi", "Nathan Lambert", "Kyle Richardson", "Luke Zettlemoyer", "Jesse Dodge", "Kyle Lo", "Luca Soldaini", "Noah A. Smith", "Hannaneh Hajishirzi" ], "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-2402-00838v1", "title": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" }, { "id": "cur20261015-support-groeneveld-et-al-olmo-research-framework-2024", "title": "Groeneveld et al.: OLMo open language-model research framework — author/company record", "url": "https://allenai.org/blog/olmo-open-language-model-87ccfc95f580" } ], "points": "145000", "published_grade": { "id": "groeneveld-et-al-olmo-research-framework-2024", "entry_id": "groeneveld-et-al-olmo-research-framework-2024", "band": "A", "modifier": null, "target": { "record_id": "urn:uuid:e8a10812-12b5-4496-a8dd-bbc35b8ceaae", "version": 1, "content_hash": "sha256:2abc9f254458dca4d138a04d629e2db4991b974065eb19ddd3dcefeb9c8a8d64" }, "what_changed": "Released language-model weights together with training data, training/evaluation code and intermediate research artifacts to enable inspectable studies of model development.", "scope": "Released language-model weights together with training data, training/evaluation code and intermediate research artifacts to enable inspectable studies of model development. An open research infrastructure/resource contribution, not proof of general model superiority or that every dataset component is free of licensing, bias or contamination concerns. Separate Dolma corpus design may have its own contribution, but no duplicate data count is implicit here.", "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:e8a10812-12b5-4496-a8dd-bbc35b8ceaae", "version": 1, "content_hash": "sha256:2abc9f254458dca4d138a04d629e2db4991b974065eb19ddd3dcefeb9c8a8d64" }, "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": "Dirk Groeneveld", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Iz Beltagy", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Pete Walsh", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Akshita Bhagia", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Rodney Kinney", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Oyvind Tafjord", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ananya Harsh Jha", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Hamish Ivison", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ian Magnusson", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yizhong Wang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Shane Arora", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "David Atkinson", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Russell Authur", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Khyathi Raghavi Chandu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Arman Cohan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jennifer Dumas", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yanai Elazar", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yuling Gu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jack Hessel", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Tushar Khot", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "William Merrill", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jacob Morrison", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Niklas Muennighoff", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Aakanksha Naik", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Crystal Nam", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Matthew E. Peters", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Valentina Pyatkin", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Abhilasha Ravichander", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dustin Schwenk", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Saurabh Shah", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Will Smith", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "Groeneveld et al.: OLMo open language-model research framework — author/company record", "url": "https://allenai.org/blog/olmo-open-language-model-87ccfc95f580" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "An open research infrastructure/resource contribution, not proof of general model superiority or that every dataset component is free of licensing, bias or contamination concerns. Separate Dolma corpus design may have its own contribution, but no duplicate data count is implicit here.", "domain": "Language-model training and open research resources" }, "sources": [ { "citation": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1" }, { "citation": "Groeneveld et al.: OLMo open language-model research framework — author/company record", "url": "https://allenai.org/blog/olmo-open-language-model-87ccfc95f580" } ], "statement": "# Groeneveld et al.: OLMo open language-model research framework\n\nReleased language-model weights together with training data, training/evaluation code and intermediate research artifacts to enable inspectable studies of model development.\n\n## Scientific scope\n\nAn open research infrastructure/resource contribution, not proof of general model superiority or that every dataset component is free of licensing, bias or contamination concerns. Separate Dolma corpus design may have its own contribution, but no duplicate data count is implicit here.\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\nDirk Groeneveld; Iz Beltagy; Pete Walsh; Akshita Bhagia; Rodney Kinney; Oyvind Tafjord; Ananya Harsh Jha; Hamish Ivison; Ian Magnusson; Yizhong Wang; Shane Arora; David Atkinson; Russell Authur; Khyathi Raghavi Chandu; Arman Cohan; Jennifer Dumas; Yanai Elazar; Yuling Gu; Jack Hessel; Tushar Khot; William Merrill; Jacob Morrison; Niklas Muennighoff; Aakanksha Naik; Crystal Nam; Matthew E. Peters; Valentina Pyatkin; Abhilasha Ravichander; Dustin Schwenk; Saurabh Shah; Will Smith; Emma Strubell; Nishant Subramani; Mitchell Wortsman; Pradeep Dasigi; Nathan Lambert; Kyle Richardson; Luke Zettlemoyer; Jesse Dodge; Kyle Lo; Luca Soldaini; Noah A. Smith; Hannaneh Hajishirzi\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- [OLMo: Accelerating the Science of Language Models](https://arxiv.org/abs/2402.00838v1)\n- [Groeneveld et al.: OLMo open language-model research framework — author/company record](https://allenai.org/blog/olmo-open-language-model-87ccfc95f580)\n", "summary": "Released language-model weights together with training data, training/evaluation code and intermediate research artifacts to enable inspectable studies of model development.", "title": "Groeneveld et al.: OLMo open language-model research framework" }, "record_id": "urn:uuid:e8a10812-12b5-4496-a8dd-bbc35b8ceaae", "version": 1, "source_ref": { "record_id": "urn:uuid:e8a10812-12b5-4496-a8dd-bbc35b8ceaae", "version": 1, "content_hash": "sha256:2abc9f254458dca4d138a04d629e2db4991b974065eb19ddd3dcefeb9c8a8d64" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:4a48f01ac19ecee599eb201a7e7ad8495b8ede2ab82ffd44e89a200560d4a550" }, "target": { "record_id": "urn:uuid:e8a10812-12b5-4496-a8dd-bbc35b8ceaae", "version": 1, "content_hash": "sha256:2abc9f254458dca4d138a04d629e2db4991b974065eb19ddd3dcefeb9c8a8d64" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "groeneveld-et-al-olmo-research-framework-2024", "entry_id": "groeneveld-et-al-olmo-research-framework-2024", "revision": 1, "title": "Groeneveld et al.: OLMo open language-model research framework", "context": "Language-model training and open research resources", "track": "Human-designed research method or resource", "band": "A", "modifier": null, "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Released language-model weights together with training data, training/evaluation code and intermediate research artifacts to enable inspectable studies of model development.", "scope": "Released language-model weights together with training data, training/evaluation code and intermediate research artifacts to enable inspectable studies of model development. An open research infrastructure/resource contribution, not proof of general model superiority or that every dataset component is free of licensing, bias or contamination concerns. Separate Dolma corpus design may have its own contribution, but no duplicate data count is implicit here.", "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. An open research infrastructure/resource contribution, not proof of general model superiority or that every dataset component is free of licensing, bias or contamination concerns. Separate Dolma corpus design may have its own contribution, but no duplicate data count is implicit here.", "references": [ { "title": "OLMo: Accelerating the Science of Language Models", "url": "https://arxiv.org/abs/2402.00838v1", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." }, { "title": "Groeneveld et al.: OLMo open language-model research framework — author/company record", "url": "https://allenai.org/blog/olmo-open-language-model-87ccfc95f580", "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:e8a10812-12b5-4496-a8dd-bbc35b8ceaae", "version": 1, "content_hash": "sha256:2abc9f254458dca4d138a04d629e2db4991b974065eb19ddd3dcefeb9c8a8d64" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "145000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }