{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "soldaini-et-al-dolma-corpus-curation-2023", "title": "Soldaini et al.: Dolma open pretraining corpus and curation toolkit", "summary": "Released a documented multi-source pretraining corpus and reproducible curation toolkit, with analyses of filtering, deduplication and source mixing for language-model research.", "boundary": "Initial corpus release was August 2023; the January 2024 paper documents later corpus/toolkit versions and analyses. Distinct from OLMo's model framework; not a claim of bias-free, contamination-free or universally licensed data.", "area": "Language-model data curation and research resources", "topic": "Artificial intelligence", "year": 2023, "lane": "HUMAN", "result": "EMPIRICAL", "package_id": "soldaini-et-al-dolma-corpus-curation-2023", "target": { "record_id": "urn:uuid:97087e66-6df3-4cf8-ac89-137de38a6609", "version": 1, "content_hash": "sha256:09cda274f889de28d09ed2afd47b7d9a5c49ade1070b366f2d8e5663ef9199cf" }, "humans": [ "Luca Soldaini", "Rodney Kinney", "Akshita Bhagia", "Dustin Schwenk", "David Atkinson", "Russell Authur", "Ben Bogin", "Khyathi Chandu", "Jennifer Dumas", "Yanai Elazar", "Valentin Hofmann", "Ananya Harsh Jha", "Sachin Kumar", "Li Lucy", "Xinxi Lyu", "Nathan Lambert", "Ian Magnusson", "Jacob Morrison", "Niklas Muennighoff", "Aakanksha Naik", "Crystal Nam", "Matthew E. Peters", "Abhilasha Ravichander", "Kyle Richardson", "Zejiang Shen", "Emma Strubell", "Nishant Subramani", "Oyvind Tafjord", "Pete Walsh", "Luke Zettlemoyer", "Noah A. Smith", "Hannaneh Hajishirzi", "Iz Beltagy", "Dirk Groeneveld", "Jesse Dodge", "Kyle Lo" ], "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-2402-00159v1", "title": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" }, { "id": "cur20261015-support-soldaini-et-al-dolma-corpus-curation-2023", "title": "Soldaini et al.: Dolma open pretraining corpus and curation toolkit — institutional/author source", "url": "https://allenai.org/blog/dolma-3-trillion-tokens-open-llm-corpus-9a0ff4b8da64" } ], "points": "65000", "published_grade": { "id": "soldaini-et-al-dolma-corpus-curation-2023", "entry_id": "soldaini-et-al-dolma-corpus-curation-2023", "band": "B", "modifier": "+", "target": { "record_id": "urn:uuid:97087e66-6df3-4cf8-ac89-137de38a6609", "version": 1, "content_hash": "sha256:09cda274f889de28d09ed2afd47b7d9a5c49ade1070b366f2d8e5663ef9199cf" }, "what_changed": "Released a documented multi-source pretraining corpus and reproducible curation toolkit, with analyses of filtering, deduplication and source mixing for language-model research.", "scope": "Released a documented multi-source pretraining corpus and reproducible curation toolkit, with analyses of filtering, deduplication and source mixing for language-model research. Initial corpus release was August 2023; the January 2024 paper documents later corpus/toolkit versions and analyses. Distinct from OLMo's model framework; not a claim of bias-free, contamination-free or universally licensed data.", "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:97087e66-6df3-4cf8-ac89-137de38a6609", "version": 1, "content_hash": "sha256:09cda274f889de28d09ed2afd47b7d9a5c49ade1070b366f2d8e5663ef9199cf" }, "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": "Luca Soldaini", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Ben Bogin", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Khyathi Chandu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Valentin Hofmann", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sachin Kumar", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Li Lucy", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xinxi Lyu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Nathan Lambert", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kyle Richardson", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Zejiang Shen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Emma Strubell", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Nishant Subramani", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "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": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Luke Zettlemoyer", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Noah A. Smith", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" } }, { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-1", "kind": "source_reference", "source": { "citation": "Soldaini et al.: Dolma open pretraining corpus and curation toolkit — institutional/author source", "url": "https://allenai.org/blog/dolma-3-trillion-tokens-open-llm-corpus-9a0ff4b8da64" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "Initial corpus release was August 2023; the January 2024 paper documents later corpus/toolkit versions and analyses. Distinct from OLMo's model framework; not a claim of bias-free, contamination-free or universally licensed data.", "domain": "Language-model data curation and research resources" }, "sources": [ { "citation": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1" }, { "citation": "Soldaini et al.: Dolma open pretraining corpus and curation toolkit — institutional/author source", "url": "https://allenai.org/blog/dolma-3-trillion-tokens-open-llm-corpus-9a0ff4b8da64" } ], "statement": "# Soldaini et al.: Dolma open pretraining corpus and curation toolkit\n\nReleased a documented multi-source pretraining corpus and reproducible curation toolkit, with analyses of filtering, deduplication and source mixing for language-model research.\n\n## Scientific scope\n\nInitial corpus release was August 2023; the January 2024 paper documents later corpus/toolkit versions and analyses. Distinct from OLMo's model framework; not a claim of bias-free, contamination-free or universally licensed data.\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\nLuca Soldaini; Rodney Kinney; Akshita Bhagia; Dustin Schwenk; David Atkinson; Russell Authur; Ben Bogin; Khyathi Chandu; Jennifer Dumas; Yanai Elazar; Valentin Hofmann; Ananya Harsh Jha; Sachin Kumar; Li Lucy; Xinxi Lyu; Nathan Lambert; Ian Magnusson; Jacob Morrison; Niklas Muennighoff; Aakanksha Naik; Crystal Nam; Matthew E. Peters; Abhilasha Ravichander; Kyle Richardson; Zejiang Shen; Emma Strubell; Nishant Subramani; Oyvind Tafjord; Pete Walsh; Luke Zettlemoyer; Noah A. Smith; Hannaneh Hajishirzi; Iz Beltagy; Dirk Groeneveld; Jesse Dodge; Kyle Lo\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- [Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research](https://arxiv.org/abs/2402.00159v1)\n- [Soldaini et al.: Dolma open pretraining corpus and curation toolkit — institutional/author source](https://allenai.org/blog/dolma-3-trillion-tokens-open-llm-corpus-9a0ff4b8da64)\n", "summary": "Released a documented multi-source pretraining corpus and reproducible curation toolkit, with analyses of filtering, deduplication and source mixing for language-model research.", "title": "Soldaini et al.: Dolma open pretraining corpus and curation toolkit" }, "record_id": "urn:uuid:97087e66-6df3-4cf8-ac89-137de38a6609", "version": 1, "source_ref": { "record_id": "urn:uuid:97087e66-6df3-4cf8-ac89-137de38a6609", "version": 1, "content_hash": "sha256:09cda274f889de28d09ed2afd47b7d9a5c49ade1070b366f2d8e5663ef9199cf" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:474281e7c55ac6220b5e7f8464460b19134df543ea9a679e355d14a14841937d" }, "target": { "record_id": "urn:uuid:97087e66-6df3-4cf8-ac89-137de38a6609", "version": 1, "content_hash": "sha256:09cda274f889de28d09ed2afd47b7d9a5c49ade1070b366f2d8e5663ef9199cf" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "soldaini-et-al-dolma-corpus-curation-2023", "entry_id": "soldaini-et-al-dolma-corpus-curation-2023", "revision": 1, "title": "Soldaini et al.: Dolma open pretraining corpus and curation toolkit", "context": "Language-model data curation and research resources", "track": "Human-designed research method or resource", "band": "B", "modifier": "+", "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Released a documented multi-source pretraining corpus and reproducible curation toolkit, with analyses of filtering, deduplication and source mixing for language-model research.", "scope": "Released a documented multi-source pretraining corpus and reproducible curation toolkit, with analyses of filtering, deduplication and source mixing for language-model research. Initial corpus release was August 2023; the January 2024 paper documents later corpus/toolkit versions and analyses. Distinct from OLMo's model framework; not a claim of bias-free, contamination-free or universally licensed data.", "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. Initial corpus release was August 2023; the January 2024 paper documents later corpus/toolkit versions and analyses. Distinct from OLMo's model framework; not a claim of bias-free, contamination-free or universally licensed data.", "references": [ { "title": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "url": "https://arxiv.org/abs/2402.00159v1", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." }, { "title": "Soldaini et al.: Dolma open pretraining corpus and curation toolkit — institutional/author source", "url": "https://allenai.org/blog/dolma-3-trillion-tokens-open-llm-corpus-9a0ff4b8da64", "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:97087e66-6df3-4cf8-ac89-137de38a6609", "version": 1, "content_hash": "sha256:09cda274f889de28d09ed2afd47b7d9a5c49ade1070b366f2d8e5663ef9199cf" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "65000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }