{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "scaling-laws-neural-language-models-2020", "title": "Kaplan and colleagues: scaling laws for neural language models", "summary": "Measured approximate power-law relationships between language-model cross-entropy loss and model size, dataset size and training compute over the studied ranges, and derived compute-allocation implications.", "boundary": "These are empirical relationships for the architectures, data and loss regimes tested in the 2020 paper, not universal laws of intelligence or guarantees outside the measured ranges.", "area": "Foundation models", "year": 2020, "lane": "HUMAN", "result": "EMPIRICAL", "package_id": "scaling-laws-neural-language-models-2020", "target": { "record_id": "urn:uuid:feb84a68-2996-45ba-a06e-78428fba8207", "version": 1, "content_hash": "sha256:59f0d59e991007fda83b7bbc0880f54fba90599878b0df89113b96ae60728567" }, "humans": [ "Jared Kaplan", "Sam McCandlish", "Tom Henighan", "Tom B. Brown", "Benjamin Chess", "Rewon Child", "Scott Gray", "Alec Radford", "Jeffrey Wu", "Dario Amodei" ], "authors_complete": true, "human_role_note": "The named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "arxiv-kaplan-scaling-laws", "title": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } ], "points": "110000", "published_grade": { "id": "scaling-laws-neural-language-models-2020", "entry_id": "scaling-laws-neural-language-models-2020", "band": "A", "modifier": "-", "target": { "record_id": "urn:uuid:feb84a68-2996-45ba-a06e-78428fba8207", "version": 1, "content_hash": "sha256:59f0d59e991007fda83b7bbc0880f54fba90599878b0df89113b96ae60728567" }, "what_changed": "Model-training tradeoffs could be summarized and forecast approximately within measured regimes.", "scope": "2020 ten-author paper, cross-entropy loss and tested model/data ranges; not universal laws of intelligence or guaranteed compute-optimality elsewhere.", "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:feb84a68-2996-45ba-a06e-78428fba8207", "version": 1, "content_hash": "sha256:59f0d59e991007fda83b7bbc0880f54fba90599878b0df89113b96ae60728567" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-09-25T00:00:00Z", "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": "Jared Kaplan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sam McCandlish", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Tom Henighan", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Tom B. Brown", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Benjamin Chess", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Rewon Child", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Scott Gray", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Alec Radford", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jeffrey Wu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Dario Amodei", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "discoverer" ], "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "These are empirical relationships for the architectures, data and loss regimes tested in the 2020 paper, not universal laws of intelligence or guarantees outside the measured ranges.", "domain": "Foundation models" }, "sources": [ { "citation": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361" } ], "statement": "# Kaplan and colleagues: scaling laws for neural language models\n\nMeasured approximate power-law relationships between language-model cross-entropy loss and model size, dataset size and training compute over the studied ranges, and derived compute-allocation implications.\n\n## Scientific scope\n\nThese are empirical relationships for the architectures, data and loss regimes tested in the 2020 paper, not universal laws of intelligence or guarantees outside the measured ranges.\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\nJared Kaplan; Sam McCandlish; Tom Henighan; Tom B. Brown; Benjamin Chess; Rewon Child; Scott Gray; Alec Radford; Jeffrey Wu; Dario Amodei\n\nThe named authors contributed to this scoped work; individual effort shares and later applications are not assigned by the byline.\n\n\n\n## Original sources\n\n- [Kaplan et al., Scaling Laws for Neural Language Models](https://arxiv.org/abs/2001.08361)\n", "summary": "Measured approximate power-law relationships between language-model cross-entropy loss and model size, dataset size and training compute over the studied ranges, and derived compute-allocation implications.", "title": "Kaplan and colleagues: scaling laws for neural language models" }, "record_id": "urn:uuid:feb84a68-2996-45ba-a06e-78428fba8207", "version": 1, "source_ref": { "record_id": "urn:uuid:feb84a68-2996-45ba-a06e-78428fba8207", "version": 1, "content_hash": "sha256:59f0d59e991007fda83b7bbc0880f54fba90599878b0df89113b96ae60728567" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:98fba65500cf2a28276bf9bc1ec30038aef140aa7ad8e22c669ad12556d164f6" }, "target": { "record_id": "urn:uuid:feb84a68-2996-45ba-a06e-78428fba8207", "version": 1, "content_hash": "sha256:59f0d59e991007fda83b7bbc0880f54fba90599878b0df89113b96ae60728567" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "scaling-laws-neural-language-models-2020", "entry_id": "scaling-laws-neural-language-models-2020", "revision": 1, "title": "Kaplan and colleagues: scaling laws for neural language models", "context": "Foundation-model research", "track": "Empirical model scaling", "band": "A", "modifier": "-", "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-09-25", "evidence_cutoff": "2026-09-25", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Model-training tradeoffs could be summarized and forecast approximately within measured regimes.", "scope": "2020 ten-author paper, cross-entropy loss and tested model/data ranges; not universal laws of intelligence or guaranteed compute-optimality elsewhere.", "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. These are empirical relationships for the architectures, data and loss regimes tested in the 2020 paper, not universal laws of intelligence or guarantees outside the measured ranges.", "references": [ { "title": "Kaplan et al., Scaling Laws for Neural Language Models", "url": "https://arxiv.org/abs/2001.08361", "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work." } ], "roles": [ { "who": "The named authors listed in the linked research record", "credit": "SCIENCE", "did": "Complete source byline retained in the research record; this collective display does not merge person identities or measure labor shares." } ], "target": { "record_id": "urn:uuid:feb84a68-2996-45ba-a06e-78428fba8207", "version": 1, "content_hash": "sha256:59f0d59e991007fda83b7bbc0880f54fba90599878b0df89113b96ae60728567" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "110000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }