{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "dietterich-classifier-comparison-tests-1998",
    "title": "Dietterich: approximate tests for comparing classification algorithms",
    "summary": "Compared five approximate significance tests for supervised-classifier comparisons by their type-I error and power, and introduced and evaluated the 5×2 cross-validation paired test.",
    "boundary": "The record is Dietterich's sole-author 1998 Neural Computation article. Recommendations are bounded to its simulation settings and computational-cost cases; it does not replace later corrected resampling methods or establish a universal test for every machine-learning comparison.",
    "area": "Evaluation, safety and interpretability",
    "topic": "Artificial intelligence",
    "year": 1998,
    "lane": "HUMAN",
    "result": "EMPIRICAL",
    "package_id": "dietterich-classifier-comparison-tests-1998",
    "target": {
      "record_id": "urn:uuid:53e745a1-7a8e-4c78-a093-6a6a83c65d96",
      "version": 1,
      "content_hash": "sha256:ceff4233bca25ba9de2dcd68dd5c1b9a4ce0379a701eca3dcea5b6425b650d84"
    },
    "humans": [
      "Thomas G. Dietterich"
    ],
    "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": "mitpress-dietterich-classifier-tests-1998",
        "title": "MIT Press record for classifier-comparison tests",
        "url": "https://doi.org/10.1162/089976698300017197"
      },
      {
        "id": "oregonstate-dietterich-classifier-tests-fulltext",
        "title": "Dietterich author-hosted full text",
        "url": "https://web.engr.oregonstate.edu/~tgd/cv/cv.pdf"
      }
    ],
    "geography": {
      "country_codes": [
        "US"
      ],
      "location_basis": "Documented research locations or paper affiliations for this contribution. Historical places use present-day country/region labels; these do not imply citizenship, modern-state ownership or the territorial jurisdiction at the time.",
      "source_url": "https://direct.mit.edu/neco/article/10/7/1895/6224/Approximate-Statistical-Tests-for-Comparing",
      "target": {
        "record_id": "urn:uuid:53e745a1-7a8e-4c78-a093-6a6a83c65d96",
        "version": 1,
        "content_hash": "sha256:ceff4233bca25ba9de2dcd68dd5c1b9a4ce0379a701eca3dcea5b6425b650d84"
      },
      "basis": "RESEARCH_LOCATION_OR_PAPER_AFFILIATION",
      "reviewed_on": "2026-09-26",
      "nationality_inferred": false,
      "sources": [
        {
          "title": "Attribution source",
          "url": "https://direct.mit.edu/neco/article/10/7/1895/6224/Approximate-Statistical-Tests-for-Comparing"
        }
      ],
      "coverage_status": "COMPLETE",
      "country_labels": {
        "US": "United States"
      }
    },
    "points": "90000",
    "published_grade": {
      "id": "dietterich-classifier-comparison-tests-1998",
      "entry_id": "dietterich-classifier-comparison-tests-1998",
      "band": "A",
      "modifier": "-",
      "target": {
        "record_id": "urn:uuid:53e745a1-7a8e-4c78-a093-6a6a83c65d96",
        "version": 1,
        "content_hash": "sha256:ceff4233bca25ba9de2dcd68dd5c1b9a4ce0379a701eca3dcea5b6425b650d84"
      },
      "what_changed": "Compared five tests and introduced/evaluated the 5x2 cross-validation paired test.",
      "scope": "The record is Dietterich's sole-author 1998 Neural Computation article. Recommendations are bounded to its simulation settings and computational-cost cases; it does not replace later corrected resampling methods or establish a universal test for every machine-learning comparison.",
      "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:53e745a1-7a8e-4c78-a093-6a6a83c65d96",
        "version": 1,
        "content_hash": "sha256:ceff4233bca25ba9de2dcd68dd5c1b9a4ce0379a701eca3dcea5b6425b650d84"
      },
      "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": "Thomas G. Dietterich",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "discoverer"
          ],
          "source": {
            "citation": "MIT Press record for classifier-comparison tests",
            "url": "https://doi.org/10.1162/089976698300017197"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "MIT Press record for classifier-comparison tests",
            "url": "https://doi.org/10.1162/089976698300017197"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Dietterich author-hosted full text",
            "url": "https://web.engr.oregonstate.edu/~tgd/cv/cv.pdf"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "The record is Dietterich's sole-author 1998 Neural Computation article. Recommendations are bounded to its simulation settings and computational-cost cases; it does not replace later corrected resampling methods or establish a universal test for every machine-learning comparison.",
        "domain": "Evaluation, safety and interpretability"
      },
      "sources": [
        {
          "citation": "MIT Press record for classifier-comparison tests",
          "url": "https://doi.org/10.1162/089976698300017197"
        },
        {
          "citation": "Dietterich author-hosted full text",
          "url": "https://web.engr.oregonstate.edu/~tgd/cv/cv.pdf"
        }
      ],
      "statement": "# Dietterich: approximate tests for comparing classification algorithms\n\nCompared five approximate significance tests for supervised-classifier comparisons by their type-I error and power, and introduced and evaluated the 5×2 cross-validation paired test.\n\n## Scientific scope\n\nThe record is Dietterich's sole-author 1998 Neural Computation article. Recommendations are bounded to its simulation settings and computational-cost cases; it does not replace later corrected resampling methods or establish a universal test for every machine-learning comparison.\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\nThomas G. Dietterich\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- [MIT Press record for classifier-comparison tests](https://doi.org/10.1162/089976698300017197)\n- [Dietterich author-hosted full text](https://web.engr.oregonstate.edu/~tgd/cv/cv.pdf)\n",
      "summary": "Compared five approximate significance tests for supervised-classifier comparisons by their type-I error and power, and introduced and evaluated the 5×2 cross-validation paired test.",
      "title": "Dietterich: approximate tests for comparing classification algorithms"
    },
    "record_id": "urn:uuid:53e745a1-7a8e-4c78-a093-6a6a83c65d96",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:53e745a1-7a8e-4c78-a093-6a6a83c65d96",
      "version": 1,
      "content_hash": "sha256:ceff4233bca25ba9de2dcd68dd5c1b9a4ce0379a701eca3dcea5b6425b650d84"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:cd9e9206864ef8579eeb4ede3ad2de2041817957d577a171a2cc0cf3d41ee719"
  },
  "target": {
    "record_id": "urn:uuid:53e745a1-7a8e-4c78-a093-6a6a83c65d96",
    "version": 1,
    "content_hash": "sha256:ceff4233bca25ba9de2dcd68dd5c1b9a4ce0379a701eca3dcea5b6425b650d84"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "dietterich-classifier-comparison-tests-1998",
    "entry_id": "dietterich-classifier-comparison-tests-1998",
    "revision": 1,
    "title": "Dietterich: approximate tests for comparing classification algorithms",
    "context": "Evaluation, safety and interpretability",
    "track": "EMPIRICAL",
    "band": "A",
    "modifier": "-",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-25",
    "evidence_cutoff": "2026-09-25",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Compared five tests and introduced/evaluated the 5x2 cross-validation paired test.",
    "scope": "The record is Dietterich's sole-author 1998 Neural Computation article. Recommendations are bounded to its simulation settings and computational-cost cases; it does not replace later corrected resampling methods or establish a universal test for every machine-learning comparison.",
    "evidence_summary": "The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is Dietterich's sole-author 1998 Neural Computation article. Recommendations are bounded to its simulation settings and computational-cost cases; it does not replace later corrected resampling methods or establish a universal test for every machine-learning comparison.",
    "references": [
      {
        "title": "MIT Press record for classifier-comparison tests",
        "url": "https://doi.org/10.1162/089976698300017197",
        "locator": "Source for the stated contribution; scientific claims remain bounded to the linked work."
      }
    ],
    "roles": [
      {
        "who": "Thomas G. Dietterich",
        "credit": "SCIENCE",
        "did": "Named source author of the scoped work; individual effort shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:53e745a1-7a8e-4c78-a093-6a6a83c65d96",
      "version": 1,
      "content_hash": "sha256:ceff4233bca25ba9de2dcd68dd5c1b9a4ce0379a701eca3dcea5b6425b650d84"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "90000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}