{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "clark-et-al-ai2-arc-2018",
    "title": "AI2 ARC: science questions separated by baseline difficulty",
    "summary": "Released grade-school science multiple-choice questions, a supporting sentence corpus and reference systems, separating a Challenge set by joint failure of retrieval and word-association solvers.",
    "boundary": "AI2 Reasoning Challenge is distinct from Chollet's Abstraction and Reasoning Corpus. Challenge membership is operationally baseline-relative, not a proof that no shortcut exists. This record concerns general AI evaluation, not scientific or biomedical discoveries in the questions.",
    "area": "Reasoning benchmarks",
    "topic": "Artificial intelligence",
    "year": 2018,
    "lane": "HUMAN",
    "result": "BENCHMARK",
    "contribution_kind": "EVALUATION_RESOURCE_DESIGN",
    "package_id": "clark-et-al-ai2-arc-2018",
    "target": {
      "record_id": "urn:uuid:b5e658d2-9bb3-42ca-a647-0d636da0202b",
      "version": 1,
      "content_hash": "sha256:3258ca04f7198a16e33335c0c7a3ba3c15f79a15905bdfa773997905fa13505a"
    },
    "humans": [
      "Peter Clark",
      "Isaac Cowhey",
      "Oren Etzioni",
      "Tushar Khot",
      "Ashish Sabharwal",
      "Carissa Schoenick",
      "Oyvind Tafjord"
    ],
    "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-1803-05457v1",
        "title": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
        "url": "https://arxiv.org/abs/1803.05457v1"
      }
    ],
    "points": "125000",
    "published_grade": {
      "id": "clark-et-al-ai2-arc-2018",
      "entry_id": "clark-et-al-ai2-arc-2018",
      "band": "A",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:b5e658d2-9bb3-42ca-a647-0d636da0202b",
        "version": 1,
        "content_hash": "sha256:3258ca04f7198a16e33335c0c7a3ba3c15f79a15905bdfa773997905fa13505a"
      },
      "what_changed": "Released grade-school science multiple-choice questions, a supporting sentence corpus and reference systems, separating a Challenge set by joint failure of retrieval and word-association solvers.",
      "scope": "Released grade-school science multiple-choice questions, a supporting sentence corpus and reference systems, separating a Challenge set by joint failure of retrieval and word-association solvers. AI2 Reasoning Challenge is distinct from Chollet's Abstraction and Reasoning Corpus. Challenge membership is operationally baseline-relative, not a proof that no shortcut exists. This record concerns general AI evaluation, not scientific or biomedical discoveries in the questions.",
      "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:b5e658d2-9bb3-42ca-a647-0d636da0202b",
        "version": 1,
        "content_hash": "sha256:3258ca04f7198a16e33335c0c7a3ba3c15f79a15905bdfa773997905fa13505a"
      },
      "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": "Peter Clark",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
            "url": "https://arxiv.org/abs/1803.05457v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Isaac Cowhey",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
            "url": "https://arxiv.org/abs/1803.05457v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Oren Etzioni",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
            "url": "https://arxiv.org/abs/1803.05457v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Tushar Khot",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
            "url": "https://arxiv.org/abs/1803.05457v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Ashish Sabharwal",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
            "url": "https://arxiv.org/abs/1803.05457v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Carissa Schoenick",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
            "url": "https://arxiv.org/abs/1803.05457v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Oyvind Tafjord",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
            "url": "https://arxiv.org/abs/1803.05457v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
            "url": "https://arxiv.org/abs/1803.05457v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "AI2 Reasoning Challenge is distinct from Chollet's Abstraction and Reasoning Corpus. Challenge membership is operationally baseline-relative, not a proof that no shortcut exists. This record concerns general AI evaluation, not scientific or biomedical discoveries in the questions.",
        "domain": "Reasoning benchmarks"
      },
      "sources": [
        {
          "citation": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
          "url": "https://arxiv.org/abs/1803.05457v1"
        }
      ],
      "statement": "# AI2 ARC: science questions separated by baseline difficulty\n\nReleased grade-school science multiple-choice questions, a supporting sentence corpus and reference systems, separating a Challenge set by joint failure of retrieval and word-association solvers.\n\n## Scientific scope\n\nAI2 Reasoning Challenge is distinct from Chollet's Abstraction and Reasoning Corpus. Challenge membership is operationally baseline-relative, not a proof that no shortcut exists. This record concerns general AI evaluation, not scientific or biomedical discoveries in the questions.\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\nPeter Clark; Isaac Cowhey; Oren Etzioni; Tushar Khot; Ashish Sabharwal; Carissa Schoenick; Oyvind Tafjord\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- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://arxiv.org/abs/1803.05457v1)\n",
      "summary": "Released grade-school science multiple-choice questions, a supporting sentence corpus and reference systems, separating a Challenge set by joint failure of retrieval and word-association solvers.",
      "title": "AI2 ARC: science questions separated by baseline difficulty"
    },
    "record_id": "urn:uuid:b5e658d2-9bb3-42ca-a647-0d636da0202b",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:b5e658d2-9bb3-42ca-a647-0d636da0202b",
      "version": 1,
      "content_hash": "sha256:3258ca04f7198a16e33335c0c7a3ba3c15f79a15905bdfa773997905fa13505a"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:5e1008cdc99fcf0e966c04e602f681ff426ed78a2ebc1e11aafd7c2218bc4f1e"
  },
  "target": {
    "record_id": "urn:uuid:b5e658d2-9bb3-42ca-a647-0d636da0202b",
    "version": 1,
    "content_hash": "sha256:3258ca04f7198a16e33335c0c7a3ba3c15f79a15905bdfa773997905fa13505a"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "clark-et-al-ai2-arc-2018",
    "entry_id": "clark-et-al-ai2-arc-2018",
    "revision": 1,
    "title": "AI2 ARC: science questions separated by baseline difficulty",
    "context": "Reasoning benchmarks",
    "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": "Released grade-school science multiple-choice questions, a supporting sentence corpus and reference systems, separating a Challenge set by joint failure of retrieval and word-association solvers.",
    "scope": "Released grade-school science multiple-choice questions, a supporting sentence corpus and reference systems, separating a Challenge set by joint failure of retrieval and word-association solvers. AI2 Reasoning Challenge is distinct from Chollet's Abstraction and Reasoning Corpus. Challenge membership is operationally baseline-relative, not a proof that no shortcut exists. This record concerns general AI evaluation, not scientific or biomedical discoveries in the questions.",
    "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. AI2 Reasoning Challenge is distinct from Chollet's Abstraction and Reasoning Corpus. Challenge membership is operationally baseline-relative, not a proof that no shortcut exists. This record concerns general AI evaluation, not scientific or biomedical discoveries in the questions.",
    "references": [
      {
        "title": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge",
        "url": "https://arxiv.org/abs/1803.05457v1",
        "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:b5e658d2-9bb3-42ca-a647-0d636da0202b",
      "version": 1,
      "content_hash": "sha256:3258ca04f7198a16e33335c0c7a3ba3c15f79a15905bdfa773997905fa13505a"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "125000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}