{
  "format": "agent-article-v0",
  "article_id": "PM-GROK-CORE-07",
  "canonical_url": "/providers/pm-grok-core-07",
  "page_type": "reference",
  "claim_ids": [],
  "evidence_ids": [
    "EVD-PM-GROK-CORE-07-URL-66321E57AE7A",
    "EVD-PM-GROK-CORE-07-URL-C547143F6623",
    "EVD-PM-GROK-CORE-07-URL-CC7D258F82FC",
    "EVD-PM-GROK-CORE-07-URL-0F8FE06795BB",
    "EVD-PM-GROK-CORE-07-URL-0878B9C4BDC7",
    "EVD-PM-GROK-CORE-07-URL-E3CAAEA65CC5",
    "EVD-PM-GROK-CORE-07-URL-2DC3FAB17BB9",
    "EVD-PM-GROK-CORE-07-URL-086CFC997988",
    "EVD-PM-GROK-CORE-07-URL-905D5D7A5FB4",
    "PM-GROK-CORE-07-DOCUMENT-READBACK"
  ],
  "unknown_ids": [
    "PM-GROK-CORE-07-CURRENTNESS"
  ],
  "operational_object_ids": [],
  "provider": [
    "GROK"
  ],
  "models": [],
  "plans": [],
  "surfaces": [],
  "regions": [],
  "current_status": "UNKNOWN",
  "observation_status": "UNOBSERVED",
  "freshness": "UNKNOWN",
  "last_verified": null,
  "supersedes": [],
  "superseded_by": [],
  "provenance": [
    "DOC-083cde4caa627644-PM-GROK-CORE-07",
    "SRC-PM-GROK-CORE-07-URL-66321E57AE7A",
    "SRC-PM-GROK-CORE-07-URL-C547143F6623",
    "SRC-PM-GROK-CORE-07-URL-CC7D258F82FC",
    "SRC-PM-GROK-CORE-07-URL-0F8FE06795BB",
    "SRC-PM-GROK-CORE-07-URL-0878B9C4BDC7",
    "SRC-PM-GROK-CORE-07-URL-E3CAAEA65CC5",
    "SRC-PM-GROK-CORE-07-URL-2DC3FAB17BB9",
    "SRC-PM-GROK-CORE-07-URL-086CFC997988",
    "SRC-PM-GROK-CORE-07-URL-905D5D7A5FB4"
  ],
  "article_sources": [
    {
      "id": "EVD-PM-GROK-CORE-07-URL-66321E57AE7A",
      "evidence_class": "RESEARCH",
      "title": "xAI, Introducing Grok 4.6: <[",
      "href": "https://x.ai/news/grok-4-6",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-66321E57AE7A"
      ],
      "supporting_locators": [
        "Provenance",
        "- xAI, Introducing Grok 4.6: <[https://x.ai/news/grok-4-6"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-PM-GROK-CORE-07-URL-C547143F6623",
      "evidence_class": "RESEARCH",
      "title": "xAI, Grok 4.6 Model Card: <[",
      "href": "https://media.x.ai/v1/website/card-4p6-4cd2dc57.pdf",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-C547143F6623"
      ],
      "supporting_locators": [
        "Provenance",
        "- xAI, Grok 4.6 Model Card: <[https://media.x.ai/v1/website/card-4p6-4cd2dc57.pdf"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-PM-GROK-CORE-07-URL-CC7D258F82FC",
      "evidence_class": "RESEARCH",
      "title": "xAI, xai-org/grok-build: <[",
      "href": "https://github.com/xai-org/grok-build",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-CC7D258F82FC"
      ],
      "supporting_locators": [
        "Provenance",
        "- xAI, xai-org/grok-build: <[https://github.com/xai-org/grok-build"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-PM-GROK-CORE-07-URL-0F8FE06795BB",
      "evidence_class": "RESEARCH",
      "title": "xAI, Grok Build changelog: <[",
      "href": "https://x.ai/build/changelog",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-0F8FE06795BB"
      ],
      "supporting_locators": [
        "Provenance",
        "- xAI, Grok Build changelog: <[https://x.ai/build/changelog"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-PM-GROK-CORE-07-URL-0878B9C4BDC7",
      "evidence_class": "RESEARCH",
      "title": "Artificial Analysis, Benchmarking Methodology / Intelligence Index: <[",
      "href": "https://artificialanalysis.ai/methodology",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-0878B9C4BDC7"
      ],
      "supporting_locators": [
        "Provenance",
        "- Artificial Analysis, Benchmarking Methodology / Intelligence Index: <[https://artificialanalysis.ai/methodology"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-PM-GROK-CORE-07-URL-E3CAAEA65CC5",
      "evidence_class": "RESEARCH",
      "title": "Artificial Analysis, Benchmarking Methodology / Intelligence Index: <[",
      "href": "https://artificialanalysis.ai/",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-E3CAAEA65CC5"
      ],
      "supporting_locators": [
        "Provenance",
        "- Artificial Analysis, Benchmarking Methodology / Intelligence Index: <[https://artificialanalysis.ai/"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-PM-GROK-CORE-07-URL-2DC3FAB17BB9",
      "evidence_class": "RESEARCH",
      "title": "xAI Batch API / Structured Outputs / Models: <[",
      "href": "https://docs.x.ai/developers/advanced-api-usage/batch-api",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-2DC3FAB17BB9"
      ],
      "supporting_locators": [
        "Provenance",
        "- xAI Batch API / Structured Outputs / Models: <[https://docs.x.ai/developers/advanced-api-usage/batch-api"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-PM-GROK-CORE-07-URL-086CFC997988",
      "evidence_class": "RESEARCH",
      "title": "xAI Batch API / Structured Outputs / Models: <[https://docs.x.ai/developers/advanced-api-usage/batch-api](https://docs.x.ai/developers/advanced-api-usage/batch-api)>; <[",
      "href": "https://docs.x.ai/developers/model-capabilities/text/structured-outputs",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-086CFC997988"
      ],
      "supporting_locators": [
        "Provenance",
        "- xAI Batch API / Structured Outputs / Models: <[https://docs.x.ai/developers/advanced-api-usage/batch-api](https://docs.x.ai/developers/advanced-api-usage/batch-api)>; <[https://docs.x.ai/developers/model-capabilities/text/structured-outputs"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "EVD-PM-GROK-CORE-07-URL-905D5D7A5FB4",
      "evidence_class": "RESEARCH",
      "title": "xAI Batch API / Structured Outputs / Models: <[https://docs.x.ai/developers/advanced-api-usage/batch-api](https://docs.x.ai/developers/advanced-api-usage/batch-api)>; <[https://doc",
      "href": "https://docs.x.ai/developers/models",
      "supports": [],
      "limit": "元の監査済み資料に記載された参照先です。URLの復元は、資料の最新性や全主張の支持を新たに検証したことを意味しません。",
      "origin_class": "APPROVED_DOCUMENT_REFERENCE",
      "source_or_experiment_ids": [
        "SRC-PM-GROK-CORE-07-URL-905D5D7A5FB4"
      ],
      "supporting_locators": [
        "Provenance",
        "- xAI Batch API / Structured Outputs / Models: <[https://docs.x.ai/developers/advanced-api-usage/batch-api](https://docs.x.ai/developers/advanced-api-usage/batch-api)>; <[https://docs.x.ai/developers/model-capabilities/text/structured-outputs](https://docs.x.ai/developers/model-capabilities/text/structured-outputs)>; <[https://docs.x.ai/developers/models"
      ],
      "scope": "Provenance",
      "provenance_status": "APPROVED_DOCUMENT_REFERENCE_PROJECTED"
    },
    {
      "id": "PM-GROK-CORE-07-DOCUMENT-READBACK",
      "evidence_class": "IMPL",
      "title": "原資料との収録照合",
      "supports": [
        "資料単位の本文ハッシュ、段落数、表数を照合しています。"
      ],
      "limit": "収録照合は主張の真偽や外部根拠の最新性を追加保証しません。",
      "origin_class": "DOCUMENT_INGESTION_READBACK",
      "source_or_experiment_ids": [
        "DOC-083cde4caa627644-PM-GROK-CORE-07"
      ],
      "supporting_locators": [
        "18WPldGemks2px0ukhKYINeBMrBwAmlAi",
        "083cde4caa627644036a2225f1f6ff29b8015bd902614fe1f7a00a997b4eb59c",
        "provider_mappings/PM-GROK-CORE-07.md",
        "7d3a9aafb59d18db0ba7b619ea02af30ecb2c9611ab34239f9708fe35fb72fa6"
      ],
      "scope": "公開指定を受けた資料単位の全文・表・出典。",
      "provenance_status": "SOURCE_IDENTITY_VERIFIED"
    }
  ],
  "research_sections": [
    {
      "heading": "資料の識別情報",
      "text": "Source SHA-256 e2ec3734d887823cc889549b45a5c24b8b98bf0fb9ca247ff10ff40461134b20"
    },
    {
      "heading": "Product Mapping — Grok / CORE-07",
      "text": "PRODUCT_MAPPING_ID: PM-GROK-CORE-07-v0.1\n\nPROVIDER: GROK / xAI\n\nCORE_PACKET: PKT-GEMINI-A-CORE-07-v0.1\n\nAS_OF: 2026-09-13 JST\n\nSTATUS: PUBLIC_MAPPING_BOUNDED_COMPLETE / BENCHMARK_PROVENANCE_SPLIT / LIVE_ORG_PENDING\n\nLAYER: PRODUCT_MAPPING (not Enterprise AI Core; not Organization Overlay)"
    },
    {
      "heading": "Scope",
      "text": "CORE-07のgolden dataset、scorer/judge、holdout、slice/tail gate、release evidenceを、Grok 4.6 announcement/model card、xAI APIのBatch/structured-output/model identity、author-maintained Grok Build、独立benchmark methodologyへ対応づける。公開benchmark値はその評価条件に限定し、xAI organizationのrelease acceptance、実tenant性能、非公開dataset、汚染有無、judge妥当性へ外挿しない。"
    },
    {
      "heading": "Surface and lifecycle separation",
      "text": "| SURFACE | CURRENT EVIDENCE | DECISION | LIMIT |\n| --- | --- | --- | --- |\n| release announcement | 2026-08-12のGrok 4.6発表はAA Intelligence、GDPVal-AA、DeepSWE 1.1、CursorBench 3.2、FrontierCode 1.1等を掲示 | model/release時点のcapability evidenceとして保存 | competitor値は各社system cardまたはleaderboard由来で、単一共通runではない |\n| model card | final deployed checkpointを原則としつつ、Cursor、Mercor、Cognition、Datacurve、Abundant AI、Harbor、Artificial Analysis等の実施結果と複数harness/effortを併記 | benchmark名/version、runner、harness、effort、sample、metric、reported-byを行単位で保存 | public scoreはorganization固有task、holdout、acceptance thresholdの証拠ではない |\n| Grok Build | xAIのcoding-agent harness/TUI。公開repoはmonorepoからperiodic syncされ、SOURCE_REVを持つ | coding/agent評価ではbinary versionとsource revision、config、tools、workspaceをcandidate environmentへ含める | current repo/sourceは過去model-card runのexact harness artifactを自動再構成しない |\n| Batch API | request単位IDとpending/success/error/cancel/expiryを持つ非同期carrier | bulk evaluationのtransport/statusとして利用可能 | batch completionはvalid result、semantic pass、release acceptanceではない |\n| structured outputs | JSON Schema subsetでresult envelopeを制約可能 | parser/schemaのdeterministic checkへ利用 | schema conformanceはoracle、rubric、judge calibration、意味品質を保証しない |\n| independent benchmark | Artificial Analysisはmodel/API/systemの独立benchmark methodologyとversioned composite indexを公開 | first-party model cardと独立測定を別provenanceで比較 | index version変更により構成評価が変わるため、異版scoreを同一系列として直結しない |"
    },
    {
      "heading": "Core → Grok mapping rows",
      "text": "| ROW | CORE CONTRACT | XAI / GROK FINDING | DECISION / UNKNOWN |\n| --- | --- | --- | --- |\n| PM-C07-GROK-001 | candidate/evaluation artifact separation | announcement、model card、API response、Batch、Grok Buildは別artifact/surface | candidate config、dataset、scorer/judge、run、result、release decisionを外部ledgerで結合 |\n| PM-C07-GROK-002 | versioned benchmark provenance | model cardはbenchmarkごとにversion、harness、thinking effort、実施者が異なる | scoreごとにexact benchmark/harness/effort/reported-by/as-ofを保存し、混合bar chartを共通runへ昇格しない |\n| PM-C07-GROK-003 | representative slice and acceptance | public coding/knowledge/safety benchmarksは広いが、組織固有のJapanese業務、RAG、tool、副作用、artifact受入を代表するとは限らない | organization task distribution、failure corpus、freshness、sealed holdoutを別設計 |\n| PM-C07-GROK-004 | deterministic-first scoring | structured outputとcoding harnessはschema、test、artifactの機械判定を支援できる | schema/test/receipt/readbackを先行し、model/judge評価だけでcritical correctnessを閉じない |\n| PM-C07-GROK-005 | judge registry/calibration | model cardにはmodel-based gradingや外部pairwise/rubric評価があるが、全judge config・order・human disagreementが一様に公開されるわけではない | judge model/config/prompt/rubric/order/sampling/abstention、人手校正をrun artifactへ固定 |\n| PM-C07-GROK-006 | harness identity | Grok Build repoはSOURCE_REVを持ち、2026-09-09のcurrent releaseはv1.0.25 | binary/version/source revision、model、tools、permissions、workspace image、networkを固定。current sourceを過去結果のexact harnessとみなさない |\n| PM-C07-GROK-007 | infra/candidate failure split | Batchはpartial/error/cancel/expiryを持ち、agent harnessもtool/terminal/network失敗を含み得る | INFRA_ERROR、invalid、missing、candidate failureを分離し、valid N不足を0点や合格へ変換しない |\n| PM-C07-GROK-008 | contamination/holdout boundary | public benchmark scoreと「contamination-resistant」という選定理由は、当該modelの非汚染を単独証明しない | leak ledger、fresh/rephrased challenge、sealed holdout、ConStat型gapを限定反証として使用し、汚染断定にも無汚染証明にも使わない |\n| PM-C07-GROK-009 | slice/tail/repetition gate | benchmark aggregateやpass@1はcritical tail、組織固有regression、反復varianceを隠し得る | slice AND gate、zero-tolerance、repeat distribution、worst case、unsafe/over-refusal対を要求 |\n| PM-C07-GROK-010 | Organization boundary | 採用model/effort/surface/harness、dataset owner、threshold、holdout custodian、judge allowlist、release authorityは公開資料から確定しない | Organization Overlayへ移送し、UNKNOWNを維持 |"
    },
    {
      "heading": "Safe verification profile",
      "text": "非機密synthetic fixtureと許可されたtest teamだけを使う。今回はxAI API、team、Console、model、Batch、Grok Build binary、tool、dataset、judgeを操作していない。\n\n- candidateにmodel/date pin、reasoning effort、system prompt、tool/source/schema、API/SDK、Grok Build binary/version/SOURCE_REV、workspace imageを固定する。\n\n- dev、representative、known-failure、freshness、challenge、sealed holdoutを分離し、benchmark/public example/prompt tuningへの露出をleak ledgerへ記録する。\n\n- exact/schema/calculation/test/receipt/artifact/readbackをdeterministic-firstで判定し、LLM judgeはorder swap、反復、abstention、人手sampleを伴う補助判定にする。\n\n- Batchはrequest IDごとにstatusをread backし、error/cancel/expire/missing/parser failureをINFRA_ERRORとしてcandidate errorから分離する。\n\n- agent/coding taskはtrajectory、tool receipt、git/workspace diff、tests、artifact digest、external readback、human acceptanceを別証拠としてjoinする。\n\n- 公開benchmark再現laneとorganization golden set laneを分け、異なるbenchmark version/harness/effortのscoreを同一aggregateへ混ぜない。\n\n- overall平均がpassでもcritical slice、known regression、Japanese、safety/over-refusal、tail、variance、valid Nのいずれかがfailならreleaseをblockする。\n\n既存EXP-C07-001の12/12はCOMPILER_EXPERIMENTであり、Grok/xAI、Grok Build、Batch、judge、modelのlive試験へ再分類しない。"
    },
    {
      "heading": "Organization Overlay handoff",
      "text": "- adopted API/consumer/Build surface、team/region、model/date pin/effort、SDK/Build version/source revision\n\n- dataset owner/access、holdout custodian、leak ledger、freshness/failure corpus更新周期\n\n- scorer/judge registry、人手sample、disagreement/abstention/tie-break policy\n\n- Batch quota/deadline/retry、infra-error policy、valid-N floor、evidence retention\n\n- slice threshold、critical failure、variance、cost ceiling、release/exception/rollback authority"
    },
    {
      "heading": "Provenance",
      "text": "- xAI, Introducing Grok 4.6: <[https://x.ai/news/grok-4-6](https://x.ai/news/grok-4-6)> (published 2026-08-12; read 2026-09-13)\n\n- xAI, Grok 4.6 Model Card: <[https://media.x.ai/v1/website/card-4p6-4cd2dc57.pdf](https://media.x.ai/v1/website/card-4p6-4cd2dc57.pdf)> (release artifact read 2026-09-13)\n\n- xAI, xai-org/grok-build: <[https://github.com/xai-org/grok-build](https://github.com/xai-org/grok-build)> (SOURCE_REV c4ea71cfdbcdb21e32e41bc25a0043d7d4836714; read 2026-09-13)\n\n- xAI, Grok Build changelog: <[https://x.ai/build/changelog](https://x.ai/build/changelog)> (v1.0.25 dated 2026-09-09; read 2026-09-13)\n\n- Artificial Analysis, Benchmarking Methodology / Intelligence Index: <[https://artificialanalysis.ai/methodology](https://artificialanalysis.ai/methodology)>; <[https://artificialanalysis.ai/](https://artificialanalysis.ai/)> (current index v4.3 observed 2026-09-13)\n\n- xAI Batch API / Structured Outputs / Models: <[https://docs.x.ai/developers/advanced-api-usage/batch-api](https://docs.x.ai/developers/advanced-api-usage/batch-api)>; <[https://docs.x.ai/developers/model-capabilities/text/structured-outputs](https://docs.x.ai/developers/model-capabilities/text/structured-outputs)>; <[https://docs.x.ai/developers/models](https://docs.x.ai/developers/models)> (reused)"
    },
    {
      "heading": "Exit condition",
      "text": "Grok 4.6のrelease/model-card benchmark、外部実施者、harness/effort、Grok Build source/release、Batch、structured output、独立benchmark methodologyを別surfaceとしてCORE-07へ対応づけた。公開scoreをorganization release acceptance、汚染有無、judge妥当性、live tenant性能へ昇格しない。Core claimは変更しないためGemini/GPT/Claude遡及監査は不要である。"
    }
  ],
  "human_url": "/providers/pm-grok-core-07",
  "markdown_url": "/agent/article.md?path=%2Fproviders%2Fpm-grok-core-07",
  "json_url": "/agent/article.json?path=%2Fproviders%2Fpm-grok-core-07"
}