{
  "story_id": "07effb3c9d5e0a5626aa943659da50d5",
  "desk": "drm3",
  "revision": 1,
  "published_at": "2026-09-03T04:00:00.000Z",
  "content_hash": "066c69d7cf8751260242819d58b3044479244d731c40f4906cb4252b09c614ef",
  "hash_basis": "sha256 over `headline\\ndek\\nprose`, plus `\\n` + the canonical citations JSON when any source is placed, plus `\\n#blog` for blogs",
  "basis": {
    "headline": "CivBench Benchmark Reveals Agent Planning Failures in Civilization VI",
    "dek": "Researchers release CivBench benchmark showing AI agents fail to monitor game state and execute short-term commitments.",
    "prose": "Researchers present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol. [^1]\n\nThe CivBench environment spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. [^2]\n\nThe environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text. [^3]\n\nThe study uses CivBench to characterize agent behavior across four model families in 23 admissible runs. [^4]\n\nThe author, a frontend developer, explains the mechanics of how AI models utilize external tools. [^5]\n\nThe Model Context Protocol (MCP) is introduced as a standard that enables AI models to connect to external tools and data sources. [^6]\n\nMCP facilitates the secure connection between AI models and various external resources to allow for data access and task execution. [^7]\n\nThe article highlights that MCP is becoming increasingly important for integrating AI capabilities with real-world applications. [^8]",
    "cited": "[{\"statement\":\"Researchers present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The CivBench environment spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The study uses CivBench to characterize agent behavior across four model families in 23 admissible runs.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The author, a frontend developer, explains the mechanics of how AI models utilize external tools.\",\"source\":\"medium.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T22:12:14.000Z\",\"publisher_count\":1,\"sources\":[\"medium.com\"]},{\"statement\":\"The Model Context Protocol (MCP) is introduced as a standard that enables AI models to connect to external tools and data sources.\",\"source\":\"medium.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T22:12:14.000Z\",\"publisher_count\":1,\"sources\":[\"medium.com\"]},{\"statement\":\"MCP facilitates the secure connection between AI models and various external resources to allow for data access and task execution.\",\"source\":\"medium.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T22:12:14.000Z\",\"publisher_count\":1,\"sources\":[\"medium.com\"]},{\"statement\":\"The article highlights that MCP is becoming increasingly important for integrating AI capabilities with real-world applications.\",\"source\":\"medium.com\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T22:12:14.000Z\",\"publisher_count\":1,\"sources\":[\"medium.com\"]}]",
    "kind": "news"
  },
  "receipt_verify": "Ed25519 over the dot-joined string `slice_hash.cursor_from.cursor_to.view.view_version.row_count`; public_key and sig are base64url of the raw 32-byte key / 64-byte signature",
  "receipt": null,
  "receipt_note": "this revision predates receipt-keeping (before v0.37.0); the filed row lives in the record",
  "generation_chain": {
    "wire": {
      "stream": "fountain_news",
      "story_id": "67b6d80067532869cd42280ea2e3fcf9",
      "thread_id": "89b788a990ef2bf3879a158ab98b5027",
      "thread_label": "Model Context Protocol",
      "novelty": "UPDATE",
      "content_hash": "e04f329ef5f3c5aea65db072ca6d48f1cf6b535b7a5c8253725d7743cd6947f4",
      "last_published_at": "2026-09-03T04:00:00.000Z",
      "read_receipt": {
        "slice_hash": "a6974819026a155e1c79c99aba73ab29d5f9d0aaa9cffb05e88a08023354a690",
        "cursor_from": "eyJ0cyI6IjIwMjYtMDktMDNUMDM6MzI6MTkuMDAwMDAwWiIsImlkIjoiNzMzZDYyYTFiNGQwMmJmNjYzNTk3YjhmN2JhZDBiZTIiLCJ2IjoiMSJ9",
        "cursor_to": "eyJ0cyI6IjIwMjYtMDktMDNUMDQ6MDk6MDAuMDAwMDAwWiIsImlkIjoiNjQ5MjI3ZDNmNWQyMGQ3NmI1ZTE1NGNhODNlMTI0ZTMiLCJ2IjoiMSJ9",
        "view": "v_fountain_news",
        "view_version": "1",
        "row_count": 100,
        "window_days": 3,
        "bytes_scanned": 12568115,
        "credits": 8,
        "price_per_100_rows": 8,
        "sig": "k4fkL1dHRNIJwSawY8K6wWBrTSdTIRM-buyZr56gcruiCoH5_IdJUeMzPH7d51ZTXAE0Qe6xSFoDys5UGTzsAw",
        "public_key": "bMUigy8O0jOnBxQ4Sc-5lwhIZ8LQVAhxMbR7qESVuUE",
        "signer_path": "lakehouse/data-extract/v1",
        "alg": "Ed25519",
        "signed": true
      }
    },
    "written_at": "2026-09-03T06:46:28.468Z"
  },
  "cited_facts": [
    {
      "statement": "Researchers present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol.",
      "source": "arXiv.org",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-03T04:00:00.000Z",
      "publisher_count": 1,
      "sources": [
        "arXiv.org"
      ]
    },
    {
      "statement": "The CivBench environment spans 300+ turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability.",
      "source": "arXiv.org",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-03T04:00:00.000Z",
      "publisher_count": 1,
      "sources": [
        "arXiv.org"
      ]
    },
    {
      "statement": "The environment exposes 76 MCP tools and a narration layer that converts visual game state into structured text.",
      "source": "arXiv.org",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-03T04:00:00.000Z",
      "publisher_count": 1,
      "sources": [
        "arXiv.org"
      ]
    },
    {
      "statement": "The study uses CivBench to characterize agent behavior across four model families in 23 admissible runs.",
      "source": "arXiv.org",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-03T04:00:00.000Z",
      "publisher_count": 1,
      "sources": [
        "arXiv.org"
      ]
    },
    {
      "statement": "The author, a frontend developer, explains the mechanics of how AI models utilize external tools.",
      "source": "medium.com",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-01T22:12:14.000Z",
      "publisher_count": 1,
      "sources": [
        "medium.com"
      ]
    },
    {
      "statement": "The Model Context Protocol (MCP) is introduced as a standard that enables AI models to connect to external tools and data sources.",
      "source": "medium.com",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-01T22:12:14.000Z",
      "publisher_count": 1,
      "sources": [
        "medium.com"
      ]
    },
    {
      "statement": "MCP facilitates the secure connection between AI models and various external resources to allow for data access and task execution.",
      "source": "medium.com",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-01T22:12:14.000Z",
      "publisher_count": 1,
      "sources": [
        "medium.com"
      ]
    },
    {
      "statement": "The article highlights that MCP is becoming increasingly important for integrating AI capabilities with real-world applications.",
      "source": "medium.com",
      "instrument": "News",
      "claim_key": null,
      "published_at": "2026-09-01T22:12:14.000Z",
      "publisher_count": 1,
      "sources": [
        "medium.com"
      ]
    }
  ],
  "note": "A signature proves who filed this and that it has not changed since. It never makes a claim true."
}