{
  "forecast_date": "2026-09-18",
  "deadline": "2026-12-18T23:59:59-05:00",
  "evidence_cutoff": "2026-09-18T12:00:49Z",
  "reviewed_through": "2026-09-18T12:00:49Z",
  "rules": [
    "Probabilities are rough subjective judgments, not market prices or fitted estimates. Events overlap and are correlated; they do not sum to 100%.",
    "Only actions after the as-of date count. Existing announcements or promises alone do not resolve a forecast positively.",
    "Preserve these forecasts unchanged. Record updates and eventual resolutions separately with dated public evidence.",
    "Absence of accessible evidence is not proof that a private action did not happen. Forecasts are deliberately about public announcements, documents or observable conduct.",
    "A forecast outcome tests the stated behavioral expectation. It does not establish the underlying motive; several motives produce the same behavior."
  ],
  "camps": [
    {
      "id": "frontier_labs",
      "name": "Frontier labs: Anthropic and OpenAI",
      "predictions": [
        {
          "id": "LAB-1",
          "probability": 0.75,
          "claim": "At least one of Anthropic or OpenAI publicly establishes a named arrangement for embedded external evaluation with concrete access and disclosure terms.",
          "resolution": "An agreement, published terms or confirmation that access is operating counts. Repeating the September promise does not."
        },
        {
          "id": "LAB-2",
          "probability": 0.85,
          "claim": "Both companies launch or substantially expand paid model or agent products before binding industry-wide pacing restrictions take effect.",
          "resolution": "A public new release or substantial expansion at each company, after September 18 and before any binding industry-wide pacing regime. This is compatible with their stated proposals and is not itself evidence of hypocrisy."
        }
      ]
    },
    {
      "id": "expansion_companies",
      "name": "Expansion businesses: Nvidia and Meta",
      "predictions": [
        {
          "id": "EXP-1",
          "probability": 0.75,
          "claim": "Nvidia announces a new funded initiative, product or government partnership for AI security, monitoring or defensive use without endorsing a general frontier slowdown.",
          "resolution": "A new identifiable programme, resource commitment, product or agreement counts. A speech about engineering safety alone does not."
        },
        {
          "id": "EXP-2",
          "probability": 0.8,
          "claim": "Meta expands public access to an agent or advanced model and issues a new public objection to general pacing requirements.",
          "resolution": "Both a new substantive availability/capability expansion and a new attributable policy statement or lobbying position must occur. Existing Muse availability and the August essay are the baseline."
        }
      ]
    },
    {
      "id": "evaluators",
      "name": "Independent evaluators, including METR",
      "predictions": [
        {
          "id": "EVAL-1",
          "probability": 0.7,
          "claim": "METR or another named frontier evaluator publishes new formal proposals or agreement terms requiring incident disclosure, sustained access or freedom to publish findings.",
          "resolution": "A concrete new protocol, contract term, standards submission or policy proposal counts; generic calls for transparency do not."
        },
        {
          "id": "EVAL-2",
          "probability": 0.6,
          "claim": "A named independent evaluator publishes new empirical results that narrow a prominent claim about dangerous capability, autonomous research or productivity.",
          "resolution": "The report must identify a measured limitation or place a named system below a stated risk threshold. Merely saying evidence is uncertain, or republishing an older reassuring result, does not count."
        }
      ]
    },
    {
      "id": "pause_campaigners",
      "name": "Pause campaigners and organised safety advocacy",
      "predictions": [
        {
          "id": "PAUSE-1",
          "probability": 0.75,
          "claim": "A new formal coalition or joint campaign joins an AI-pause organisation with a labour, religious or child-protection organisation around restrictions on advanced AI development.",
          "resolution": "A new co-signed intervention or organised joint campaign counts. Recounting attendance at the September 15 assembly does not."
        },
        {
          "id": "PAUSE-2",
          "probability": 0.55,
          "claim": "At least one materially qualified or corrected technical claim is subsequently repeated in a stronger form by two identifiable pause-campaign leaders or organisations.",
          "resolution": "Preserve the primary clarification and two later statements. The discrepancy must concern autonomy, actual harm or imminence, with no new supporting evidence. Conditional concern about possible future harm does not count; random followers do not count. This tests transmission accuracy, not clinical delusion or intentional lying."
        }
      ]
    },
    {
      "id": "trump_sacks",
      "name": "Trump, Sacks and the administration's acceleration position",
      "predictions": [
        {
          "id": "ADMIN-1",
          "probability": 0.8,
          "claim": "The administration does not endorse legally binding general limits on the pace of frontier training or model releases by the deadline.",
          "resolution": "Targeted restrictions on particular harmful uses, actors or foreign access do not count as general pacing. An explicit official endorsement of a binding general cap resolves this forecast negatively."
        },
        {
          "id": "ADMIN-2",
          "probability": 0.75,
          "claim": "The administration announces a new concrete AI-security, infrastructure or government-access initiative with industry partners.",
          "resolution": "A signed agreement, order, procurement decision or funded programme counts. A promise of American dominance or an unresourced speech does not."
        }
      ]
    },
    {
      "id": "economic_populists",
      "name": "Economic populists: Sanders and Warren",
      "predictions": [
        {
          "id": "POP-1",
          "probability": 0.65,
          "claim": "Sanders or Warren advances a new legislative amendment, package or formal platform connecting AI governance to worker compensation, working hours, bargaining power or ownership.",
          "resolution": "The action must add a provision, legislative vehicle or joint commitment beyond the existing September proposals. Repeating the current workweek bill in an interview does not count."
        },
        {
          "id": "POP-2",
          "probability": 0.6,
          "claim": "A national labour or consumer organisation newly endorses an advanced-AI pause or permission requirement promoted by this political camp.",
          "resolution": "A formal new organisational endorsement of the development restriction counts. General support for worker protection or safer chatbots is insufficient."
        }
      ]
    },
    {
      "id": "pragmatic_oversight",
      "name": "Pragmatic oversight: Shapiro and bipartisan legislators",
      "predictions": [
        {
          "id": "PRAG-1",
          "probability": 0.75,
          "claim": "A congressional committee holds an AI oversight hearing or advances legislation specifically addressing incident reporting, independent evaluation or development security.",
          "resolution": "A held hearing, markup or recorded committee advancement counts. Another letter asking for action does not."
        },
        {
          "id": "PRAG-2",
          "probability": 0.6,
          "claim": "Pennsylvania adds a binding AI procurement, operational-safety or data-centre condition while continuing to back a named new AI investment or deployment.",
          "resolution": "Both a new enforceable condition and a new identifiable state-backed investment/deployment must appear. A speech alone is insufficient; the previous August data-centre order is the baseline."
        }
      ]
    },
    {
      "id": "chinese_open_builders",
      "name": "Chinese open-model developers: DeepSeek, Moonshot and Z.ai",
      "predictions": [
        {
          "id": "OPEN-1",
          "probability": 0.85,
          "claim": "At least one of DeepSeek, Moonshot or Z.ai releases new downloadable model weights or general agent tooling explicitly promoted as improving cost, access or performance.",
          "resolution": "A usable new release after September 18 counts. A benchmark tease, an old release gaining attention or an announcement with no accessible artifact does not."
        },
        {
          "id": "OPEN-2",
          "probability": 0.8,
          "claim": "None of these three developers publicly joins a binding, independently verifiable international agreement limiting frontier training or release cadence by the deadline.",
          "resolution": "A general statement supporting safety or international cooperation is not such an agreement. Public accession to concrete reciprocal limits with a verification mechanism resolves this forecast negatively."
        }
      ]
    }
  ],
  "methods": {},
  "updates": []
}