ChaosWatch
New here? Start here →
Evidence inspector

North America · 2026-06-28

The receipts. This is the exact material every model was shown for this day and region, followed by what each of them made of it — in its own words, next to the number it gave.

It is worth reading once even if you skip everything else: it is where confident-sounding reasoning and a score that turns out to be no better than chance sit side by side.

Why the evidence is identical, and how you can check

Evidence is gathered once per (date, region, depth_profile), hashed, and reused for every model in the run. A disagreement below is therefore a disagreement about identical input, not two models getting different search results. The evidence hash shown on this page is what makes that checkable.

Evidence hash
ab2fd91aadcae3b76b60722cf4c85b281e1654c2f6137295819f88d27650a684

SHA-256 over the canonically serialised payload minus the hash itself, so it is stable across processes and machines. It is stored on the run and on every score row below — provenance is checkable, not asserted. Every score row below carries this same hash.

Source material · 10

shallow

These headlines, in this order, are the entire world the models were given. Nothing else about North America on 2026-06-28 was in the prompt.

08

Nordex Group scores 325 MW order in the US

Nordex SE/ Key word(s): Incoming OrdersNordex Group scores 325 MW order in the US29.06.2026 / 07:30 CET/CESTThe issuer is solely responsible for the content...

tradingview.com

Extracts: not gathered at shallow depth — Stage 7 populates extracts only for standard and deep profiles. Zero here means "not requested", not "requested and empty". Full article texts: not gathered at shallow depth — only the deep profile fetches them.

The shallow profile requests 20 headlines and 10 are stored. That is a known provider cap, not a clipped payload: the Serper news endpoint returns at most 10 items per request regardless of the count asked for, and pagination has not been added. The three profiles currently differ in enrichment, not in headline breadth.

Model rationales

prompt p1

Same headlines, same rendered prompt, different readings. Where two models diverge, the disagreement is about interpretation, because the input was byte-identical and the hash proves it. The scored verdicts here span 28.0 points of the 0-100 scale.

deepseek-reasoner
deepseek
38.0
okElevated

The evidence shows moderate geopolitical and economic tensions, including USMCA renewal uncertainty and a new US military drone deployment near China, which could destabilize regional stability. However, most headlines concern routine energy, economic, and World Cup reporting, with no immediate signs of acute crisis.

evidence ab2fd91aadca…prompt p1
claude-haiku-4-5
anthropic
28.0
okStable

The evidence reflects routine economic and political developments including energy trade discussions, trade agreement review processes, and sports/climate commentary, with no indicators of acute instability or conflict. The deployment of reconnaissance drones near China and USMCA renewal uncertainty represent normal geopolitical and trade dynamics rather than destabilizing crises affecting the US directly on this date.

evidence ab2fd91aadca…prompt p1
gemini-3.1-pro-preview
google
25.0
okElevated

The region exhibits general stability, with major events centered around routine economic developments, the 2026 World Cup, and energy infrastructure investments. However, minor geopolitical and economic frictions exist due to uncertainty surrounding the USMCA trade agreement renewal and the strategic deployment of reconnaissance drones near China.

evidence ab2fd91aadca…prompt p1
claude-opus-5
anthropic
19.0
okStable

The evidence is dominated by routine economic, energy, sports and business coverage, with no indication of violence, unrest, or institutional breakdown within the US. Mild elevation is warranted only for trade-policy uncertainty around the July 1 USMCA review and a modest military signaling item involving drone deployments near China.

evidence ab2fd91aadca…prompt p1
llama-3.3-70b-versatile
groq
10.0
okStable

The provided evidence does not indicate any significant instability or chaos in the region, with most headlines focusing on economic and environmental issues rather than conflict or unrest. The deployment of RQ-4 Long Range Recon Drones near China and uncertainty surrounding the USMCA renewal are notable, but do not currently suggest a high level of chaos.

evidence ab2fd91aadca…prompt p1

Every model returned a parseable verdict for this evidence, so no failure card is shown. Non-ok rows are rendered by the same component — with error_text where the rationale would be — and are covered by tests/rationale_card_test.tsx.