ChaosWatch
New here? Start here →
Evidence inspector

North America · 2026-07-02

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
2fc6c039842e33ce45f16373b50bf4e9fcbf3fe0cd470dc2889b30ab4b8a7c29

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 2026-07-02 was in the prompt.

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 17.0 points of the 0-100 scale.

claude-haiku-4-5
anthropic
32.0
okElevated

The US faces a missed trade deal deadline with Mexico and Canada that triggers a decade-long renegotiation process, creating economic uncertainty in a critical regional partnership. However, this is offset by positive developments in energy infrastructure investment and nuclear capacity expansion, while isolated weather threats and international incidents do not directly destabilize the domestic situation on this date. The evidence suggests manageable economic friction rather than systemic instability, warranting an elevated but not severe assessment of chaos risk for the US region on July 2, 2026.

evidence 2fc6c039842e…prompt p1
gemini-3.1-pro-preview
google
30.0
okElevated

The expiration of a key North American trade deal deadline introduces long-term economic uncertainty, though immediate disruptions remain minimal. Meanwhile, an impending super typhoon threatening the U.S. Northern Mariana Islands presents a localized but significant natural disaster risk, slightly elevating overall instability.

evidence 2fc6c039842e…prompt p1
claude-opus-5
anthropic
27.0
okElevated

The main destabilizing signal is trade policy: the USMCA renewal deadline lapsed and the administration formally started a withdrawal clock, injecting real economic and diplomatic uncertainty across North America, while a potential super typhoon threatens the U.S. Northern Mariana Islands and cyber-threat concerns tied to Iran are noted. Otherwise the evidence is dominated by routine business, energy investment, aviation and World Cup coverage, indicating no violence, unrest, or institutional breakdown.

evidence 2fc6c039842e…prompt p1
llama-3.3-70b-versatile
groq
20.0
okElevated

The region is experiencing a mix of economic and trade developments, including a missed deadline for a North American trade deal and significant investments in energy solutions, which may lead to some instability. However, the overall tone of the headlines suggests a sense of ongoing activity and adaptation, rather than outright crisis or conflict, warranting an elevated but not severe chaos score.

evidence 2fc6c039842e…prompt p1
deepseek-reasoner
deepseek
15.0
okStable

The evidence shows routine economic and political developments, with the trade deal expiration starting a multi-year process rather than an immediate crisis. A potential typhoon in the Northern Mariana Islands is a localized natural hazard, not indicative of broader national instability.

evidence 2fc6c039842e…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.