●ChaosWatch
New here? Start here →
Evidence inspector

North America · 2026-07-07

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.

Region
Asia-PacificEuropeMiddle East & North AfricaSub-Saharan AfricaNorth America
Depth profile
shallow
Date
2026-07-122026-07-112026-07-102026-07-092026-07-082026-07-072026-07-062026-07-052026-07-042026-07-032026-07-022026-07-012026-06-302026-06-292026-06-282026-06-272026-06-262026-06-25
Evidence hash
ed1bb9229c61c3d8f932d16acdd3fa5dc97b1f9d4359bc5c84ca7eeb806e0ba0

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 2026-07-07 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 18.0 points of the 0-100 scale.

claude-haiku-4-5
anthropic
28.0
okStable

The evidence shows routine business activity across energy, technology, and automotive sectors with no indicators of domestic instability or conflict. The only geopolitical element is a US sanctions action against Iran, which is a standard foreign policy tool rather than evidence of internal US chaos or crisis conditions on this date.

evidence ed1bb9229c61…prompt p1
gemini-3.1-pro-preview
google
20.0
okStable

The domestic environment remains highly stable, characterized by routine corporate acquisitions, academic initiatives, and advancements in the renewable energy sector. While the revocation of an Iranian oil license following tanker attacks introduces minor geopolitical and economic friction, it poses no immediate threat to internal United States stability.

evidence ed1bb9229c61…prompt p1
claude-opus-5
anthropic
19.0
okStable

The overwhelming majority of the evidence concerns routine domestic business activity—energy acquisitions, university-industry partnerships, renewables data, and a corporate emergence from Chapter 11—indicating normal institutional and economic functioning within the US. The only destabilizing signal is external: renewed US sanctions enforcement against Iranian oil amid reported Strait of Hormuz tanker attacks, which lifts crude prices and introduces modest energy-market and geopolitical risk without evidence of domestic disruption.

evidence ed1bb9229c61…prompt p1
deepseek-reasoner
deepseek
15.0
okStable

The headlines focus on corporate energy deals, academic partnerships, and renewable energy developments, indicating normal economic and industrial activity. The only geopolitical item, US blocking Iranian oil sales, raises energy prices but does not indicate domestic chaos or instability.

evidence ed1bb9229c61…prompt p1
llama-3.3-70b-versatile
groq
10.0
okStable

The region is experiencing economic and technological advancements, with partnerships and acquisitions in the energy sector, such as Clemson's partnership with BMW and Marubeni's acquisition of EagleRidge Energy, indicating a stable business environment. However, the rise in crude prices due to the US blocking Iran from selling oil and reports of tanker attacks in the Strait of Hormuz introduce a minor note of instability, preventing a perfect score.

evidence ed1bb9229c61…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.