●ChaosWatch
New here? Start here →
Evidence inspector

Sub-Saharan Africa · 2026-06-30

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
e5e3ebe9a4d1fbefa108df5c8becb11fa898e40c824608cc50bc06c887b1b50b

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 Sub-Saharan Africa on 2026-06-30 was in the prompt.

08

The Global Polytunity

Polycrisis or polytunity? How global disruptions can spark inclusive transformation and a new adaptive, moral political economy.

worldpeacefoundation.org

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
68.0
okUnstable

The region faces compounding pressures from conflict and governance failures that deter investment, while global conflicts and climate shocks threaten economic stability and push millions toward poverty. Food insecurity and fiscal constraints further undermine resilience, though no single event indicates an immediate collapse.

evidence e5e3ebe9a4d1…prompt p1
claude-haiku-4-5
anthropic
52.0
okUnstable

Sub-Saharan Africa faces multiple overlapping pressures including climate shocks, food insecurity affecting millions, governance failures deterring investment, and economic constraints limiting vehicle sales and infrastructure development. While the region demonstrates resilience through informal economic systems and ongoing development initiatives, the combination of environmental stress, poverty risks, and institutional weaknesses creates significant instability without immediate crisis indicators of armed conflict or state collapse at scale across the region on this date.

evidence e5e3ebe9a4d1…prompt p1
gemini-3.1-pro-preview
google
48.0
okUnstable

Chronic governance failures, climate shocks, and rising fuel costs are stifling foreign investment and exacerbating food insecurity across the region. While international development initiatives are expanding electricity access and agricultural support, the looming threat of millions falling into poverty keeps regional instability at a concerning level.

evidence e5e3ebe9a4d1…prompt p1
claude-opus-5
anthropic
46.0
okElevated

The day's evidence is dominated by structural and economic stressors—food insecurity, informal-economy dependence, climate shocks, fuel-cost inflation from the Iran conflict, and investment-deterring governance and security failures—rather than any acute crisis or active escalation. These chronic pressures, plus warnings that over 40 million people could be pushed back into poverty, keep the region above a calm baseline without indicating imminent breakdown in the shallow evidence provided.

evidence e5e3ebe9a4d1…prompt p1
llama-3.3-70b-versatile
groq
40.0
okUnstable

The region is experiencing various challenges including conflict, governance failures, climate shocks, and food insecurity, which are stifling investment and threatening to push people back into poverty. However, there are also efforts underway to address these issues, such as the World Bank's Mission 300 and initiatives to support women farmers, which suggest that the situation is not yet catastrophic.

evidence e5e3ebe9a4d1…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.