ChaosWatch
New here? Start here →
Evidence inspector

Sub-Saharan Africa · 2026-07-10

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
820b6bb605e84cb46de4e7a77807ff64c16e75855afcad1901a4be92888a62ff

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 2026-07-10 was in the prompt.

09

The Short Happy Life of Francis Macomber

The Short Happy Life of Francis Macomber, short story by Ernest Hemingway, first published in Cosmopolitan in 1936, collected in The Fifth Column and the...

britannica.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 20.0 points of the 0-100 scale.

deepseek-reasoner
deepseek
58.0
okUnstable

Sub-Saharan Africa faces elevated instability due to external economic shocks from the Iran war, including fuel and LPG supply disruptions that harm clean energy goals and raise costs, while heavy debt burdens divert resources from education and infrastructure. Although renewable energy deals and startup investments signal some resilience, these pressures combined with global peace decline suggest a precarious situation.

evidence 820b6bb605e8…prompt p1
gemini-3.1-pro-preview
google
48.0
okUnstable

Sub-Saharan Africa faces mounting economic pressures as severe debt burdens force governments to prioritize loan repayments over essential services like education. Additionally, external shocks from Middle Eastern conflicts are disrupting vital fuel supplies, though ongoing investments in green energy and tech startups provide some economic resilience.

evidence 820b6bb605e8…prompt p1
claude-haiku-4-5
anthropic
42.0
okElevated

Sub-Saharan Africa faces mounting economic pressures from external shocks (Iran-related energy disruptions affecting oil and LPG supplies), compounded by structural debt burdens that are crowding out social spending and limiting government capacity. However, concurrent positive developments in renewable energy investment and fintech innovation suggest adaptive capacity and economic diversification efforts that partially offset these destabilizing factors, preventing a higher severity classification at this moment in time.

evidence 820b6bb605e8…prompt p1
llama-3.3-70b-versatile
groq
40.0
okElevated

The region is experiencing elevated instability due to potential disruptions in the Strait of Hormuz, which could impact oil-importing economies in sub-Saharan Africa, and the strain of debt repayment on education and infrastructure development. However, the presence of initiatives such as green power supply agreements, AI-driven telco tower optimization, and investments in African startups suggests that the region is also making efforts to adapt and innovate, preventing the situation from escalating further.

evidence 820b6bb605e8…prompt p1
claude-opus-5
anthropic
38.0
okElevated

The evidence points to compounding economic stress rather than active violence in sub-Saharan Africa: external fuel shocks from Strait of Hormuz disruptions threaten oil-importing economies and clean cooking programs, while debt servicing crowds out education spending and a major metro scrambles to clear $146 million in arrears. Offsetting signals include renewable energy deals, telecom investment, and startup funding, and no headlines report armed conflict or state collapse in the region on this date.

evidence 820b6bb605e8…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.