●ChaosWatch
New here? Start here →
Evidence inspector

Sub-Saharan Africa · 2026-07-12

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
90ae8eedd611763559066fadcf454f1cda78e523d57149b426c9ff3b6312bb18

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 2026-07-12 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 6.0 points of the 0-100 scale.

deepseek-reasoner
deepseek
62.0
okUnstable

The region faces escalating violent extremism in the Sahel and economic shocks from Gulf hostilities, compounded by governance weaknesses and electoral tensions in key countries. While these factors indicate significant instability, the absence of a region-wide acute crisis keeps the score below severe thresholds.

evidence 90ae8eedd611…prompt p1
gemini-3.1-pro-preview
google
62.0
okUnstable

Escalating arms trafficking and violent extremism in the Sahel, combined with severe economic spillovers from Gulf hostilities affecting food and energy security, drive regional instability. While diplomatic engagements like the SADC ministerial meetings provide some resilience, systemic governance weaknesses and early electoral tensions in Kenya maintain an unstable environment.

evidence 90ae8eedd611…prompt p1
llama-3.3-70b-versatile
groq
60.0
okUnstable

The region is experiencing elevated instability due to the rise of violent extremist organizations, arms trafficking, and the potential for conflict escalation, as evidenced by the headlines on the Sahel region and the impact of the Iran war on Africa. However, the presence of diplomatic efforts, such as the meeting of SADC Water and Energy Ministers, and the focus on governance and development in countries like Nigeria, suggest that the situation is not yet at a critical point.

evidence 90ae8eedd611…prompt p1
claude-haiku-4-5
anthropic
58.0
okUnstable

Sub-Saharan Africa faces multiple overlapping destabilizing factors including escalating Sahel extremism fueled by arms trafficking, foreign military recruitment (African fighters in Russia), governance weaknesses in Nigeria, and pre-election tensions in Kenya, alongside economic pressures from regional conflicts and climate impacts. While no single crisis reaches critical levels, the combination of armed group proliferation, political fragility, and external interference creates sustained instability across the region without immediate signs of resolution or de-escalation.

evidence 90ae8eedd611…prompt p1
claude-opus-5
anthropic
56.0
okUnstable

Evidence points to entrenched Sahel insecurity driven by arms trafficking and violent extremist groups, African recruits caught in the Russia-Ukraine war, and warnings of pre-election tension in Kenya, alongside fiscal strain and food/energy shocks transmitted from renewed Gulf hostilities. However, the day's reporting is largely analytical rather than describing new mass-casualty events or state collapse, and includes routine regional cooperation and governance items, keeping the score in the unstable rather than severe range.

evidence 90ae8eedd611…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.