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.
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.
These headlines, in this order, are the entire world the models were given. Nothing else about North America on 2026-07-12 was in the prompt.
The usual picture of primate origins is warm, leafy and tropical: small tree-dwelling mammals evolving in forests where fruit, flowers and insects were.
Argan posts record Q1 FY27 revenue (+50%) and a $2.8B backlog. Click for more on AGX stock prospects.
Some 44 million Americans were under a heat wave warning on Saturday as temperatures in the Rocky Mountains and northern plains of the United States were...
TCS announces major leadership reshuffle across BFSI, verticals and markets, creating new business groups and units to drive AI, platforms and operations...
Weather cycle threatens harvests worldwide, adding to inflation already fuelled by the Iran war.
The Southwest's monsoon storms are set to bring much-needed rain but also risks of flash flooding, lightning and strong winds.
Celebrate the life of Michael Soland, leave a kind word or memory and get funeral service information care of The Settegast-Kopf Company@Sugar Creek.
2026 Eastern Pacific hurricane season is entering its most dangerous stretch: a tropical wave south of Mexico has reached 90% formation odds,...
New data reveals a single export spike generates an additional $202M for South Korea's retail, beauty, and tourism sectors while creating 3389 jobs.
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 9 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.
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.
The US faces multiple simultaneous climate-related stresses, including a major heat wave affecting 44 million people and heightened monsoon and hurricane risks, which could disrupt communities and infrastructure. While these are natural events rather than direct conflict, their scale warrants an elevated instability assessment, especially with potential global food price shocks adding economic pressure.
The United States faces moderate environmental and economic pressures, driven by a severe heat wave affecting millions and looming inflation from global food price shocks. Despite these compounding stressors and background geopolitical tensions, domestic institutions remain secure with no signs of civil unrest or systemic disruption.
The US faces multiple concurrent environmental stressors including a significant heat wave affecting 44 million Americans, active hurricane formation in the Eastern Pacific, monsoon risks in the Southwest, and broader climate pressures from a potential 'super' El Niño that could impact food prices through 2028. However, these are primarily natural disasters and economic pressures rather than indicators of political instability, civil unrest, or systemic governance failure, keeping the score in the elevated but not severe range.
The evidence is dominated by weather and climate hazards — a record-threatening heat wave affecting 44 million Americans, monsoon flash flooding risk in the Southwest, and an active Eastern Pacific hurricane season — alongside inflation pressure from an El Niño food price shock and a referenced Iran war. There are no indications of domestic political violence, unrest, or institutional breakdown, so the picture is one of manageable environmental and economic strain rather than systemic instability.
The US is experiencing a heat wave that could break records, and there are warnings of potential flash flooding and strong winds with the arrival of the monsoon season, indicating some level of instability. However, the economic news, such as Argan's record revenue and the boost from K-pop's export boom, suggests that the overall situation is not critical, thus warranting an elevated but not severe chaos score.
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.