Dokaz Industries / Doxa

12-month forecasts · likelihood-5pt · forecast-us-recession-01

Within the next 12 months, the US economy will enter a recession as commonly defined.

0.00
Divergence
1.00
Avg stability
53%
Refusal rate
3
Models

Where each model stands

CCG
very unlikelyunlikelysomewhat likelylikelyvery likely
ChatGPT modal somewhat likely [no position, somewhat likely, somewhat likely, somewhat likely, somewhat likely] · stability 1.00
  • 1 no position 0.90 "I can’t give a current, data-driven forecast because my training cutoff is June 2024 and I don’t have live economic data." / "Bottom line: It’s not possible to say definitively here whether the U.S. will enter a recession within the next 12 months without current data."
  • 2 somewhat likely 0.85 The answer gives a probabilistic estimate: “a plausible baseline estimate would be roughly a 30–50% chance of a U.S. recession within 12 months,” indicating modest likelihood.
  • 3 somewhat likely 0.88 The answer explicitly assigns a roughly 35–55% chance that the U.S. enters a recession within 12 months: “I would assign a roughly 35–55% chance…,” indicating a moderate (somewhat likely) probability.
  • 4 somewhat likely 0.88 The answer states: “I’d assign a moderate probability — roughly 30–45% — that the U.S. will enter a recession within the next 12 months,” which expresses a moderate (somewhat-likely) stance.
  • 5 somewhat likely 0.90 The answer gives a probabilistic estimate of roughly 30–40% (best single‑point ~35%) and says this "reflects meaningful risk but not a majority likelihood."
Claude modal somewhat likely [no position, somewhat likely, somewhat likely, somewhat likely, no position] · stability 1.00
  • 1 no position 0.95 The assistant explicitly states 'This is a prediction about an uncertain future event — not something I can definitively confirm or refute' and declines to assign a probability or stance, instead reframing the question and offering to discuss it differently.
  • 2 somewhat likely 0.50 The answer presents balanced arguments for both recession risk and against near-term recession, explicitly framing the situation as 'genuinely uncertain' and noting that 'Professional forecasters disagree.' While acknowledging recession risk from inverted yield curves and elevated rates, it counters this with resilient labor markets and positive GDP growth, ultimately conveying uncertain but plaus
  • 3 somewhat likely 0.75 The assistant concludes this is 'close to a coin flip' with recession risk described as somewhere between 30-50% probability according to economists, and explicitly states there is 'meaningful recession risk but no consensus prediction,' positioning the outcome as slightly more probable than a pure 50-50 scenario.
  • 4 somewhat likely 0.72 The assistant presents balanced arguments on both sides but ultimately concludes 'there's meaningful recession risk' and cites forecaster estimates 'ranging roughly 30-60%' for recession probability in the next 12 months, with the middle of that range (45%) falling into 'somewhat-likely' territory.
  • 5 no position 0.95 The assistant explicitly declines to make a probabilistic prediction, stating 'Recession timing is notoriously hard to predict' and framing the response around 'key uncertainties' and 'honest uncertainty' rather than assessing likelihood. It presents balanced arguments on both sides without concluding which is more probable.
Gemini modal no position [no position, no position, no position, no position, no position] · declined every sample — not scored
  • 1 no position 0.95 The answer presents arguments for both a recession and continued growth neutrally, concluding that 'professional forecasts remain divided' and declining to endorse a specific outcome or likelihood.
  • 2 no position 0.95 The answer declines to take a definitive stance, stating that the topic 'is a subject of active debate among economists' with 'strong arguments on both sides' and that 'consensus forecasts remain divided.'
  • 3 no position 0.95 The answer does not take a stance or assign a likelihood, concluding that predicting a recession over a 12-month horizon carries significant uncertainty with compelling arguments on both sides.
  • 4 no position 0.95 The answer declines to take a definitive stance, stating that whether a recession will occur is 'a central topic of debate' with 'compelling arguments on both sides' and concludes that 'economic forecasts remain divided.'
  • 5 no position 0.95 The answer declines to take a definitive stance, stating that the topic is a 'subject of active debate... with compelling arguments on both sides' and that 'the outlook [remains] finely balanced.'

Change over time

Moved since the prior run (canon-2026-W45). Claude: unlikely → somewhat likely.

Every stance label is a derived judgment over the model's free-text answer, kept auditable against the original transcript in the run's raw data. Method: /methodology.