A modeled public · United States + world

Model how public reaction could move.

Pheme is a simulation—not a poll. Ask a question, test a scenario, and inspect how modeled reactions vary by place.

How Pheme builds a resultIllustrative flow · not live data
01
Observed context

Named public demographic and geographic inputs.

02
Your input

A question or explicitly hypothetical scenario.

03
Modeled response

Estimated patterns, shown with sources and limits.

Process diagram only. It shows no observed opinion, geography, or result.

Validation scopeLoading scorecard…Issue count, run count, and holdout status loading…
Issue average errorLoading…
Worst issue missLoading…
Artifact identityProvider/model and manifest loading…

Choose your instrument

Four ways into the signal.

Start with a task. Method and supporting detail stay close without blocking the work.

Observed versus modeled

A model earns trust by showing the miss.

Pheme publishes its committed validation set, source links, average error, and worst result. Direction can be useful while an exact percentage is still wrong. This is a simulation, not a poll.

Inspect every benchmark and source →
Observed pollModeled simulation

Loading the committed scorecard…

Issue count, run count, holdout status, and artifact identity loading…

Current brief

Read the source. Then inspect the signal.

Loading the latest sourced stories…

Open the full news and evidence desk →
1Input

A question, sourced story, bill, or hypothetical scenario.

2Model

Deterministic geography plus bounded synthetic-persona reasoning.

3Inspect

Result, sources, version, limitations, and validation together.

Read the full method →