Historical model audit

Forecast Replay

Return to a historical cutoff and reconstruct what 1stSeen could have predicted, using only the evidence it held by then. Every run is computed by the worker’s leak-safe backtest when you ask for it.

Future evidence is sealed

The held-out opening and every post-cutoff observation are scoring data only. They cannot enter the forecasting component.

What can be replayed

Held-out targets with a defensible actual interval

Roles with two or more recorded openings: 179
Excluded: only observed-by evidence: 26
Replay candidates: 153
held out on an exact opening: 153
held out on a bounded opening: 0

An archive capture proves a role was visible by then, not that it opened then, so an observed-by opening is never scored as ground truth.

Latest backtest

Why targets could not be scored

Finished Oct 3, 2026 · cutoff 60 days before each target · 890 targets, 0 scored, 890 skipped

no temporal evidence was available by the forecast cutoff689
held-out opening is observed-by only and has no scoreable actual interval201

Counted over every reconstructed cycle the backtest evaluated, which is more than the replay candidates above. Reasons are the backtest’s own words.

Choose a held-out target

Showing 121–140 of 153

IMC
Graduate Machine Learning Researcher Chicago
Held outJul 1, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Optiver
Quantitative Intern Summer
Held outJul 1, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
IMC
Graduate Hardware Engineer
Held outJul 1, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
IMC
Quantitative Research Intern BS MS Summer
Held outJul 1, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Virtu Financial
Intern Quantitative Trading
Held outJul 1, 2026exactexact
Not in the latest backtest run
IMC
Hardware Engineer Intern Summer
Held outJul 1, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
IMC
Graduate Quantitative Trader
Held outJul 1, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Forward Deployed Software Engineer New Grad US Government
Held outJun 15, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Anduril
Manufacturing Engineer Intern
Held outJun 11, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Forward Deployed Software Engineer Intern US Government
Held outMar 10, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Flow Traders
Graduate Trader
Held outJan 30, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Nuro
Software Engineer AI Platform New Grad
Held outOct 22, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Nuro
Software Engineer AI Platform Intern
Held outOct 22, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Software Engineer New Grad Infrastructure
Held outAug 19, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Product Designer Intern US Government
Held outAug 12, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Forward Deployed Software Engineer Intern UK Government
Held outAug 1, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Forward Deployed Software Engineer New Grad Commercial
Held outAug 1, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Software Engineer New Grad Infrastructure
Held outJun 26, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Software Engineer New Grad Infrastructure
Held outJun 26, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Palantir
Software Engineer New Grad
Held outJun 19, 2025exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff

Choose the historical vantage point

IMC · Graduate Machine Learning Researcher Chicago · held out Jul 1, 2026 exact

Forecast cutoff

Why targets could not be scored

Finished Oct 3, 2026 · cutoff 60 days before each target · 890 targets, 0 scored, 890 skipped

no temporal evidence was available by the forecast cutoff689

held-out opening is observed-by only and has no scoreable actual interval201

Counted over every reconstructed cycle the backtest evaluated, which is more than the replay candidates above. Reasons are the backtest’s own words.