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 61–80 of 153

Tower Research Capital
Quantitative Trader Researcher Summer Intern Graduates
Held outSep 1, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Hudson River Trading
Hardware Design Engineer Grads
Held outAug 31, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Hudson River Trading
Hardware Engineer Intern Summer
Held outAug 31, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
IMC
Quant Performance Engineer Intern Summer
Held outAug 27, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Flow Traders
Junior Quantitative Researcher
Held outAug 25, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Jump Trading
AI ML Researcher Intern
Held outAug 24, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Databricks
Software Engineering Intern Start Winter
Held outAug 20, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
SpaceX
New Grad Engineer Software Starship
Held outAug 19, 2026exactexact
Latest backtest held out another posting of this role that year
Notion
Data Science Intern Winter
Held outAug 19, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Tower Research Capital
Quantitative Developer Intern
Held outAug 18, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Anduril
Systems Engineer
Held outAug 18, 2026exactexact
Not in the latest backtest run
Datadog
Product Management Intern
Held outAug 17, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Notion
Software Engineer Intern Winter
Held outAug 14, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Applied Intuition
Research Engineer New Grad
Held outAug 14, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Notion
Software Engineer New Grad Dec
Held outAug 14, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Notion
Software Engineer Intern Summer
Held outAug 14, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
Applied Intuition
Software Engineer New Grad December
Held outAug 14, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
DRW
Software Engineer Intern Data Engineering
Held outAug 13, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
IMC
Software Engineer Intern
Held outAug 12, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff
IMC
Quantitative Research Intern
Held outAug 12, 2026exactexact
Skipped in the latest backtest
no temporal evidence was available by the forecast cutoff

Choose the historical vantage point

Tower Research Capital · Quantitative Trader Researcher Summer Intern Graduates · held out Sep 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.