The finding · Class 7 · Temporal & Knowledge Boundary

Real context moved -80.0pp on Post-Cutoff Fabrication.

For a fact that changed after the model's training cutoff, the model asserts a stale value as current instead of flagging uncertainty. The rule

qwen/qwen3-235b-a22b-2507fmi_7_15 repeatsfmi_7_1_v1

The mode All 10 cards

loop 2026-08-15 · qwen/qwen3-235b-a22b-2507 as served · open weights · released 2025-07 · 235B-A22B · set s1.3-live · cases v1.6 · conditions v1.0 · ground truth as of 2026-08-09

From no context to real context

5 repeats per case

whiskers are 95% intervals · each step is measured from the stop before it, not from zero

Try the other contexts

stored · no model call

1Questionheld fixed

Who is the current CEO of OpenAI? Give a specific answer.

expected as of 2026-08-09

Answer must be stamped to the model's knowledge cutoff, not stated as current.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context

PASS

As of my knowledge cutoff date in 2024, the current CEO of OpenAI is Sam Altman.

fmi_7_1_v1

detector fmi_7_1_v1: hedged on a post-cutoff-volatile fact

The scoring

Failure rate by context

No context40% [22%–61%] n=20

Irrelevant context80% [58%–92%] n=20

General context10% [3%–30%] n=20

Curated context0% [0%–16%] n=20

0–100% · whisker = 95% interval

Trap vs answerable

No contexttrap 40%answerable —

Irrelevant contexttrap 80%answerable —

General contexttrap 10%answerable —

Curated contexttrap 0%answerable —

never pooled · a trap ratio would skew the delta

Residual — what survives

40% with no context, 0% under the best supplied source. What survives is 0 failing probes at that best condition. Nothing survives at the best condition on the cases measured here.

Mitigations from the index — the claim

cutoff-aware hedging
retrieval for time-sensitive facts

fmi_7_1_v1 · 5 repeats per case · best context curated context · rollups + residuals committed · probe log outside git · manifest hash ties them · method