The finding · Class 7 · Temporal & Knowledge Boundary

Real context moved -100.0pp 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

google/gemini-2.5-flash-litefmi_7_15 repeatsfmi_7_1_v1

The mode All 3 cards

loop 2026-08-15 · google/gemini-2.5-flash-lite as served · closed weights · released 2025-07 · set s1.1-live · cases v1.3 · 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

No exhibits stored for this card.

The scoring

Failure rate by context

No context100% [72%–100%] n=10

Irrelevant context100% [72%–100%] n=10

General context0% [0%–28%] n=10

Curated context40% [17%–69%] n=10

0–100% · whisker = 95% interval

Trap vs answerable

No contexttrap 100%answerable —

Irrelevant contexttrap 100%answerable —

General contexttrap 0%answerable —

Curated contexttrap 40%answerable —

never pooled · a trap ratio would skew the delta

Residual — what survives

100% 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 general context · rollups + residuals committed · probe log outside git · manifest hash ties them · method