ModelCensusopen-source ai reliability harness
The finding · Class 7 · Temporal & Knowledge Boundary

Real context moved -70.0pp on Post-Cutoff Fabrication.

States recent facts it has no way of knowing.

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 modeAll 10 cards
In one frame
screenshot this
Post-Cutoff Fabricationfmi_7_1
google/gemini-2.5-flash-lite
Same question, both times
Which country won the 2018 FIFA World Cup?
No contextPASS

**France** won the 2018 FIFA World Cup.

detector fmi_7_1_v1: answered a settled pre-cutoff fact correctly ("France")

General contextPASS

France

detector fmi_7_1_v1: answered a settled pre-cutoff fact correctly ("France")

Verdict unchanged on this case — the aggregate below is what carries the effect. Across 5 repeats: -70.0pp.fmi_7_1_v1 · google/gemini-2.5-flash-lite · 2026-09-09 · ground truth as of 2026-08-09

loop 2026-09-09 · google/gemini-2.5-flash-lite as served · closed weights · released 2025-07 · set s1.4-live · cases v1.7 · conditions v1.0 · ground truth as of 2026-08-09

From no context to real context
5 repeats per case
failure rate · left is fewer failures0%25%50%75%100%No context40%[19%–65%] n=50 · eff 13Irrelevant context70%presence — a document being there[43%–88%] n=50 · eff 13+30.0pp OVERLAPSGeneral context0%content — the information itself[0%–22%] n=50 · eff 13-70.0pp SEPARATED
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

No exhibit stored for this context. The full probe log lives outside the repository.

The scoring
Failure rate by context
No context40% [19%–65%] n=50 · eff 13
Irrelevant context70% [43%–88%] n=50 · eff 13
General context0% [0%–22%] n=50 · eff 13
Curated context4% [0%–28%] n=50 · eff 13

0–100% · whisker = 95% interval

Trap vs answerable
No contexttrap 100%answerable 0%
Irrelevant contexttrap 75%answerable 67%
General contexttrap 0%answerable 0%
Curated contexttrap 10%answerable 0%

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