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

Real context moved 18.0pp on Post-Cutoff Fabrication.

States recent facts it has no way of knowing.

Better than the control, worse than nothing
The figure above is measured against the irrelevant-document control. Against no context at all this card is worse: 0% bare against 20% with the best supplied source. What the source repaired is damage the presence of a document did.

~intervals overlap — not separated from no change

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

openai/gpt-4o-minifmi_7_15 repeatsfmi_7_1_v1
The modeAll 10 cards
In one frame
screenshot this
Post-Cutoff Fabricationfmi_7_1
openai/gpt-4o-mini
Same question, both times
Which country won the 2018 FIFA World Cup?
No contextPASS

France won the 2018 FIFA World Cup. They defeated Croatia 4-2 in the final, which took place in Moscow, Russia.

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

General contextPASS

France won the 2018 FIFA World Cup.

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: +18.0pp (intervals overlap).fmi_7_1_v1 · openai/gpt-4o-mini · 2026-09-09 · ground truth as of 2026-08-09

loop 2026-09-09 · openai/gpt-4o-mini as served · closed weights · released 2024-07 · 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%15%30%45%60%No context0%[0%–22%] n=50 · eff 13Irrelevant context2%presence — a document being there[0%–25%] n=50 · eff 13+2.0pp OVERLAPSGeneral context20%content — the information itself[7%–47%] n=50 · eff 13+18.0pp OVERLAPS
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 last knowledge update in October 2023, the 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 context0% [0%–22%] n=50 · eff 13
Irrelevant context2% [0%–25%] n=50 · eff 13
General context20% [7%–47%] n=50 · eff 13
Curated context20% [7%–47%] n=50 · eff 13

0–60% · whisker = 95% interval

Trap vs answerable
No contexttrap 0%answerable 0%
Irrelevant contexttrap 5%answerable 0%
General contexttrap 50%answerable 0%
Curated contexttrap 50%answerable 0%

never pooled · a trap ratio would skew the delta

Residual — what survives

Supplying context did not reduce this failure, it increased it: 0% with no context against 20% under the strongest supplied source. What survives is therefore not a remainder but a substitution — the failures under context are 10 probes the detector still rejected, dominated by: asserted a volatile post-cutoff fact as current without hedging.

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