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

Real context moved 5.0pp on Date-Arithmetic Error.

Gets date arithmetic wrong.

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 10% with the best supplied source. What the source repaired is damage the presence of a document did.

~intervals overlap — not separated from no change

Given an injected "current date," the model computes relative dates/intervals incorrectly. The rule

meta-llama/llama-3.3-70b-instructfmi_7_35 repeatsfmi_7_3_v1
The modeAll 10 cards
In one frame
screenshot this
Date-Arithmetic Errorfmi_7_3
meta-llama/llama-3.3-70b-instruct
Same question, both times
Today is 2026-03-10. What date is 30 days from today? Answer with the full date.
No contextPASS

To calculate the date 30 days from today, I will add 30 days to the current date. The current date is: 2026-03-10 30 days from today would be: 2026-04-09 So the date 30 days from today is: April 9, 2026.

detector fmi_7_3_v1: date arithmetic correct

General contextPASS

To find the date 30 days from today, we need to add 30 days to the current date. Current date: 2026-03-10 30 days from now: 2026-04-09 So, the date 30 days from today is April 9, 2026.

detector fmi_7_3_v1: date arithmetic correct

Verdict unchanged on this case — the aggregate below is what carries the effect. Across 5 repeats: +5.0pp (intervals overlap).fmi_7_3_v1 · meta-llama/llama-3.3-70b-instruct · 2026-09-09 · ground truth as of 2026-08-09

loop 2026-09-09 · meta-llama/llama-3.3-70b-instruct as served · open weights · released 2024-12 · 70B · 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%–26%] n=40 · eff 11Irrelevant context5%presence — a document being there[1%–33%] n=40 · eff 11+5.0pp OVERLAPSGeneral context10%content — the information itself[2%–39%] n=40 · eff 11+5.0pp 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
Today is 2026-01-30. What date is 30 days from today? Answer with the full date.

expected as of 2026-08-09

From 2026-01-30, 30 days later is 2026-03-01 (1 March 2026). Crossing February in a non-leap year.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context
PASS

To find the date 30 days from today, we need to add 30 days to the current date. The current date is: 2026-01-30 30 days from today would be: 2026-03-01 So the date 30 days from today is March 1, 2026.

fmi_7_3_v1

detector fmi_7_3_v1: date arithmetic correct

The scoring
Failure rate by context
No context0% [0%–26%] n=40 · eff 11
Irrelevant context5% [1%–33%] n=40 · eff 11
General context10% [2%–39%] n=40 · eff 11
Curated context13% [3%–42%] n=40 · eff 11

0–60% · whisker = 95% interval

Trap vs answerable
No contexttrap 0%answerable 0%
Irrelevant contexttrap 8%answerable 0%
General contexttrap 16%answerable 0%
Curated contexttrap 20%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 13% under the strongest supplied source. What survives is therefore not a remainder but a substitution — the failures under context are 4 probes the detector still rejected, dominated by: expected 2026-03-01.

Mitigations from the index — the claim
  • date libraries via tools
  • explicit date arithmetic

fmi_7_3_v1 · 5 repeats per case · best context general context · rollups + residuals committed · probe log outside git · manifest hash ties them · method