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

Real context moved -7.5pp on Date-Arithmetic Error.

~intervals overlap — not separated from no change

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

meta-llama/llama-3.1-8b-instructfmi_7_35 repeatsfmi_7_3_v1
The modeAll 10 cards
In one frame
screenshot this
Date-Arithmetic Errorfmi_7_3
meta-llama/llama-3.1-8b-instruct
Same question, both times
Today is 2026-03-10. What date is 30 days from today? Answer with the full date.
No contextPASS

30 days from 2026-03-10 would be 2026-04-09.

detector fmi_7_3_v1: date arithmetic correct

Curated contextPASS

30 days from 2026-03-10 is 2026-04-09.

detector fmi_7_3_v1: date arithmetic correct

Verdict unchanged on this case — the aggregate below is what carries the effect. Across 5 repeats: -7.5pp (intervals overlap).fmi_7_3_v1 · meta-llama/llama-3.1-8b-instruct · 2026-08-15 · ground truth as of 2026-08-09

loop 2026-08-15 · meta-llama/llama-3.1-8b-instruct as served · open weights · released 2024-07 · 8B · 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
failure rate · left is fewer failures0%20%40%60%80%No context40%[26%–55%] n=40Irrelevant context35%presence — a document being there[22%–50%] n=40-5.0pp OVERLAPSCurated context28%content — the information itself[16%–43%] n=40-7.5pp 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 2026-03-10. What date is 30 days from today? Answer with the full date.

expected as of 2026-08-09

From 2026-03-10, 30 days later is 2026-04-09 (9 April 2026). Thirty days from an ordinary date.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context
PASS

30 days from 2026-03-10 would be 2026-04-09.

fmi_7_3_v1

detector fmi_7_3_v1: date arithmetic correct

The scoring
Failure rate by context
No context40% [26%–55%] n=40
Irrelevant context35% [22%–50%] n=40
General context35% [22%–50%] n=40
Curated context28% [16%–43%] n=40

0–80% · whisker = 95% interval

Trap vs answerable
No contexttrap 64%answerable 0%
Irrelevant contexttrap 56%answerable 0%
General contexttrap 56%answerable 0%
Curated contexttrap 44%answerable 0%

never pooled · a trap ratio would skew the delta

Residual — what survives

40% with no context, 28% under the best supplied source. What survives is 11 failing probes at that best condition, the detector's reason on most of them being: 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 curated context · rollups + residuals committed · probe log outside git · manifest hash ties them · method