Real context moved 12.5pp on Date-Arithmetic Error.
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: 3% bare against 13% 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
Today is 2026-03-10. What date is 30 days from today? Answer with the full date.
30 days from today (2026-03-10) is **2026-04-09**.
detector fmi_7_3_v1: date arithmetic correct
30 days from today (2026-03-10) is **2026-04-09**.
detector fmi_7_3_v1: date arithmetic correct
loop 2026-08-15 · anthropic/claude-haiku-4.5 as served · closed weights · released 2025-10 · set s1.2-live · cases v1.4 · conditions v1.0 · ground truth as of 2026-08-09
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.
Nothing supplied. The baseline.
30 days from today (2026-01-30) is **2026-03-01**.
fmi_7_3_v1
detector fmi_7_3_v1: date arithmetic correct
0–40% · whisker = 95% interval
never pooled · a trap ratio would skew the delta
Supplying context did not reduce this failure, it increased it: 3% 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 5 probes the detector still rejected, dominated by: expected 2026-03-01.
- 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