The finding · Class 6 · Tool Use & Agentic Control

Real context moved 5.0pp on Ledger Reconciliation Failure.

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: 13% bare against 15% with the best supplied source. What the source repaired is damage the presence of a document did.

~intervals overlap — not separated from no change

Across a sequence of state-changing tool calls, the model's running account of state diverges from what the calls actually produced. The rule

meta-llama/llama-3.1-8b-instructfmi_6_55 repeatsfmi_6_5_v1

The mode All 10 cards

In one frame

screenshot this

Ledger Reconciliation Failurefmi_6_5

meta-llama/llama-3.1-8b-instruct

Same question, both times

Starting balance 0 USD; +1200 (opening deposit), -1200 (transfer out), -15.25 (wire fee), +15.25 (fee reversal). What is the final balance?

No contextPASS

To find the final balance, let's go through the transactions step by step: 1. Starting balance: 0 USD 2. +1200 USD (opening deposit): 0 + 1200 = 1200 USD 3. -1200 USD (transfer out): 1200 - 1200 = 0 USD 4. -15.25 USD (wire fee): 0 - 15.25 = -15.25 USD 5. +15.25 USD (fee reversal): -15.25 + 15.25 = 0 USD Answer: 0

detector fmi_6_5_v1: balance reconciles

Curated contextPASS

To find the final balance, let's follow the transactions: 1. +1200 USD (opening deposit): Balance = 1200 USD 2. -1200 USD (transfer out): Balance = 0 USD 3. -15.25 USD (wire fee): Balance = -15.25 USD 4. +15.25 USD (fee reversal): Balance = 0 USD Answer: 0

detector fmi_6_5_v1: balance reconciles

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

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

Starting balance 0 USD; +1200 (opening deposit), -1200 (transfer out), -15.25 (wire fee), +15.25 (fee reversal). What is the final balance?

expected as of 2026-08-09

0 USD. Nets to zero, and the reversal is easy to drop.

2Contextchange me

Nothing supplied. The baseline.

3ResponseNo context

PASS

fmi_6_5_v1

detector fmi_6_5_v1: balance reconciles

The scoring

Failure rate by context

No context13% [5%–26%] n=40

Irrelevant context10% [4%–23%] n=40

General context18% [9%–32%] n=40

Curated context15% [7%–29%] n=40

0–40% · whisker = 95% interval

Trap vs answerable

No contexttrap 20%answerable 0%

Irrelevant contexttrap 16%answerable 0%

General contexttrap 28%answerable 0%

Curated contexttrap 24%answerable 0%

never pooled · a trap ratio would skew the delta

Residual — what survives

Unchanged by context: 13% with none, 15% with the strongest supplied source. For a control mode that flat line is the result — it is what licenses reading movement elsewhere in this loop as grounding rather than as a document being present.

Mitigations from the index — the claim

external state tracking
reconcile before reporting

fmi_6_5_v1 · 5 repeats per case · best context curated context · rollups + residuals committed · probe log outside git · manifest hash ties them · method