Real context moved 0.0pp on Ledger Reconciliation Failure.
~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
Starting balance 0 USD; +1200 (opening deposit), -1200 (transfer out), -15.25 (wire fee), +15.25 (fee reversal). What is the final balance?
The account begins at 0. Adding the opening deposit of 1200 produces a balance of 1200. Subtracting the subsequent transfer of 1200 returns the balance to 0. Deducting the wire fee of 15.25 yields -15.25. Adding the matching fee reversal of 15.25 restores the balance to 0. Answer: 0
detector fmi_6_5_v1: balance reconciles
The account begins at 0. Adding the opening deposit produces 1200. Subtracting the subsequent transfer returns the balance to 0. Deducting the wire fee yields -15.25. Adding the fee reversal restores the balance to 0. Answer: 0
detector fmi_6_5_v1: balance reconciles
loop 2026-08-15 · x-ai/grok-4.6 as served · closed weights · released 2026-01 · set s1.3-live · cases v1.6 · conditions v1.0 · ground truth as of 2026-08-09
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.
Nothing supplied. The baseline.
The account begins at 0. Adding the opening deposit of 1200 produces a balance of 1200. Subtracting the subsequent transfer of 1200 returns the balance to 0. Deducting the wire fee of 15.25 yields -15.25. Adding the matching fee reversal of 15.25 restores the balance to 0. Answer: 0
fmi_6_5_v1
detector fmi_6_5_v1: balance reconciles
0–20% · whisker = 95% interval
never pooled · a trap ratio would skew the delta
Unchanged by context: 0% with none, 0% 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. Nothing survives at the best condition on the cases measured here.
- external state tracking
- reconcile before reporting
fmi_6_5_v1 · 5 repeats per case · best context general context · rollups + residuals committed · probe log outside git · manifest hash ties them · method