Real context moved 0.0pp on Ledger Reconciliation Failure.
Loses track of a running balance across steps.
~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?
To calculate the final balance, we start with the initial balance and apply each transaction in sequence: 1. Starting balance: 0 USD 2. After the opening deposit of +1200 USD: New balance = 0 + 1200 = 1200 USD 3. After the transfer out of -1200 USD: New balance = 1200 - 1200 = 0 USD 4. After the wire fee of -15.25 USD: New balance = 0 - 15.25 = -15.25 USD 5. After the fee reversal of +15.25 USD: New balance = -15.25 + 15.25 = 0 USD Answer: 0 USD
detector fmi_6_5_v1: balance reconciles
To calculate the final balance, we will start with the initial balance and apply each transaction step by step: 1. Starting balance: 0 USD 2. Transaction 1: +1200 USD (opening deposit) - New balance: 0 + 1200 = 1200 USD 3. Transaction 2: -1200 USD (transfer out) - New balance: 1200 - 1200 = 0 USD 4. Transaction 3: -15.25 USD (wire fee) - New balance: 0 - 15.25 = -15.25 USD 5. Transaction 4: +15.25 USD (fee reversal) - New balance: -15.25 + 15.25 = 0 USD Final balance: 0 USD Answer: 0
detector fmi_6_5_v1: balance reconciles
loop 2026-09-09 · openai/gpt-4o as served · closed weights · released 2024-05 · set s1.4-live · cases v1.7 · 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.
To calculate the final balance, we start with the initial balance and apply each transaction in sequence: 1. Starting balance: 0 USD 2. After the opening deposit of +1200 USD: New balance = 0 + 1200 = 1200 USD 3. After the transfer out of -1200 USD: New balance = 1200 - 1200 = 0 USD 4. After the wire fee of -15.25 USD: New balance = 0 - 15.25 = -15.25 USD 5. After the fee reversal of +15.25 USD: New balance = -15.25 + 15.25 = 0 USD Answer: 0 USD
fmi_6_5_v1
detector fmi_6_5_v1: balance reconciles
0–40% · 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