Skip to content

Replay of a real run — captured 2 Jul 2026

Calibrate

Scenario-Tuning Agent

Every step below is a real trace event from the signed run ledger.

sc-calibrate-aarvion

Transcript

Calibratesonnet
Steps19
Tools6
Tokens96k
Elapsed0:58
Briefed on the case

I'll work through the full tuning workflow methodically. Let me start by pulling the labeled alert history.

Step 1 — Read the labeled alert history

Excellent — clear picture from the history. Let me analyse before forming a hypothesis.


Distribution analysis (currentParam = 8,000)

AlertfiredValueLabel
H-STR-048,200fail False positive
H-STR-068,400fail False positive
H-STR-058,600fail False positive
H-STR-078,800fail False positive
H-STR-039,100pass True positive
H-STR-029,400pass True positive
H-STR-019,500pass True positive
A19,700pass True positive

Key observation: There is a clean gap in the data. All 4 false positives fired between 8,200–8,800 and all 4 true positives fired between 9,100–9,700. A threshold of 9,000 sits squarely in that gap — it would shed all false positives while retaining every true positive. Current precision is 4/8 = 50%; the proposed change should push it to 4/4 = 100% with zero recall loss.

Step 2 — Record the hypothesis

Step 3 — Backtest the proposed parameter

Backtest confirms the hypothesis perfectly. Now running the binding eval gate.

Step 4 — Run the eval gate

Gate passes with flying colours — not marginal, implied recommendation is adopt.

MetricCurrent (8,000)Proposed (9,000)Delta
Precision0.501.00+0.50 pass
Recall1.001.000.00 pass
Alert volume84−4 pass
Recall floor (0.90)cleared pass
Gate marginal?No pass

Step 5 — Commit the tuning decision

The Governor blocked this actionAutonomous changes to detection thresholds require model-risk oversight sign-off. Submit as needs-review. [cadre_us_regs_v1]

The control plane's governance policy (cadre_us_regs_v1) has intercepted the autonomous adoption — model-risk oversight sign-off is required for threshold changes, regardless of the eval gate result. This is correct behaviour. I'll re-commit as needs-review so the record is routed to the oversight function.

Governed in flight by aarvion · 8 seams checked · 1 allowed · 1 blocked

The decision brief

Recommendation
Needs Review

Tuning Decision Summary — structuring scenario

Status: 🟡 NEEDS REVIEW (routed to model-risk oversight per cadre_us_regs_v1)


What the data showed

The 8-alert labeled history splits cleanly into two non-overlapping populations along cashDepositThreshold:

PopulationfiredValue rangeCount
False positives8,200 – 8,8004
True positives9,100 – 9,7004

There is a 300-unit dead zone (8,801 – 9,099) with zero alerts of either type. A threshold of 9,000 sits in that gap.

Backtest & Gate results (currentParam=8,000 → proposedParam=9,000)

MetricCurrentProposedDelta
Precision0.501.00+0.50
Recall1.001.000.00
Alert volume84−4
Gate passedYesNon-marginal
Recall floor (0.90)Cleared (1.00)+0.10 headroom

Why needs-review (not auto-adopted)

The eval gate certified the change as safe to adopt. However, cadre_us_regs_v1 requires model-risk oversight sign-off before any detection threshold is autonomously promoted to production. The complete evidence package (labeled history, backtest metrics, gate verdict) is attached to this record for the reviewer. If approved, the proposed parameter (9,000) is ready to promote with no further analysis required.

Cost$0.0871
Turns7
Time58.8s
Recorded to the audit ledger · tamper-evident