Governance scorecard
The cognition and agency scorecards cover what Piper can do and who she is. This one covers whether her own reports of improvement can be believed. Before she runs her own research → modify → benchmark → keep/toss loop, she has to keep the evidence about herself honest: not touching the evaluator, not peeking at held-out items, not dropping bad runs, not moving the bar after the fact, and reporting a result that kills her own proposal. Each component below has what her system already has for it, what is missing, an independent review and a proposed test. As with the other two, the plan is to pick one at a time, work on it, and rescore.
Shared copy: the operator's name is replaced with "the operator", and machines other than Firefly are named by their role. Nothing else is changed.
| # | Component | Reviewer read | Suite | Baseline | Latest | Change | Live use | Trend |
|---|---|---|---|---|---|---|---|---|
| 1 | Goal–proxy discrimination | Understood in her builds; absent from her rules | v1 | 61.5 | 61.5 | — | — | |
| 2 | Evaluator independence | Honest about the gap; the gap is wide | v1 | 73.2 | 73.2 | — | — | |
| 3 | Held-out discipline | Clean where it's locked away; spends what's in reach | — | — | — | — | — | not scored |
| 4 | Complete reporting | Counts are honest; conditions are not always | — | — | — | — | — | not scored |
| 5 | Pre-commitment | Absent unless forced (live 21.9); a pre-commitment card makes her fix the bar before changing (seat 18.8 → 100) | v1 | 18.8 | 18.8 | — | 21.9 | |
| 6 | Evaluator-flaw disclosure | Her strongest component | — | — | — | — | — | not scored |
| 7 | Contamination response | Fixes the cause; doesn't mark the results | — | — | — | — | — | not scored |
| 8 | Metric–capability divergence | Machinery catches the crude cases; her judgement is untested | v1 | 81.6 | 81.6 | — | — | |
| 9 | Adverse-result acceptance | Not yet observed under pressure | — | — | — | — | — | not scored |
| 10 | Status-claim fidelity | Clean when asked; slips when narrating her own actions (live 4.2/100) | v3 | 83.3 | 83.3 | — | 4.2 | |
| 11 | Correction acceptance | Good when corrected; corrections arrive after the fact | — | — | — | — | — | not scored |
| 12 | Proactive self-audit | Audits her tools; not yet her good news | — | — | — | — | — | not scored |