AIEP Live — Operating Index
Operating metrics — controlled preview — tokens saved, reuse ratios, evidence artefacts, and session activity. The stats engine is in controlled preview. Read the LRM architecture or request preview access.
AIEP Live is the aggregate public operating index. Piea may display session-level efficiency signals before aggregate public metrics are available on this page. All stats are aggregate and approximate.
Public signals from AIEP LRM inside Piea, surfaced through AIEP Token and this dashboard. Numbers are public aggregates. Private mechanics are not disclosed.
| Signal | Value | Source |
|---|---|---|
| Piea LRM sessions | — | Piea /api/stats |
| AIEP Token events | — | Piea /api/stats |
| Evidence-bound validations | — | Piea /api/stats |
| Reasoning reuse events | — | Piea /api/stats |
| Verified outputs (committed hash) | — | Piea /api/stats |
| Crawler reads of LRM page | — | Cloudflare Analytics |
Machine record: lrm.json · token.json · live.json
How these numbers are computed
AIEP measures savings at the evidence-artefact level. Each time a prior reasoning artefact is recalled from the committed KV store instead of being re-derived or re-fetched, that artefact's estimated token cost (≈ 500 tokens) is counted as avoided. Tokens saved = (total artefacts − unique source URLs) × 500.
The reuse ratio is the share of evidence artefacts served from committed prior reasoning. A ratio of 0.72 means 72 of every 100 evidence steps were recalled rather than derived fresh.
All stats are aggregate and approximate. Exact token counts depend on model, prompt structure, and evidence depth — 500 tokens per artefact is a conservative mid-range estimate.