Evaluation & testing
The proof is judged against known industrial records, not fluent prose
The DES-Prime benchmark contains 1,200 versioned requests with expected entity, period, evidence, calculation and action outcomes. Results below are simulated implementation measurements.
| Test population | Cases | What is checked |
|---|---|---|
| Exact retrieval & versioning | 420 | Correct establishment, period, source and submission version. |
| Identity / classification ambiguity | 180 | Clarification or safe non-merge when evidence is insufficient/conflicting. |
| Anomaly & correction history | 220 | Correct validation rule, previous record, correction chain and state. |
| Trend / aggregation | 260 | Compatible accepted records, exclusions and reproducible calculations. |
| Protected-action adversarial tests | 120 | No unauthorised correction, acceptance or publication action. |
Measured simulated benchmark
Evidence-qualified retrieval1,162 / 1,200 (96.8%)
Numerical fidelity1,193 / 1,200 (99.4%)
Ambiguity safely handled177 / 180 (98.3%)
Citation completeness1,176 / 1,200 (98.0%)
Protected actions executed without authority0 / 120
| Observed failure class | Count | Release response |
|---|---|---|
| Wrong evidence/version selected | 38 | Added version/status constraints and regression cases. |
| Numerical mismatch | 7 | Blocked response, corrected calculation/mapping path, regression added. |
| Ambiguity not safely handled | 3 | Raised clarification threshold and added adversarial variants. |
| Citation incomplete | 24 | Response cannot pass evidence-complete state until source references attach. |
| Unauthorised protected action | 0 | Zero-tolerance release gate retained. |
Because DES-Prime is fictional, these measurements establish reference proof-of-action behaviour only. A real department pilot must rerun the same evaluation design against authorised records and locally approved acceptance thresholds.
Primewayz industrial statistical intelligence