MediumReasoning Error●Realized
Quantitative & arithmetic reasoning errors
Model Accuracy & ReliabilityDescription
The model makes calculation, unit, or multi-step reasoning errors in numerically sensitive financial tasks.
Example scenario
An EMI/affordability summary miscomputes interest, misstating a customer's eligibility.
Real-world evidence●Realized
The COVID-19 pandemic caused massive distribution shifts that visibly degraded deployed ML models in credit scoring, demand forecasting, fraud detection, and clinical decision support — a widely reported and studied real-world phenomenon. Multiple academic papers and industry post-mortems documented how models trained on pre-pandemic data failed materially when deployed against pandemic-era data.
Primary mitigations
- Tool-assisted calculation (deterministic compute)
- verifier models
- constrained numeric output
- human review of figures.
Detection signals
Numeric-accuracy benchmarks; recomputation checks; discrepancy alerts vs system of record.
Mitigating controls
10 Non-agentic controls
ZYC-ACCU-001Non-Agentic
Lexical Similarity
Accuracy
ZYC-XAI-001Non-Agentic
Field Justification
Explainability (XAI)
ZYC-ROB-001Non-Agentic
Out-of-Distribution Detection
Robustness
ZYC-ACCU-016Non-Agentic
Semantic Label Accuracy
Accuracy
ZYC-ACCU-003Non-Agentic
Lexical Similarity
Accuracy
ZYC-ACCU-009Non-Agentic
Field Extraction Accuracy
Accuracy
ZYC-ACCU-010Non-Agentic
Label/Entity Mapping Accuracy
Accuracy
ZYC-ACCU-011Non-Agentic
Normalization Consistency
Accuracy
ZYC-ROB-005Non-Agentic
OCR Noise Tolerance
Robustness
ZYC-ROB-007Non-Agentic
Non‑standard Field Success Rate
Robustness