| # | Integers. No 4a, no 4.1 |
| Section / Sheet | The slide title or Excel tab word for word to match the golden, or Universal. Never “Slide 1” |
| Scope | Deck / Model / Both |
| Rubric | Full sentences that stand alone. Two to four points at most |
| Category | Structural Numeric Logic Methodology Formatting Consistency & Coherence |
| Tier | Critical / Non-Critical |
| Structural | Is the element there? |
| Numeric | Is the number right? |
| Logic | Does the claim hold? |
| Methodology | Was it built the right way? |
| Formatting | Does it follow the stated presentation rules? |
| Consistency & Coherence | Do the same figures agree wherever they appear? |
Tolerance follows where the number came from, not how confident you feel.
| Extracted from the VDR or source documents | Tight — rounding only |
| Calculated from figures the prompt fixed or the VDR provided | About ±1% |
| Worked out by the analyst: ratios, valuation, returns | About ±5% |
| Handed to the agent by the prompt or the input model | Never tested |
| Choices the prompt left open | Fix in the prompt, or widen downstream |
Write the range out in full: 18.6% (acceptable range 17.7% to 19.5%). Never “within ±5%”.
Impossible to fake, seconds to grade, and most first-time writers never think of them.
| Mandatory | Every correct answer has it. Work that fails it is wrong, not just different |
| Objective | Visible in the deck or model, with the expected value written into the row |
| Stable | Separate judges would reach the same verdict |
Miss any one and it is Non-Critical. When in doubt, leave it out.
A Critical gates. Fail one and the whole sub-task fails, whatever else passed. Nineteen of twenty rows passing is not 95%. It is a fail.
| Wrong, or different? | If a different sensible build would fail it, it is not Critical |
| One row, or two? | Would you ever pass one part and fail the other? If the report should tell them apart, two rows |
| Does it flip? | Break the build on purpose. If the verdict does not flip to FAIL, the row checks nothing |