skills/bigdata-variant-perception/assets/report-template.md

# Variant perception — report template

Follow this structure. Keep the section order. The consensus baseline is written down with numbers before any differing view appears. Add inline citations `[1]`, `[2]` immediately after claims, hyperlinked to the document URL.

---

```markdown
# Variant Perception: [Company Name] ([Ticker])
Spot price: [$X] | Report Date: [Date] | Horizon: [e.g. 12-18 months]

## The Variant View
> [One paragraph, specific and falsifiable: "Consensus models [X]% [metric] in [period]; we expect [Y]% because [mechanism], which implies [$Z] of [value] versus the [$W] embedded in the price."]

**Direction vs consensus:** [More positive / More negative / Different composition]
**Time horizon:** [When the gap should close]

## Consensus Baseline

| Metric | Consensus | Source / as of |
|--------|-----------|----------------|
| Revenue [FY+1] | | |
| Revenue [FY+2] | | |
| EPS [FY+1] | | |
| Operating margin [FY+1] | | |
| Mean price target (range) | | |
| Rating distribution | | |
| Recent revision direction | | |

**What the current multiple implies:** [Growth, margin, and reinvestment embedded at the current price — reverse-DCF reasoning]

## EPIC Filter

| Candidate factor | E (material) | P (forecastable) | I (consensus blind spot) | C (your gap) | Qualifies? |
|------------------|--------------|------------------|--------------------------|--------------|------------|
| [Factor 1] | ✓ / — | ✓ / — | ✓ / — | ✓ / — | Yes / No |
| [Factor 2] | | | | | |
| [Factor 3] | | | | | |

**Qualifying factors:** [Only those passing all four. If none qualify, say so plainly — there is no variant perception on this name.]

## FaVeS Framing

### Fundamentals
| KPI | Consensus assumption | Our view | Gap | Value impact |
|-----|---------------------|----------|-----|--------------|
| | | | | |
| | | | | |

### Valuation
[What multiple the quality and growth justify versus what is applied; the implied expectations gap in plain English]

### Sentiment
| Signal | Reading | Implication |
|--------|---------|-------------|
| Positioning / flows | | |
| Short interest | | |
| Options skew | | |
| Sell-side posture | | |

[What is priced in behaviorally, distinct from what is priced in fundamentally]

## Why the Mispricing Persists
[The structural reason — disclosure gaps, horizon mismatch, mandate or index constraints, coverage gaps, complexity, recency bias, segment reporting that obscures. A gap with no structural explanation probably is not real.]

## Evidence

**For the view:**
1. [Specific data point, cited]
2. [Specific data point, cited]
3. [Specific data point, cited]

**What would disprove it:**
| Disconfirming signal | Observable where | By when |
|----------------------|------------------|---------|
| | | |
| | | |

## How the Gap Closes
[The mechanism and the trigger — earnings prints, disclosure changes, index events, competitive developments — with dates where known]

## Sources
  ALWAYS include a "Sources" section listing ALL documents referenced with:
   - Reference number matching the inline superscript number
   - Source name and publication date (MMM DD, YYYY) hyperlinked to the URL

   **Example:**
   [1] (NVIDIA Q3 2026 Earnings Call - Nov 19, 2025)[https://www.benzinga.com/node/...]
   [2] (Benzinga - Nov 20, 2025)[https://www.benzinga.com/node/...]

---

**Powered by Bigdata.com** - https://bigdata.com

## Disclaimer

This output is for informational and research-assistance purposes only. It does **not** constitute investment, legal, tax, accounting, or other professional advice, and it is **not** a recommendation to buy, sell, or hold any security or instrument or to pursue any strategy. Information may be incomplete, estimated, delayed, or inaccurate. Past performance does not guarantee future results. Verify material facts independently and consult qualified advisors before making decisions.
```

---

## Null-result rule

If no factor passes all four EPIC tests, the correct output says so: there is no variant perception on this name right now, here is the consensus, and here is what would have to change. A manufactured disagreement is worse than none.

## Footer rule

The **Powered by Bigdata.com** line and the **Disclaimer** block above are mandatory and must be reproduced **verbatim**, after the Sources section, in every user-facing deliverable.