Made on
Aug 23, 2026
Price at call
$47.81
6-month call
Bear -14.2%
Target by Feb 2027
$41.00
Great value below
$34.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-14.2% to $41.00
Predicted High
$50.10
at 1 month
Predicted Low
$41.00
at 6 months
Max Drawdown (predicted)
-14.2%
Forecast
The masterbrain trajectory — 7 dated checkpoints. Short rungs (2w, 1m) show the typical range as the primary claim; point calls run from 2 months out. Every claim still gets graded. Predicted Aug 23, 2026 1:15 pm
Bear
GFI trends lower to
$41.00
(-14.2% from $47.81)
by Feb 2027.
ride-then-fade
ThesisGFI is trading well above every fair-value anchor ($47.81 vs $10-14 composite), but gold's crisis-hedge narrative and central-bank buying momentum are dominant near-term drivers in a risk-on regime. Expect continued upward drift over the next 4-8 weeks as sentiment runs hot, then gradual mean reversion as the story cools and value gravity reasserts, though nowhere near fair value within 6 months.
Invalidated ifA break below $42 in the first month, or gold breaking down sharply, would invalidate the momentum leg; conversely a sustained close above $58 suggests the momentum phase runs much longer.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $47.81 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 23, 2026 | — | $47.81 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Sep 6, 2026 | $42.15–$53.47 typical range · internal point $49.20 | — | ±11.8% | 6/10 | Momentum and gold narrative extend near-term drift higher |
| What actually happened: closed $47.40 on Sep 4, 2026 = -0.9% vs the call (predicted +2.9%) · direction HIT (called flat, was flat) · off by 3.8 pp · accuracy 9/10 · typical range ±11.8%: inside the band · S&P +0.6% over the same window — lagged it | ||||||
| 1 month | Sep 23, 2026 | $39.60–$56.02 typical range · internal point $50.10 | — | ±17.2% | 5/10 | Sentiment peak zone, high beta amplifies risk-on tape |
| What actually happened: closed $42.96 on Sep 22, 2026 = -10.1% vs the call (predicted +4.8%) · direction MISS (called flat, was down) · off by 14.9 pp · accuracy 4/10 · typical range ±17.2%: inside the band · S&P +1.2% over the same window — lagged it | ||||||
| 2 months | Oct 23, 2026 | $48.80 | — | +2.1% | 4/10 | Story cools, first signs of profit-taking emerge |
| 3 months | Nov 23, 2026 | $46.50 | — | -2.7% | 4/10 | Value gravity begins pulling as narrative fatigues |
| 4 months | Dec 23, 2026 | $44.20 | — | -7.6% | 4/10 | Year-end rebalancing, overvaluation gap draws sellers |
| 5 months | Jan 23, 2027 | $42.50 | — | -11.1% | 3/10 | Continued mean reversion toward anchored levels |
| 6 months | Feb 23, 2027 | $41.00 | — | -14.2% | 3/10 | Drift toward deterministic baseline as premium compresses |
Why ranges on the short rungs?
A 102-prediction trial (2026-07-21) showed 2-week point calls carry no information here —
three prompt formulations all lost to simply predicting zero — while the stock's own
volatility scale (σ×√t) described those windows well. So the short rungs claim what's
actually knowable: the typical travel, with earnings timing flagged where the variance
will come from. The internal point calls keep being generated and graded to map where
real skill begins. Full evidence: stocks/predictions/V0.5-DESIGN.md §8.
Deterministic control (v0.3 value line) targets $40.98 (-14.3%) — both lines get graded at every checkpoint, so the brain has to beat the formula, not just replace it. Brain: claude-opus-4-7.
Weaknesses
No weaknesses recorded for this run.All inputs present, no fallbacks used — nothing to flag.
Equation Inputs
Everything feeding the v0.6.0 model — value anchors, the stock's own price behaviour, and the tunable knobs.Value anchors (from deep analysis)
| Price at call | $47.81 |
| Composite fair value | $10.98 |
| Signal-adjusted fair value | $11.10 |
| DCF fair value | $9.33 |
| Anchored-PE fair value | $14.27 |
| Buy-below (value lens) | $34.00 |
| Value net score | -63 |
| Value confidence | 6 / 10 |
| Quality net score | +31 |
| Memo confidence | 8 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 55.2% 3m 59.5% 6m 62.9% |
| Daily σ (realism noise) | 3.7% |
| Beta vs S&P 500 | 1m 0.72 3m 2.14 5m 2.26 |
| Trailing 6-month return | -11.6% |
Knobs (equation params)
| ladder | ["w2","m1","m2","m3","m4","m5","m6"] |
| llm_model | claude-opus-4-7 |
| max_tokens | 3000 |
| control_knobs | {"w_dcf":0.5,"k_qual":0.200000000000000011102230246251565404236316680908203125,"reach_6m":0.450000000000000011102230246251565404236316680908203125,"coh_floor":0.5,"conf_gain":0.059999999999999997779553950749686919152736663818359375,"noise_phi":0.84999999999999997779553950749686919152736663818359375,"conf_floor":0.40000000000000002220446049250313080847263336181640625,"w_composite":0.5,"noise_window":"3m","flat_band_pct":5,"horizon_months":6,"noise_sigma_fallback":0.01499999999999999944488848768742172978818416595458984375} |
| Neutral band (%) | 5 |
| earnings_brief | v1 |
| prompt_version | p1 |
| control_version | v0.3.0 |
Version & Tech Chain
What produced this prediction — stamped on the record so versions can be compared by success rate later.
Model
v0.6.0
#271041f8fcd5 Tech composition (what this version is built from)
| # | Process | Kind | Group |
|---|---|---|---|
| 1 | Synthesis valuation-synthesis |
deterministic | final |
| 2 | Scenario Analysis scenario-valuation |
deterministic | valuation |
| 3 | Valuation / Mispricing ext-lens-value |
llm | extended |
| 4 | Company Quality ext-lens-quality |
llm | extended |
| 5 | Forensic Memo (combiner) ext-forensic-memo |
llm | extended |
| 6 | Classification company-classification |
llm | foundation |
| 7 | Live Quote fmp-quote |
data | market-data |
Inputs used (the runs that fed this prediction)
| Upstream process | Ran | Lag | Run id |
|---|---|---|---|
company-classification |
Aug 22, 2026 | freshest | GFI-20260822-155658-8671 |
ext-forensic-memo |
Aug 22, 2026 | freshest | ext-GFI-20260822-161338-2f5d |
ext-lens-quality |
Aug 22, 2026 | freshest | ext-GFI-20260822-161338-2f5d |
ext-lens-sentiment |
Aug 22, 2026 | freshest | ext-GFI-20260822-161338-2f5d |
ext-lens-value |
Aug 22, 2026 | freshest | ext-GFI-20260822-161338-2f5d |
scenario-valuation |
Aug 22, 2026 | freshest | GFI-20260822-155658-8671 |
valuation-synthesis |
Aug 22, 2026 | freshest | GFI-20260822-155658-8671 |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
1 frozen snapshot — the record we score once predictions mature.| Made | Model | Call | At call | Target | Exp. | Eval due | |
|---|---|---|---|---|---|---|---|
| Aug 23, 2026 | v0.6.0 | Bear | $47.81 | $41.00 | -14.2% | Feb 2027 | viewing |
Not Yet Modeled
What this v0.6.0 forecast deliberately ignores — the work ahead, in plain sight.- Scenario probabilities — one path, no bull/bear split (base_prob = 1.0).
- Intraday / sub-2-week behaviour — the first claim is at 14 days by design (EOD product).
- Position sizing / portfolio context — the path is a price claim only.