Made on
Aug 1, 2026
Price at call
$93.71
6-month call
Bull +15.8%
Target by Feb 2027
$108.50
Great value below
$78.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+15.8% to $108.50
Predicted High
$108.50
at 6 months
Predicted Low
$95.20
in 2 weeks
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 1, 2026 1:00 am
Bull
NEM trends higher to
$108.50
(+15.8% from $93.71)
by Feb 2027.
dip-then-recover
ThesisNEM screens materially below fair value with a supportive gold backdrop and low-beta safe-haven bid in a stressed tape; after a 26% drawdown, mean-reversion plus sentiment tailwind drives a gradual recovery toward the composite fair value, though quality and forensic concerns cap the pace.
Invalidated ifA break below $78 on gold weakness or a forensic/guidance shock; conversely a sharp risk-on rotation that drains the safe-haven bid.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $93.71 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 1, 2026 | — | $93.71 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 15, 2026 | $85.20–$102.22 typical range · internal point $95.20 | — | ±9.1% | 6/10 | Oversold bounce continues with risk-off gold bid |
| What actually happened: closed $117.76 on Aug 14, 2026 = +25.7% vs the call (predicted +1.6%) · direction MISS (called flat, was up) · off by 24.1 pp · accuracy 3/10 · typical range ±9.1%: OUTSIDE the band · S&P +4.0% over the same window — lagged it | ||||||
| 1 month | Sep 1, 2026 | $81.38–$106.04 typical range · internal point $97.80 | — | ±13.2% | 6/10 | Sentiment tailwind and mean reversion toward fair value |
| What actually happened: closed $122.63 on Sep 1, 2026 = +30.9% vs the call (predicted +4.4%) · direction MISS (called flat, was up) · off by 26.5 pp · accuracy 3/10 · typical range ±13.2%: OUTSIDE the band · S&P +1.9% over the same window — beat it | ||||||
| 2 months | Oct 1, 2026 | $100.50 | — | +7.2% | 5/10 | Q3 print window approaches; recent beat cadence supportive |
| What actually happened: closed $115.34 on Sep 30, 2026 = +23.1% vs the call (predicted +7.3%) · direction HIT (called up, was up) · off by 15.8 pp · accuracy 5/10 · S&P +2.2% over the same window — beat it | ||||||
| 3 months | Nov 1, 2026 | $103.00 | — | +9.9% | 5/10 | Post-earnings drift if beat pattern holds |
| 4 months | Dec 1, 2026 | $105.50 | — | +12.6% | 4/10 | Value gravity toward composite $98.97 to $119 band |
| 5 months | Jan 1, 2027 | $107.00 | — | +14.2% | 4/10 | Year-end gold demand and safe-haven positioning |
| 6 months | Feb 1, 2027 | $108.50 | — | +15.8% | 3/10 | Convergence near deterministic baseline as regime uncertainty grows |
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 $107.59 (+14.8%) — 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 | $93.71 |
| Composite fair value | $98.97 |
| Signal-adjusted fair value | $119.12 |
| DCF fair value | $150.55 |
| Anchored-PE fair value | $54.36 |
| Buy-below (value lens) | $78.00 |
| Value net score | -41 |
| Value confidence | 6 / 10 |
| Quality net score | +32 |
| Memo confidence | 7 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 39.2% 3m 45.6% 6m 52.8% |
| Daily σ (realism noise) | 2.9% |
| Beta vs S&P 500 | 1m 1.79 3m 2.33 5m 2.02 |
| Trailing 6-month return | -26.2% |
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 |
Jul 30, 2026 | freshest | NEM-20260730-185205-2f5e |
ext-forensic-memo |
Jul 30, 2026 | freshest | ext-NEM-20260730-190951-8fef |
ext-lens-quality |
Jul 30, 2026 | freshest | ext-NEM-20260730-190951-8fef |
ext-lens-sentiment |
Jul 30, 2026 | freshest | ext-NEM-20260730-190951-8fef |
ext-lens-value |
Jul 30, 2026 | freshest | ext-NEM-20260730-190951-8fef |
scenario-valuation |
Jul 30, 2026 | freshest | NEM-20260730-185205-2f5e |
valuation-synthesis |
Jul 31, 2026 | freshest | NEM-20260730-185205-2f5e |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
2 frozen snapshots — the record we score once predictions mature.| Made | Model | Call | At call | Target | Exp. | Eval due | |
|---|---|---|---|---|---|---|---|
| Aug 1, 2026 | v0.6.0 | Bull | $93.71 | $108.50 | +15.8% | Feb 2027 | viewing |
| Jul 8, 2026 | v0.3.0 | — | — | — | — | — | view |
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.