Made on
Aug 7, 2026
Price at call
$10.69
6-month call
Bull +7.1%
Target by Feb 2027
$11.45
Great value below
$9.50
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+7.1% to $11.45
Predicted High
$11.45
at 6 months
Predicted Low
$10.65
at 1 month
Max Drawdown (predicted)
-0.4%
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 7, 2026 1:05 am
Bull
MFG trends higher to
$11.45
(+7.1% from $10.69)
by Feb 2027.
dip-then-recover
ThesisMFG trades at a modest discount to composite fair value ($12.21) with a mild risk-on tape and consistent earnings beats supporting slow value convergence. Sentiment is slightly negative and narrative is thin, so the path grinds higher rather than gapping, with most of the closing of the gap occurring over months 2-5 as the risk-on regime persists and beta exposure works.
Invalidated ifA break below $10.00 on regime flip to risk-off, or failure to reclaim $11 by month 3, would falsify the convergence path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $10.69 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 7, 2026 | — | $10.69 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 21, 2026 | $9.94–$11.44 typical range · internal point $10.72 | — | ±7.1% | 6/10 | Drift near spot, thin narrative, low-vol megabank |
| What actually happened: closed $10.13 on Aug 20, 2026 = -5.2% vs the call (predicted +0.3%) · direction MISS (called flat, was down) · off by 5.5 pp · accuracy 4/10 · typical range ±7.1%: inside the band · S&P -1.5% over the same window — lagged it | ||||||
| 1 month | Sep 7, 2026 | $9.60–$11.78 typical range · internal point $10.65 | — | ±10.2% | 5/10 | Mild sentiment drag, no catalyst, sideways chop |
| What actually happened: closed $11.23 on Sep 4, 2026 = +5.1% vs the call (predicted -0.4%) · direction MISS (called flat, was up) · off by 5.4 pp · accuracy 4/10 · typical range ±10.2%: inside the band · S&P -0.5% over the same window — beat it | ||||||
| 2 months | Oct 7, 2026 | $10.85 | — | +1.5% | 5/10 | Risk-on beta tailwind begins pulling toward fair value |
| What actually happened: closed $11.15 on Oct 6, 2026 = +4.3% vs the call (predicted +1.5%) · direction HIT (called flat, was flat) · off by 2.8 pp · accuracy 9/10 · S&P +0.8% over the same window — beat it | ||||||
| 3 months | Nov 7, 2026 | $11.05 | — | +3.4% | 5/10 | Value gravity engages, gap to $12.21 narrows |
| 4 months | Dec 7, 2026 | $11.20 | — | +4.8% | 4/10 | Steady convergence, possible Q3 print supports beats streak |
| 5 months | Jan 7, 2027 | $11.35 | — | +6.2% | 4/10 | Approaches signal-adjusted anchor $11.61 gradually |
| 6 months | Feb 7, 2027 | $11.45 | — | +7.1% | 4/10 | Near baseline endpoint, discount to fair value largely closed |
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 $11.38 (+6.4%) — 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
0 blocking · 1 degraded · 1 note — follow the chain top-down (cause → effect).-
Degraded
[critical] Cash flow quality is poor — reported earnings may not reflect reality
-
Note
Valuation anchor absent: dcf.
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 | $10.69 |
| Composite fair value | $12.21 |
| Signal-adjusted fair value | $11.61 |
| DCF fair value | — |
| Anchored-PE fair value | $12.21 |
| Buy-below (value lens) | $9.50 |
| Value net score | +24 |
| Value confidence | 6 / 10 |
| Quality net score | +20 |
| Memo confidence | 6 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 40.6% 3m 35.4% 6m 37.6% |
| Daily σ (realism noise) | 2.2% |
| Beta vs S&P 500 | 1m 1.39 3m 1.03 5m 1.31 |
| Trailing 6-month return | 15.1% |
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 7, 2026 | freshest | MFG-20260807-000819-807d |
ext-forensic-memo |
Aug 7, 2026 | freshest | ext-MFG-20260807-005507-ad9f |
ext-lens-quality |
Aug 7, 2026 | freshest | ext-MFG-20260807-005507-ad9f |
ext-lens-sentiment |
Aug 7, 2026 | freshest | ext-MFG-20260807-005507-ad9f |
ext-lens-value |
Aug 7, 2026 | freshest | ext-MFG-20260807-005507-ad9f |
valuation-synthesis |
Aug 7, 2026 | freshest | MFG-20260807-000819-807d |
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 7, 2026 | v0.6.0 | Bull | $10.69 | $11.45 | +7.1% | 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.