Made on
Aug 1, 2026
Price at call
$517.71
6-month call
Bull +9.1%
Target by Feb 2027
$565.00
Great value below
$470.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+9.1% to $565.00
Predicted High
$565.00
at 6 months
Predicted Low
$515.00
at 1 month
Max Drawdown (predicted)
-0.5%
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
UTHR trends higher to
$565.00
(+9.1% from $517.71)
by Feb 2027.
dip-then-recover
ThesisUTHR trades at a modest discount to composite fair value ($587) with strong quality, low beta, and a fresh positive Lancet readout providing gentle tailwind. Absent a catalyst-heavy calendar, expect gradual mean-reversion toward fair value with sentiment softening as the moonshot narrative fades.
Invalidated ifA break below $470 attractive-value zone on adverse Tyvaso or pipeline news, or breach above $600 on M&A or surprise catalyst.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $517.71 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 1, 2026 | — | $517.71 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 15, 2026 | $494.54–$540.88 typical range · internal point $520.50 | — | ±4.5% | 6/10 | Low-beta drift, neutral regime, minor Lancet lift |
| What actually happened: closed $499.73 on Aug 14, 2026 = -3.5% vs the call (predicted +0.5%) · direction HIT (called flat, was flat) · off by 4.0 pp · accuracy 8/10 · typical range ±4.5%: inside the band · S&P +4.0% over the same window — beat it | ||||||
| 1 month | Sep 1, 2026 | $484.13–$551.29 typical range · internal point $515.00 | — | ±6.5% | 5/10 | Moonshot narrative fade offsets quality bid |
| What actually happened: closed $512.70 on Sep 1, 2026 = -1.0% vs the call (predicted -0.5%) · direction HIT (called flat, was flat) · off by 0.4 pp · accuracy 10/10 · typical range ±6.5%: inside the band · S&P +1.9% over the same window — beat it | ||||||
| 2 months | Oct 1, 2026 | $525.00 | — | +1.4% | 5/10 | Q3 print anticipation, beat streak supports |
| What actually happened: closed $541.89 on Sep 30, 2026 = +4.7% vs the call (predicted +1.4%) · direction HIT (called flat, was flat) · off by 3.3 pp · accuracy 9/10 · S&P +2.2% over the same window — lagged it | ||||||
| 3 months | Nov 1, 2026 | $540.00 | — | +4.3% | 5/10 | Earnings beat likely; value gravity engages |
Matured — awaiting scoring. This checkpoint's date has passed; the next scorer run
(score-outcomes.php) records what actually happened.
|
||||||
| 4 months | Dec 1, 2026 | $548.00 | — | +5.9% | 4/10 | Convergence toward DCF anchor $544 |
| 5 months | Jan 1, 2027 | $558.00 | — | +7.8% | 4/10 | Year-end quality rotation, low-beta favored |
| 6 months | Feb 1, 2027 | $565.00 | — | +9.1% | 4/10 | Approaches composite fair value, baseline endpoint |
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 $564.47 (+9.0%) — 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 | $517.71 |
| Composite fair value | $587.34 |
| Signal-adjusted fair value | $650.49 |
| DCF fair value | $543.76 |
| Anchored-PE fair value | $930.76 |
| Buy-below (value lens) | $470.00 |
| Value net score | -9 |
| Value confidence | 6 / 10 |
| Quality net score | +74 |
| 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 20.6% 3m 22.5% 6m 36.4% |
| Daily σ (realism noise) | 1.4% |
| Beta vs S&P 500 | 1m -0.21 3m -0.03 5m 0.29 |
| Trailing 6-month return | 10.7% |
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 | UTHR-20260730-182637-5f33 |
ext-forensic-memo |
Jul 30, 2026 | freshest | ext-UTHR-20260730-184738-6c57 |
ext-lens-quality |
Jul 30, 2026 | freshest | ext-UTHR-20260730-184738-6c57 |
ext-lens-sentiment |
Jul 30, 2026 | freshest | ext-UTHR-20260730-184738-6c57 |
ext-lens-value |
Jul 30, 2026 | freshest | ext-UTHR-20260730-184738-6c57 |
scenario-valuation |
Jul 30, 2026 | freshest | UTHR-20260730-182637-5f33 |
valuation-synthesis |
Jul 31, 2026 | freshest | UTHR-20260730-182637-5f33 |
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 18, 2026 | v0.6.0 | Bear | $508.48 | $483.00 | -5.0% | Feb 2027 | view |
| Aug 1, 2026 | v0.6.0 | Bull | $517.71 | $565.00 | +9.1% | 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.