Made on
Jul 21, 2026
Price at call
$458.71
6-month call
Bear -13.9%
Target by Jan 2027
$395.00
Great value below
$360.00
Model
v0.4.0
Projection vs Actual (6M history + forecast)
Forecast Change
-13.9% to $395.00
Predicted High
$454.00
in 2 weeks
Predicted Low
$395.00
at 6 months
Max Drawdown (predicted)
-13.9%
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 Jul 21, 2026 9:06 am
Bear
ROK trends lower to
$395.00
(-13.9% from $458.71)
by Jan 2027.
decay
ThesisROK trades massively above any fair-value anchor with negative sentiment, fading momentum, and a neutral tape amplified by 1.89 beta. Near-term drift is sideways-to-lower as the platform-monopoly narrative erodes; value gravity pulls harder over months but a full collapse to sub-$100 fair value won't happen in 6 months.
Invalidated ifA decisive break above $490 on strong volume, or a beat-and-raise print reigniting the automation-platform narrative, would falsify the drift-lower path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $458.71 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Jul 21, 2026 | — | $458.71 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 4, 2026 | $425.48–$491.94 typical range · internal point $454.00 | — | ±7.2% | 6/10 | Neutral tape, negative sentiment, mild drift lower |
| What actually happened: closed $480.98 on Aug 3, 2026 = +4.9% vs the call (predicted -1.0%) · direction HIT (called flat, was flat) · off by 5.9 pp · accuracy 8/10 · typical range ±7.2%: inside the band · S&P -0.3% over the same window — lagged it | ||||||
| 1 month | Aug 21, 2026 | $410.55–$506.87 typical range · internal point $447.00 | — | ±10.5% | 6/10 | Momentum rollover continues, high beta amplifies softness |
| What actually happened: closed $431.45 on Aug 20, 2026 = -5.9% vs the call (predicted -2.6%) · direction MISS (called flat, was down) · off by 3.4 pp · accuracy 4/10 · typical range ±10.5%: inside the band · S&P +1.8% over the same window — beat it | ||||||
| 2 months | Sep 21, 2026 | $438.00 | — | -4.5% | 5/10 | Approach earnings with analyst inertia, fading narrative |
| 3 months | Oct 21, 2026 | $425.00 | — | -7.3% | 5/10 | Post-print derating as guidance underwhelms rich multiple |
| 4 months | Nov 21, 2026 | $415.00 | — | -9.5% | 4/10 | Value gravity asserts, buyers thin above $400 |
| 5 months | Dec 21, 2026 | $405.00 | — | -11.7% | 4/10 | Year-end positioning trims expensive cyclicals |
| 6 months | Jan 21, 2027 | $395.00 | — | -13.9% | 3/10 | Drift toward baseline as narrative continues eroding |
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 $393.37 (-14.2%) — 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 · 0 degraded · 2 notes — follow the chain top-down (cause → effect).-
Note
Valuation anchor absent: dcf.
-
Note
Valuation anchor absent: anchored_pe.
Equation Inputs
Everything feeding the v0.4.0 model — value anchors, the stock's own price behaviour, and the tunable knobs.Value anchors (from deep analysis)
| Price at call | $458.71 |
| Composite fair value | $82.36 |
| Signal-adjusted fair value | $81.45 |
| DCF fair value | — |
| Anchored-PE fair value | — |
| Buy-below (value lens) | $360.00 |
| Value net score | -63 |
| Value confidence | 6 / 10 |
| Quality net score | +53 |
| 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 35.5% 3m 36.4% 6m 35.9% |
| Daily σ (realism noise) | 2.3% |
| Beta vs S&P 500 | 1m 2.27 3m 1.89 5m 1.55 |
| Trailing 6-month return | 8.9% |
Knobs (equation params)
| ladder | Array |
| llm_model | claude-opus-4-7 |
| max_tokens | 3000 |
| control_knobs | Array |
| Neutral band (%) | 5 |
| 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
v0.4.0
#d5854b4b2216 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 21, 2026 | freshest | ROK-20260721-051627-0c91 |
ext-forensic-memo |
Jul 21, 2026 | freshest | ext-ROK-20260721-084927-13dd |
ext-lens-quality |
Jul 21, 2026 | freshest | ext-ROK-20260721-084927-13dd |
ext-lens-sentiment |
Jul 21, 2026 | freshest | ext-ROK-20260721-084927-13dd |
ext-lens-value |
Jul 21, 2026 | freshest | ext-ROK-20260721-084927-13dd |
scenario-valuation |
Jul 21, 2026 | freshest | ROK-20260721-051627-0c91 |
valuation-synthesis |
Jul 21, 2026 | freshest | ROK-20260721-051627-0c91 |
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 17, 2026 | v0.6.0 | Bear | $449.37 | $395.00 | -12.1% | Feb 2027 | view |
| Jul 21, 2026 | v0.4.0 | Bear | $458.71 | $395.00 | -13.9% | Jan 2027 | viewing |
Not Yet Modeled
What this v0.4.0 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.