Made on
Aug 19, 2026
Price at call
$36.41
6-month call
Bull +21.1%
Target by Feb 2027
$44.10
Great value below
$34.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+21.1% to $44.10
Predicted High
$44.10
at 6 months
Predicted Low
$36.90
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 19, 2026 7:13 pm
Bull
G trends higher to
$44.10
(+21.1% from $36.41)
by Feb 2027.
dip-then-recover
ThesisGenpact trades well below composite fair value with quality intact and sentiment quietly turning constructive in a risk-on tape; no earnings catalyst inside the window means the re-rate should be gradual, with value gravity pulling toward the mid-40s over six months.
Invalidated ifBreak below $34 on rising volume or regime flip to risk-off invalidates the gradual re-rate thesis.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $36.41 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 19, 2026 | — | $36.41 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Sep 2, 2026 | $33.30–$39.52 typical range · internal point $36.90 | — | ±8.5% | 6/10 | quiet drift higher as AI-services narrative supports tape |
| What actually happened: closed $37.69 on Sep 1, 2026 = +3.5% vs the call (predicted +1.4%) · direction HIT (called flat, was flat) · off by 2.2 pp · accuracy 9/10 · typical range ±8.5%: inside the band · S&P -1.0% over the same window — beat it | ||||||
| 1 month | Sep 19, 2026 | $31.91–$40.91 typical range · internal point $37.60 | — | ±12.4% | 6/10 | risk-on regime and low beta keep bid steady |
| What actually happened: closed $34.14 on Sep 18, 2026 = -6.2% vs the call (predicted +3.3%) · direction MISS (called flat, was down) · off by 9.5 pp · accuracy 4/10 · typical range ±12.4%: inside the band · S&P -0.8% over the same window — lagged it | ||||||
| 2 months | Oct 19, 2026 | $38.80 | — | +6.6% | 5/10 | value buyers accumulate below fair value anchors |
Matured — awaiting scoring. This checkpoint's date has passed; the next scorer run
(score-outcomes.php) records what actually happened.
|
||||||
| 3 months | Nov 19, 2026 | $40.20 | — | +10.4% | 5/10 | Q3 print likely another beat extends streak |
| 4 months | Dec 19, 2026 | $41.50 | — | +14.0% | 4/10 | year-end positioning toward quality compounders |
| 5 months | Jan 19, 2027 | $42.80 | — | +17.6% | 4/10 | gradual re-rate toward anchored-PE $49 target |
| 6 months | Feb 19, 2027 | $44.10 | — | +21.1% | 4/10 | value gravity pulls toward signal-adjusted $53 fair value |
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 $48.71 (+33.8%) — 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 | $36.41 |
| Composite fair value | $58.45 |
| Signal-adjusted fair value | $53.38 |
| DCF fair value | $69.90 |
| Anchored-PE fair value | $49.40 |
| Buy-below (value lens) | $34.00 |
| Value net score | +31 |
| Value confidence | 6 / 10 |
| Quality net score | +64 |
| 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 49.1% 3m 42.8% 6m 40.1% |
| Daily σ (realism noise) | 2.7% |
| Beta vs S&P 500 | 1m -0.89 3m -0.62 5m -0.40 |
| Trailing 6-month return | -5.2% |
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 |
Aug 3, 2026 | 15d behind | G-20260803-164946-c090 |
ext-forensic-memo |
Aug 19, 2026 | freshest | ext-G-20260819-143345-33b5 |
ext-lens-quality |
Aug 19, 2026 | freshest | ext-G-20260819-143345-33b5 |
ext-lens-sentiment |
Aug 19, 2026 | freshest | ext-G-20260819-143345-33b5 |
ext-lens-value |
Aug 19, 2026 | freshest | ext-G-20260819-143345-33b5 |
scenario-valuation |
Aug 19, 2026 | freshest | G-20260819-122627-bb82 |
valuation-synthesis |
Aug 19, 2026 | freshest | G-20260819-122627-bb82 |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
7 frozen snapshots — the record we score once predictions mature.| Made | Model | Call | At call | Target | Exp. | Eval due | |
|---|---|---|---|---|---|---|---|
| Sep 5, 2026 | v0.6.0 | Bull | $37.32 | $46.00 | +23.3% | Mar 2027 | view |
| Aug 31, 2026 | v0.6.0 | Bull | $38.11 | $47.50 | +24.7% | Mar 2027 | view |
| Aug 27, 2026 | v0.6.0 | Bull | $37.68 | $45.80 | +21.5% | Feb 2027 | view |
| Aug 24, 2026 | v0.6.0 | Bull | $37.57 | $48.20 | +28.3% | Feb 2027 | view |
| Aug 19, 2026 | v0.6.0 | Bull | $36.41 | $44.10 | +21.1% | Feb 2027 | viewing |
| Aug 14, 2026 | v0.6.0 | Bull | $34.37 | $42.30 | +23.1% | Feb 2027 | view |
| Aug 4, 2026 | v0.6.0 | Bull | $35.16 | $43.50 | +23.7% | Feb 2027 | 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.