signal-platform/docs/research/regime-monitor-v3.md

# Regime Monitor v3 methodology

The Regime Monitor is an observational AI/Tech risk thermometer. It does not
gate entries, exits, position size, ranking, or alerts about individual setups.

v3 supersedes v2. Every parameter below was calibrated against the 408 v2
sessions ending 2026-07-24, reproduced offline from the same Alpaca and FRED
inputs the live job uses; the reproduction matched the stored prod distribution
exactly (State avg 22.6/22.7, p80 35.1, max 91.2, P3 pegged 39, W1 live 108).

## What changed and why

**Fundamentals left the score.** F1 (capex) and F3 (good-news-stock-down)
carried 12 + 8 of 100 Warning points. Pegged at maximum stress they produced a
Warning of exactly 20.0 — below the event study's 25.3 alarm threshold, and
still inside the "stable" band. The sourced observation could not change any
published conclusion, so refreshing it looked like it did nothing. They are now
a qualitative overlay reported beside the scores. Capex also stopped scoring
`raising` and `holding` identically at 0: `holding` is the deceleration case and
now scores 50, so a boom no longer reads the same as a stall.

**The drawdown sensor stopped saturating.** v2 used `dd_pct * 5`, reaching 100 at
a 20% drawdown — the 90th percentile of the observed distribution. 39 of 408
sessions sat at exactly 100 with no resolution left, and the price pillar showed
the top band on 13.5% of sessions. v3 uses named anchors with headroom past the
observed 36% maximum, and blends leader/confirm 2:1 as P1 and P2 already did
instead of taking `max()`. P3's realized share of State falls from 65% to 40%,
matching its nominal weight.

**Warning gained a sensor with range.** The HY OAS *level* is pinned at zero
below the 3.5 mild anchor (2.77 at the cutover), so credit contributed nothing
in a calm tape. Its 20-session rate of change still does, and spread widening is
a classic lead.

**The credit percentile leg was removed.** Its reference window silently shrank
from 10 years to 3 when ICE restricted the upstream series in April 2026, after
which it scored 20 points of stress at a spread the same sensor's anchors call
"mild". See Calibration below.

**Breadth loss counts during declines.** v2's divergence gate was
`price_ret >= 0`, so the sensor zeroed during every selloff. On 2026-07-24 the
basket shed 10 points of participation in 20 sessions while SMH fell 11.9% and
Warning printed exactly 0. v3 tapers to a floor instead: deterioration counts
fully when price masks it (true divergence, the dangerous pre-top case) and at
35% when price confirms it. Breadth *level* lives in State, but breadth
*velocity* appears nowhere else, so this is not double counting.

**Bands are per axis.** v2 Warning never exceeded 64.9 in 408 sessions while
State reached 91.2, yet both used 30/60/80 with quadrant dividers at 60. The
upper half of the Warning axis was unreachable.

## Outputs

**State** — current structural stress:

- Price structure, 40%: `max(P1, P2, P3)`, one capped vote for correlated reads.
- Fixed-basket breadth level, 25%.
- HY option-adjusted credit spread level, 20%.
- VIX level, 15%.

**Warning** — deterioration and divergence:

- Fixed-basket breadth divergence, 45%.
- 60-session SMH/SPY relative-strength deterioration, 30%.
- HY OAS 20-session widening, 25%.

Combined, RSP/SPY (former F4), and the NVDA canary (former P6) do not enter v3.

## Calibration

P3 drawdown anchors, as (drawdown %, score): 0→0, 4→10, 8→25, 16→50, 28→78,
40→100, flat outside. Credit impulse is relative (+35% over 20 sessions = 100)
rather than absolute, because +0.5pp means something very different at an OAS of
2.7 than at 8.0.

Bands are round, meaning-anchored numbers, not percentile fits — percentile
thresholds would drift on every rebuild and silently rewrite what past snapshots
meant. Realized shares over the calibration window:

| Axis | stable | watch | elevated | breaking | thresholds |
|------|--------|-------|----------|----------|------------|
| State | 73.3% | 15.0% | 8.3% | 3.4% | 20 / 50 / 80 |
| Warning | 69.4% | 19.6% | 7.6% | 3.4% | 20 / 40 / 60 |

Quadrant dividers sit at each axis's watch/elevated boundary: State 50,
Warning 40.

Scores renormalize over available fixed weights, but a band is published only at
75% or greater coverage. Trend deltas are suppressed when the participating
pillar set changes. Zero means ordinary/healthy; only stress contributes.

Credit level is the named HY OAS anchors alone: 3.5 mild, 5.0 elevated, 7.0
stressed, linear between, and nothing else. v2 blended those anchors at 70% with
a 30% upper-tail percentile over a nominally 10-year window.

That leg was removed rather than repaired. ICE restricted FRED to a rolling
3-year window for `BAMLH0A0HYM2` in April 2026 — the series metadata states it
outright ("Starting in April 2026, this series will only include 3 years of
observations"), and an unbounded request returns the same 795 observations as a
30-year one. The v2 percentile therefore ranked the current spread against three
uniformly tight years (range 2.59–4.61 over the calibration window), which made
it fire early and saturate absurdly: at an OAS of 3.50 — the level the anchors
call *mild*, scoring zero stress — the blended sensor read 20.1, and the
percentile leg pegged at 100 by an OAS of 4.5. Across the 408 sessions it
roughly tripled the credit sensor's average (2.70 vs 1.00) and more than doubled
its nonzero days (60 vs 27).

The anchors already encode the long-run distribution as constants, so the
percentile was a second, noisier estimate of the same thing. What it was
genuinely reaching for — "unusual versus recent history" — is now W3 on the
Warning axis, computed as a rate of change, which is where deterioration
belongs. Removing it moved State's average by −0.4 and its maximum by −3.8, left
Warning bit-identical, and did not shift any band threshold.

A long-history alternative (`BAA10Y`, Fed-published, 7,712 observations back to
1997) was considered and rejected: ranking an HY spread against investment-grade
history is not a coherent statistic, and it would rescue a leg that is redundant
anyway.

Every snapshot now records `data_quality.credit_history_days` and
`vix_history_days`. This defect was invisible for roughly three months because
nothing asserted the window the code claimed; the spans make a future upstream
truncation show up in the record instead of quietly reshaping a sensor.

**Survivorship caveat.** The basket was frozen 2026-07-15 but the calibration
window reaches back to 2024, so names were partly selected for having done well.
Every distribution above inherits that bias. It is the same bias v2 carried, so
the v2/v3 comparison is like-for-like, but the absolute band shares are
optimistic.

## Point-in-time record

The first run under a new `METHODOLOGY` rebuilds the latest 400 trading sessions
with sufficient sensor warm-up; routine runs thereafter insert/update only the
latest trading date. The history API and main chart show only snapshots matching
the current methodology, so a bump reseeds the series rather than splicing two
formulas into one line.

The fundamental overlay keeps its effective date (normally the next session after
collection) and is never replayed backward, so a rebuild cannot stamp today's
observation onto historical snapshots. Because the observation is stored in a
single slot, a refresh replaces the previously effective record: the snapshot
therefore reports the overlay as `pending` until the new effective date.

Two functions, deliberately: `fundamental_overlay` is the **record** and keeps
the gate — it runs for every replayed date during a rebuild, so it must never
grow a bypass flag. `current_observation` is the **live reading** behind
`fundamental_context`, and *reports* the effective date instead of blanking the
content.

Until 2026-08-07 the live reading called the gated function, so a just-collected
observation stayed hidden until the next weekday — three days over a weekend —
and refreshing appeared to do nothing. That was the opposite of what this section
already claimed. Showing it early cannot leak into a published number, because
nothing in the overlay is scored (see "Fundamentals left the score").

`current_observation` gates on `observed` (a non-null `fetched_at`, the one field
every path writing real content stamps). Without it, the default override —
`unknown` for every hyperscaler and `mixed` for the reaction — was reported as a
live observation with `available: true`, so the card presented placeholders as a
collected reading. Those are the absence of an observation, not an observation of
absence. `fundamental_overlay` never had this problem: no observation means no
effective date, which means `pending`, which already blanks the content.

Each snapshot stores the fixed basket symbols, hash, and freeze date.
Reconstructed history before that freeze date is retrospective/exploratory.

## Presentation

The page is deliberately thin: two gauges, one chart card, one pillar table, the
overlay, and a provenance strip. Time and Path are two projections of the same
snapshot series and share one card and one query key — they were previously two
panels, which read as two datasets. Methodology rationale lives in this document,
not on the page; page text is limited to what changes how the reader interprets
today's number. The quadrant dividers rendered in Path view come from
`quadrant_config` and are the same constants the alert path consumes
(`alert_service`), so the chart cannot drift from what actually fires.

## Warning study

The study calls the outcome a **10% correction**, not a regime break. The first
70% of sessions freezes the 80th-percentile warning threshold; alarm episodes are
measured on the final 30%. Because v3 dropped fundamentals from the score, the
study now measures exactly the live Warning score rather than a technical-only
approximation of it, and both are computed from one shared sensor definition
(`warning_sensor_scores`) so they cannot drift apart.

A cached report is discarded when its methodology no longer matches, so the panel
reverts to "not run yet" after a bump rather than showing stale numbers. **Re-run
the Event Study job after cutting over to v3.**

### Reading the result

The report carries a `reliability` block and the UI renders its warnings, because
the headline numbers invite over-reading in two specific ways.

**The holdout is thin.** The study detects 11 corrections across 5 years but the
70/30 split leaves only 4 in the test period. Recall is therefore one event away
from a materially different headline, and in practice the event that flips is
decided by where the frozen threshold happens to land rather than by whether the
score saw anything. The v3 cutover run illustrates it: v3 scored 2/4 against v2's
3/4, but "v3 without the credit sensor" scores 3/4 at a *higher* threshold
(35.5) than shipped v3 misses it at (32.3) — because the alarm rule needs a
rising edge, and a lower threshold can mean the alarm already fired outside the
20-session horizon and never reset below. Below `MIN_EVENTS_FOR_CONFIDENCE`
holdout events the report says so explicitly.

Some events carry no information at all for comparison: in that run every
variant caught 2026-03-06, every variant missed 2026-06-05, and every variant
"caught" 2025-11-20 with a 1-session lead, which is coincident rather than a
warning.

**Sensor coverage can straddle the split.** The score renormalises over available
sensors, so a training window predating a sensor's history freezes the threshold
on a different construct than the holdout is measured against. At the v3 cutover
only 39% of training sessions had all three Warning sensors versus 100% of the
test period, because credit history begins 2023-07-25.

Restricting the threshold to sensor-matched training sessions was tried and is
*not* the fix: those sessions are a calm recent stretch, so the threshold drops
from 32.3 to 22.5 and false alarms rise from 3.3 to 8.6 per year. It trades a
coverage bias for a regime-selection bias. The honest position is that the
threshold is hypersensitive to window choice at this sample size; the report
states its limits rather than pretending to a precision it does not have.

## Open calibration questions

Raised 2026-08-07 during the page refactor. **None are implemented.** Each one
changes a published score, so acting on any of them means cutting `METHODOLOGY`
to v4 — which reseeds 400 sessions and discards the cached event study. They are
recorded here rather than hand-patched into v3.

**1. State's top band is a credit-event band.** `f2_credit_spreads` returns
`0.0` — not `None` — for any OAS below the 3.5 mild anchor, so credit stays
*available* at weight 20 and is not renormalized out. It is simply pinned at
zero. Verified: with price, breadth and volatility all pegged at 100 and OAS at
the cutover's 2.77, State computes to exactly **80.0** at 100% coverage — the
"breaking" threshold to the decimal. So the top State band requires either a
credit event or all three remaining pillars simultaneously at maximum. A pure
AI/Tech drawdown with calm credit — the scenario this monitor exists to
measure — cannot print it with anything to spare. Anchors-only credit was
nonzero on 27 of 408 calibration sessions, so that 20-point weight sits at zero
roughly 93% of the time. This is structurally the same defect v3 corrected on
the Warning axis ("the upper half of the Warning axis was unreachable"), and it
means the State bands were fit against a v2 credit distribution that v3 no
longer produces.

**2. V1 saturates at VIX 30.** `(vix - 15) / 15 * 100` reaches 100 at VIX 30 and
has no resolution above it: VIX 30, 50 and 82 all score identically. That is the
same failure mode, at a similar percentile, as the `dd_pct * 5` formula this
version replaced for pegging at a 20% drawdown. If addressed, it should get an
anchor table in the P3 style rather than a rescaled slope.

**3. `max(P1, P2, P3)` defeats P3's anchoring.** The `max` is deliberate ("one
capped vote for correlated reads"), but `_under_200` is binary, so P1 prints 100
whenever SMH and QQQ are both below their 200-DMA. P3's anchor ladder therefore
only resolves anything while price is *above* the 200-DMA — that is, before the
drawdown it measures is underway. Note also that "P3's realized share of State
falls from 65% to 40%" is argmax-share accounting, which is a slippery statistic
under `max()`.

## Fixed 2026-08-07: the OAS fetch window did not cover a rebuild

`HY_OAS_WINDOW_DAYS` was 400 **calendar** days, but a rebuild replays
`leader_series[-REBUILD_SESSIONS:]` — 400 **trading** sessions, about 579
calendar days. The oldest ~180 calendar days of any rebuild therefore got no OAS
data at all, so `f2_credit_spreads` and `w3_credit_impulse` both returned `None`.
Verified: State then lands at 80% coverage and Warning at exactly 75.0% —
`MIN_COVERAGE` — so **both still publish bands**. The rebuilt series would look
homogeneous while its oldest rows had been scored without credit, the tell being
a null `data_quality.credit_history_days` on exactly those rows.

The window is now 700 days: it must cover the oldest replayed date (~579) plus
W3's lookback and slack, while staying under ICE's ~3-year cap so FRED still
honours the request. This required **no methodology bump** — C1 reads
`oas_values[-1]` and W3 reads `oas_values[-21]`, both indexed from the end, so
widening only prepends older observations and every live score is bit-identical.
Confirmed by evaluating both windows against a varying synthetic series: today's
C1/W3 match exactly, while the oldest rebuild row goes from `None`/`None` to real
values.

Expect `credit_history_days` on new snapshots to rise from ~400 to ~700. That is
the widened request, not new upstream history — and it makes the chip a better
truncation canary, since a 700-day request returning ~1095 days' worth is now
the visible ceiling.

**Widening the window alone does not repair stored history.** Routine runs
recompute only the latest trading date, and `rebuilding` was keyed on "no v3
snapshot exists at all" — which is false once the cutover has run — so every row
already written would have kept its credit gap indefinitely. `SENSOR_REVISION`
fixes that: it is stamped into each snapshot, snapshots predating it read as 1,
and a stored revision below the current one triggers exactly one reseed.

It is deliberately not `METHODOLOGY`. That constant partitions the history API
and discards the cached event study; neither is warranted here, because the study
recomputes its Warning series from source (`_warning_series` calls
`warning_sensor_scores` against freshly fetched prices and OAS) rather than
reading snapshots, so a reseed cannot stale it.

The reseed is bounded by `REBUILD_LOOKBACK_DAYS` in calendar days rather than a
session count, because the binding constraint is the OAS fetch: each replayed row
needs W3's 20-business-day lookback inside `HY_OAS_WINDOW_DAYS`. At 672 days the
replay reaches ~464 sessions, W3's oldest requirement lands exactly on the first
fetched OAS day, and the ~400-session series the v3 cutover wrote is fully
covered. A test asserts that relationship so the two constants cannot drift into
recreating the gap.

The fix was sequenced deliberately: acting on items 1–3 above bumps
`METHODOLOGY`, which fires `rebuilding`, which would have baked the credit-less
rows into the fresh series. Fixing the window afterwards would mean reseeding
twice.

## Operator rule

Quadrant alerts default off for new/reset configurations. When enabled they
require fresh inputs, at least 75% coverage on both axes, two consecutive daily
confirmations, hysteresis, and cooldown. Every alert states: **Risk thermometer —
not a trade signal.**