Quantmodel · Research
Exploratory campaigns, experiments, and negative results. Playable and labeled — not official catalog admission.
2026-09-04
completed Research 1598 recessionalert research_campaign proxy trendex
SHA-pinned PRO>Trendex Charts page discloses three DEM++ stop horizons, diffusion 0-3 staging, and 20y duration-exceedance probabilities with 85%+ conviction gated on crosses, without a stop formula or on-row assets. Twenty-nine labeled close-only public proxies plus related off-
2026-09-04
completed Research 1599 recessionalert research_campaign proxy trendex
SHA-pinned Trendex guide discloses end-of-day three-horizon stops, 0-3 diffusion with thirds sizing, trend-count exceedance conviction with a 90% gate, TOP 0-5 / BOT 0-6 scores, and an MFP reference panel, without executable formulas or on-row assets. Thirty-three labeled close-o
2026-09-03
completed Research 1587 recessionalert research_campaign lowry breadth
The SHA-pinned Lowry buy-the-dip article discloses 80/90 stacked-count Class-A/B buys without named SP-500 breadth series, sell rules, or asset SHA256. Twenty-one labeled UVOL/DVOL public-proxy overlays were tested with causal lag>=1; disposition exploratory_tested_proxy under Ot
2026-09-03
completed Research 1589 recessionalert research_campaign nber coincident
The SHA-pinned NBER co-incident article discloses 4 monthly inputs, 6m/3m/3m-0.415/12m growths, syndrome thresholds, 17/31/30/12/10 composite weights, and 0.10/0.40 Probit thresholds without Moore formula, deflator pins, or Probit coefficients. Eighteen labeled FRED-proxy overlay
2026-09-03
completed Research 1576 recessionalert research_campaign proxy gen1
SHA-pinned PRO>SP500 Charts page discloses Gen-1 Diffusion/top-3 cues, Gen-2 horizons 6/17/34/68, and ST-ALGO lag/latch hints without DEM++, closed-form maps, or on-row assets. Twenty-nine labeled close-only public proxies plus related off-row WeeklyData MF/GEN-2 overlays were ex
2026-09-03
completed Research 1586 recessionalert research_campaign hilo breadth
SHA-pinned RecessionAlert HiLo page discloses daily 13w/52w net-highs% and HiLo=diff smoothed plus HiLo Fast, 5-level warnings, Diffusion 0-5 and -5 reversal, but smoothing constants, denominator timing, confirmation/hold mapping and asset SHA256 are undisclosed. Thirty labeled N
2026-09-03
completed Research 1575 recessionalert research_campaign spm sp500
The SHA-pinned SPM V1.0 page describes a 6-factor percentile-rank diffusion model for S&P 500 correction bottoms using drawdown, duration, bull traps, consecutive down-weeks, VIX, and a proprietary modified DeMark count. Twenty-four proxy variants tested across VIX de-trending me
2026-09-03
completed Research 1565 recessionalert research_campaign sahm proxy
SHA-pinned SAHM Rule Redux MODELS article discloses multiple Sahm constructions without page-local assets or portfolio mapping. Six labeled UNRATE proxy variants executed with causal lag>=1; disposition exploratory_tested_proxy with explicit NO-GO for native fidelity.
2026-09-03
completed Research 1549 recessionalert research_campaign proxy optimum
SHA-pinned PRO>OPTIMUM page discloses an OPTIMUM/STM/OPT-D dashboard without formulas or on-row assets. Twenty-six labeled public month-end proxies plus related off-row OPTIMUM_DATA.xlsx overlays were executed with causal lag>=1; disposition exploratory_tested_proxy under Other/R
2026-09-03
completed Research 1547 recessionalert research_campaign proxy pct
SHA-pinned PCT/Gen2 page discloses four zig-zag horizons, PCT expand-x, and ST-ALGO lag/latch hints without a closed-form map or on-row assets. Twenty-nine labeled close-only public proxies plus related off-row WeeklyData GEN-2 overlays were executed with causal lag>=1; dispositi
2026-09-03
completed Research 1556 recessionalert research_campaign usmlei probability
The SHA-pinned USMLEI probability-enhancements article describes four recession-probability models and preferred top-2 aggregation without disclosing coefficients or trading rules. Eighteen labeled offline USMLEI_V2 / public-proxy overlays were tested with causal lag>=1; disposit
2026-09-03
completed Research 1536 recessionalert research_campaign proxy optimum
SHA-pinned New Optimum Market Timing page discloses an OPTIMUM family catalog without formulas or on-row assets. Twenty-five labeled public month-end proxies plus related off-row OPTIMUM_DATA.xlsx overlays were executed with causal lag>=1; disposition exploratory_tested_proxy und
2026-09-03
completed Research 1617 recessionalert research_campaign proxy ushmi
SHA-pinned USHMI page discloses eight-component housing mainline/diffusion and a 10s/1s AND-combo without formulas, weights, native series, or on-row assets. Labeled PERMIT/HOUST YoY diffusion and DGS10−DGS1 proxies were executed with causal lag>=1 on SPY/IEF month-end overlays;
2026-09-03
completed Research 1555 anxiety-index spf recessionalert other-indicators
Published a fail-closed Other-indicators specification for the SHA-pinned RecessionAlert Anxiety Index page (91b3792b): SPF Anxious Index RECESS2 with disclosed threshold 28.2, never-revised quarterly→monthly publication mapping, native 1968Q4→2026Q2 / effective monthly 1968-11→2
2026-09-03
completed Research 1554 recessionalert research_campaign rfe-6 recession
The SHA-pinned RFE-6 article discloses a six-model ensemble and SPX cash@RFE>=3 / reenter-on-decline-1 rules without component formulas. Eighteen public-proxy overlays were tested with causal lag>=1; disposition exploratory_tested_proxy under Other/Research with explicit NO-GO fo
2026-09-03
completed Research 1550 recessionalert research_campaign ravi valuation-risk
The SHA-pinned PART-3 article describes RAVI target distances and a short-term risk zone without disclosing native construction. Twenty-eight public valuation, trend, liquidity, and related-workbook overlays were tested with causal lag>=1; disposition exploratory_tested_proxy und
2026-09-03
completed Research 1528 recessionalert research_campaign proxy monthly-charts
SHA-pinned Monthly Charts page discloses a multi-tab monthly chart family and cadence only, with zero linked assets. Twenty-one labeled public month-end proxy variants (Sahm/LEI/VIX-YC/CMHI/macro vote/best_effort) were executed with causal lag>=1; disposition exploratory_tested_p
2026-09-03
completed Research 1473 recessionalert research_campaign proxy selling_pressure
The SHA-pinned Measuring Selling Pressure page discloses a six-component diffusion and rise-above-4/fall-below buy rule, but ships no native series and leaves most component thresholds chart-only. Fifteen labeled public-proxy variants were executed with causal lag defaults; publi
2026-09-03
completed Research 1472 recessionalert research_campaign proxy mcclellan
SHA-pinned McClellan Liquidity Indices page discloses VMCOS/STL/MTL formulas and an STL zero-cross idea but no native ADV/DECL volume. Eighteen labeled public-proxy variants were executed with causal lag>=1; disposition exploratory_tested_proxy under Other/Research with explicit
2026-09-03
completed Research 1445 recessionalert research_campaign proxy market-top-warnings
SHA-pinned Market Top Warnings page discloses HILO/HILO2/NEWHI and dashboard SELL hints but no native series. Eighteen labeled public-proxy variants were executed with causal lag>=1; disposition exploratory_tested_proxy under Other/Research, not a playable indicator.
2026-09-03
completed Research 1443 recessionalert research_campaign proxy dashboard
SHA-pinned Market & Economic Dashboard documents multi-pane gauge semantics but no native series. Sixteen labeled public-proxy variants were executed with causal lag>=1; disposition exploratory_tested_proxy under Other/Research, not a playable indicator.
2026-09-03
completed Research 1444 recessionalert research_campaign proxy market-timing
SHA-pinned 2013 Market Timing Strategies meta-article documents parallel-sleeve / SIGS / dip / Death-Power fragments but no native series. Eighteen labeled public-proxy variants were executed with causal lag>=1; disposition exploratory_tested_proxy under Other/Research, not a pla
2026-09-03
completed Research 1592 recessionalert research_campaign proxy goodbye-kiss
The SHA-pinned Goodbye Kiss page documents an S&P vs 200dma retest family with no executable price source, SMA spec, lag clock, or portfolio mapping. Seven labeled public-proxy variants were executed with causal lag>=1 defaults; all trail buy-hold SPY, so publication is explorato
2026-09-03
completed Research great-trough recessionalert trough-detector fail-closed
Published the fail-closed Great Trough Detector specification from SHA-verified offline fixtures (project page af1b726b plus siblings d909e1ae/c3ab47de/e6cafff2 and WeeklyData.xlsx fc2be5f1): disclosed 27.4/10/80 Class A/B semantics, native and effective spans 2015-03-26 to 2026-
2026-09-03
completed Research 1597 recessionalert research_campaign proxy timing-entry
The SHA-pinned timing-entry page documents a 7-tool bear-bottom re-entry toolkit with no executable formulas, named series, vintages, lags, or portfolio mapping. Thirteen labeled public-proxy variants were executed with causal lag>=1 defaults; publication is exploratory Other/Res
2026-09-02
completed Research 1412 recessionalert research_campaign proxy gen2
The SHA-pinned Gen2 application note documents Zig-Zag rank probabilities and diffusion scoring but no native numeric series. Twenty-four labeled public-proxy variants were executed with causal lag>=1 defaults; publication is exploratory Other/Research only.
2026-09-02
completed Research 1429 recessionalert research_campaign proxy selling_pressure
The SHA-pinned Improved SP-500 Selling Pressure page adds a seventh DeMark BUY-setup component and retains >=5 component buy hints when diffusion drops below 4, but ships no native component/diffusion series. Fifteen labeled public-proxy variants were executed with causal lag def
2026-09-02
completed Research 1382 recessionalert research_campaign proxy mega
The SHA-pinned MEGA major-bottoms MODELS page discloses eight trough sub-models, partial panic-flush thresholds, and a 15-session 3–4 model agreement rule but ships no native MEGA SIG series. One hundred sixty-four labeled public-proxy variants were executed on a 1993–2026 SPY/^V
2026-09-02
completed Research 1380 recessionalert research_campaign proxy buy-the-dip
The SHA-pinned March 2021 BUY-THE-DIP survey discloses four complementary families (ZBT, GTR, SIGS, Trendex) with qualitative buy rules but no native SIGS/Trendex tables or complete execution map. Thirty-four labeled workbook-replay and public-proxy variants were executed with ca
2026-09-02
completed Research 1379 recessionalert research_campaign proxy demark
The SHA-pinned DeMark SP-500 article discloses modified TD-Setup Class-A/B/C rules with RA buy>=8/sell>=9 thresholds but no native setup/summation series. Twenty-four labeled public-proxy variants were executed with causal lag defaults; publication is exploratory Other/Research o
2026-09-01
Insufficient evidence Experiment
Five labeled BTC price, Mayer, momentum, and correction proxies were executed over a frozen 5,852-row Coin Metrics PriceUSD history with cached SPY/BIL sleeves. Causal lag-1 and lag-2 variants are retained, lag-zero is a control only, and no candidate establishes native Recession
2026-09-01
Completed Experiment
Yes as research_campaign proxies; no as official playable RA parity. SHA-verified Dashboard discloses SIGS/MTDIFF/FEAR/PANIC/MEGA fragments without observation tables. Eight labeled public-proxy variants were executed with lag>=1 primary policy. Publish under Other/Research; do n
2026-09-01
completed Research 1375 recessionalert research_campaign proxy cmhi
The SHA-pinned offline CMHI article discloses a daily -1..+1 composite with zero and +0.3 pivot concepts but no native observations or complete BUY/SELL rule. Thirty-three labeled public-proxy trials were executed with causal lag defaults; publication is exploratory Other/Researc
2026-09-01
completed Experiment 1351 recessionalert indicator alix inferred_proxy
Recorded the SHA-verified RecessionAlert ALIX rule and its gaps, then tested six explicitly inferred public-proxy variants over the longest checked-in monthly SPY/IEF overlap; proxy results are exploratory and not native ALIX evidence or an executable buy/sell recommendation.
2026-08-30
Insufficient evidence Experiment
No. The SHA-pinned CHARTS PRO page discloses MTLV2/DCOM medium-term factors, six long-term trough-buy counters, and Fed balance-sheet/liquidity chart interpretations, including some thresholds and schedules. It provides no source-linked numeric observations, single scalar state,
2026-08-30
completed Research 1699 pipeline research_campaign best_effort
Research pipeline now requires proxy search and at least three inferred-rule variants instead of stopping when series, rules, or lag are missing. RecessionAlert source-fidelity specs stay as documentary records; #1331–#1373 are reopened under the new contract.
2026-08-29
Insufficient evidence Experiment
No playable series. The SHA-verified May 1, 2024 article discloses OECD LEI breadth, central-bank easing breadth, reported 7- and 10-month leads, a 0.57 R-squared claim, monthly report/chart location, and qualitative buy-the-dip context, but no machine-readable observations, exac
2026-08-29
Insufficient evidence Experiment
No playable series. The SHA-verified March 3, 2016 article lists 23 monthly components, four recession-probability interpretations, a preferred average of the highest two probabilities, and Long-/Short-leading views, but provides no source-linked observations, complete transforma
2026-08-29
Insufficient evidence Experiment
No playable series. The SHA-verified March 6, 2012 article describes Google global search volume for recession as a promising indicator and fear gauge, with contextual 2008 and 2011 observations, but no machine-readable Fear series, reproducible query configuration, native span,
2026-08-29
Insufficient evidence Experiment
No playable series. The SHA-verified March 18, 2022 page describes a fifteen-model recession diffusion ranging from 0 to 15 and a documented warning trigger above five (at least six models in recession), with an approximately six-month lead objective. The checked-in snapshot has
2026-08-29
Insufficient evidence Experiment
No playable series. The SHA-verified February 23, 2016 page describes a weekly WLEI growth index built from more than 20 weekly time series across six broad categories, with claimed Thursday-afternoon publication and at most a one-week data lag, but it contains no source-linked o
2026-08-29
Insufficient evidence Experiment
No playable series. The SHA-verified September 4, 2019 article describes support/resistance trend tracking and dynamically mapped historical reversal probabilities, with top/bottom probability context, STOP, p(n), and p(n+1) labels. It contains no source-linked observations, exac
2026-08-29
Insufficient evidence Experiment
No playable series. The SHA-verified December 27, 2019 article describes annual, bi-annual, tri-annual, and quadrennial SP500 seasonality from monthly closes since 1957, rank-based composite scoring, and short/long/2x strategy text, but the snapshot contains no source-linked mont
2026-08-29
Insufficient evidence Experiment
Disclosed risk-off cash advice exists on the page, but no playable signal can be rebuilt from this row alone. The manifest-selected snapshot verified at sha256:9bead77031d36f389d1b2204111f926fce443af211023b6ccda3a4febb59000a on 2026-08-22 records the August 25, 2015 Reflections n
2026-08-29
Insufficient evidence Experiment
The checked-in page is a source-bound Bitcoin multi-model context suite rather than one executable signal. It discloses daily BOCA-3 and BOCA-4 address-accumulation cues, falling exchange balances as bullish context, a 30-minute technical overlay, Mayer Multiple thresholds (MM=1
2026-08-29
Insufficient evidence Experiment
The SHA-pinned page is a May 22, 2023 article that records eight qualitative bullish-context observations across labor, earnings, global leading data, the S&P 500 200-day average, Zweig breadth, WLEI, a Gen2 probability model, and CMHI. It explicitly says bearish data outweighs b
2026-08-29
Insufficient evidence Experiment
No. The SHA-pinned Standard Charts page discloses a multi-tab family of SP-500 trough/top probability models, TRENDEX, MCOS, HILO/HILO2, ALIX, and NEWHI formulas and directional thresholds, but no source-linked observations, single scalar identity, complete vintage policy, state
2026-08-28
Insufficient evidence Experiment
No playable series. The SHA-verified page is a November 16, 2018 article that describes the second derivative as the percentage of historical WLEI readings above the current reading and frames it as a warning with WLEI Diffusion and ECRI WLI, but it contains no source-linked obse
2026-08-28
completed Research
Implemented reproducible GARCH, GJR-GARCH, and EGARCH bottoming/sizing overlays, backtested causal variants, and published the evidence as exploratory research with no production promotion.
2026-08-28
completed Research 1038 indicators strategies best-variant public-proxy
Inventoried the 30 issue-linked experiment records and related findings, documented one best variant per distinct family, added the missing VIX/NH-NL and four Berg public-proxy families to the canonical Other-indicators signal registry, and regenerated producer-owned experiment a
2026-08-27
Completed Experiment
The causal public-data replica clears every publisher fidelity tolerance on the approximate 2001–2026 window (Sharpe 1.445 vs 1.44). It does not clear the frozen untouched 2023–2025 economic floors versus its own static beta (Sharpe improvement −0.64 vs +0.20 required). Dispositi
2026-08-26
completed Research 1312 UPRO research-campaign walk-forward leveraged-etf
Preregistered expanding annual January selection on the issue-1310 causal neighborhood. Primary local stitched OOS CAGR 12.23% with max drawdown -25.45% fails the -25% floor; safety-margin and focused-grid frozen rules still clear without full-sample parameter choice.
2026-08-26
completed Research 1313 UPRO hindsight drawdown research-campaign
The full-window UPRO/cash target is numerically attainable only with non-causal hindsight in this search: 16 oracle variants exceed 30% CAGR under the 25% drawdown cap, led by a same-session return oracle at 1,942.14% CAGR and -0.14% drawdown. None of 1,816 causal full-window fit
2026-08-26
completed Research 1310 UPRO research-campaign leveraged-etf drawdown-control
Searched conceptually diverse indicators to maximize causal UPRO/cash CAGR while keeping historical maximum drawdown at or above -25%. The exploratory winner reaches 8.32% full-window CAGR (-24.78% drawdown) and 12.75% in the actual-UPRO era. Owner feedback after review requires
2026-08-23
Completed Experiment
Yes for the supplied 2015-2026 snapshot: all four source pages and the workbook match pinned SHA-256 values, and the runner reproduces 27 Class A markers, 58 Class B markers, and 83 unique buy sessions. No for rebuilding the hidden breadth formula or exact pre-2015 dates. On this
2026-08-23
completed Research qm-09tp zweig breadth-thrust recessionalert zbt-a
Reproduced the RecessionAlert Zweig Breadth Thrust Redux (ZBT-A) from SHA-verified offline fixtures (page 6cc53ced 93502 bytes and WeeklyData.xlsx fc2be5f1) as a buy-only Other-indicators signal with 12 Redux markers 2004-05-21→2022-10-04 replayed exact, classic 0.40/0.615/10d di
2026-08-23
completed Research qm-09tp recessionalert fear-indicator google-trends
Documented the RecessionAlert Recession Fear Indicator from the SHA-verified offline page (sha256:2cb8464ee, 83313 bytes) and six workbook assets as a fail-closed public gap report: Google Trends global recession search volume is the only disclosed input, no threshold, cadence, l
2026-08-23
completed Research qm-09tp usmlei recessionalert leading-index
Reproduced the RecessionAlert U.S. Monthly Leading Economic Index from SHA-verified offline fixtures (pages dbea5c54e/508260beb and MonthlyData.xlsx 435d142f) as a continuous Other-indicators gauge (-100 to +100, 698 months 1968-05→2026-06, Oct 2022 -18.4 vs page -19.7, 210 negat
2026-08-22
Completed Experiment
Yes for historical shape, no for a live strategy. The frozen 80% event replay reaches 0.999982 correlation with the published report and matches every major rise, pause, and drawdown. But the Pine source, five signal defaults, exact input formulas, and a genuinely untouched econo
2026-08-22
completed Research trailing-stop atr volatility generic-signals experiment-harness
Extended generic trailing-stop harness with ATR and volatility-scaled variants compared against fixed percent stops on same window, costs and lag; new rows render in the experiment detail delta table and offline tests pass without live fetch.
2026-08-22
completed Investigation
Evaluated all four Berg empirical families against the frozen tradable promotion gate: no family shows a robust, causally-lagged, cost-aware, subperiod-stable overlay. Price/boundary (389 signals, 2008-2019 delta -0.70pp, overlay -10.3pp vs SPY), capitulation (183 signals, 2008-2
2026-08-22
completed Investigation
Evaluated all four Berg empirical families against the frozen tradable promotion gate: no family shows a robust, causally-lagged, cost-aware, subperiod-stable overlay. Price/boundary (389 signals, 2008-2019 delta -0.70pp, overlay -10.3pp vs SPY), capitulation (183 signals, 2008-2
2026-08-22
completed Investigation
Completed Berg F4 composite licensing/ToS assessment as deferral to open bead qm-zfl5: native Berg 30k daily feeds remain proprietary/not redistributable per ledger F4 doctrine and gap record qm-zzdt, with zero Berg tickers in data/market.sqlite; no proprietary series adopted; F1
2026-08-21
completed Research beads leverage modeled-history catalog
Path returns resolve __SYNTHETIC_LEVERED_<BASE>_<L>X__ only under an explicit modeled_history=synthetic_levered policy, keep live LETF returns on overlap, disclose daily-reset/DFF method and funding, and rebuild catalog/Meta payloads with longer pre-IPO windows.
2026-08-19
Rejected Experiment
No. All rolling windows fail vs expanding on common 1996-2026 net 10bps next_close base: Sharpe rolling 1.14-1.29 vs expanding 1.30, Sortino 1.62-1.80 vs 2.21. Regime wins only 1/5 for both 36m variants, neighbor plateau fails (>95% test), turnover higher and allocation stability
2026-08-19
completed Experiment
Wired a reusable generic opposite-signal harness for the ADL Volume Ratio buy signal qm-kdnj.2 (USI:UVOL 7616 rows 1996-04-19→2026-08-11, USI:DVOL 8643 rows 1992-01-02→2026-08-11 tradingview close_only, persisted offline via ensure_universe offline=True) and published determinist
2026-08-19
completed Experiment
Wired the qm-kdnj generic opposite-signal harness for S&P 500 breadth low HMA20 8.5/0 qm-kdnj.1 (INDEX:S5FI 4956 rows 2006-12-29..2026-08-11 tradingview daily persisted, Pine HMA20 WMA(2*WMA10-WMA20,4) crossover 8.5/crossunder 0 hw20, 18 triggers SPY-aligned 224 active) as head-t
2026-08-19
completed Experiment
Wired a reusable generic opposite-signal harness for the Fed balance-sheet ROC buy signal qm-kdnj.5 (WSHOSHO weekly W-WED 1234 rows 2002-12-18→2026-08-05 via FRED fredgraph.csv and macro_series_meta, persisted offline via ensure_macro offline=True) and published head-to-head indi
2026-08-19
completed Experiment
Recorded insufficient_evidence gap for qm-y8j-5-max-cagr-at-vol in research/findings/qm-u94t-gap-audit.md with qm-ghn0-pattern walk-forward gate (expanding annual Jan, next_close, 10/20bps, vol-band 0.8-1.2x) and public datastore provenance (data/market.sqlite close_only v5 785k
2026-08-19
completed Experiment
Audited all experiments not meeting parity+generic-baseline+persistence after qm-kdnj, published research/findings/qm-u94t-gap-audit.md listing 16 gaps with datastore provenance coverage (MAHX/MALX/NADC/MADC/MADP, HIGN/LOWN, S5FI, UVOL/DVOL, VIX/VIX3M, WSHOSHO/WALCL in data/marke
2026-08-19
completed Experiment
Wired generic opposite-signal harness for the VIX contango Pine experiment qm-kdnj.3 (VIX/VIX3M EMA50/252, sell when EMA50>EMA252, SMA-seed, 252 warmup, continuous regime) with ^VIX 9215 rows and ^VIX3M 5032 rows persisted offline in data/market.sqlite via yahoo instruments and p
2026-08-19
completed Experiment
Routed cross-cutting experiments rebuild through fallback: classified as fallback (no single strategy/indicator/data_source gate fits), mapped parity/harness/persistence gaps via scouts (site.js montage, scaffold/experiments payload gaps, SMACross-only generic baseline, sqlite v5
2026-08-18
Rejected Experiment
No. Both variants underperform on feasible OOS 2010-02-28..2026-07-31 (198m, 17 Jan signals, panel 2006-03-31..2026-07-31 245m) net 10bps next_close and across gross/2x: SPX delta -0.04367 (0.08053 vs 0.12420) and 6040 delta -0.03587 (0.06222 vs 0.09809). Vol-band 0.8-1.2x fails
2026-08-18
Rejected Experiment
Pine semantics frozen and tick-for-tick correct (HMA20=WMA(2*WMA10-WMA20,4) sparse buy impulse, 19 triggers native vs 18 SPY-aligned due to 2008-11-27 Thanksgiving bar shift and Jan28 HMA drift from holiday gap — 10.5% calendar delta not definition bug; evaluator vs direct delta
2026-08-18
Rejected Experiment
Pine semantics frozen and tick-for-tick correct (strict >22 daily raw ratio, 0 mismatches vs prior qm-4bx.17/22: both 24 triggers 259 active hw20 on 1996-04-19→2026-08-11 7616 ratios; sum5 max 5.08 never hits 22, MA 3/5/10/20 collapse to 0, evaluator vs direct delta 0, pinned 15-
2026-08-18
Rejected Experiment
Pine semantics are now frozen and tick-for-tick correct (SMA-seed EMA, continuous regime, 252-bar warmup). Date-fidelity audit vs prior 4-point ensemble (qm-4bx.15 spot3m_ratio sma10 quantile0.80) shows 31.9% mismatch (1528/4785 dates, prior 12.2% active vs 43.2% active, 75 vs 88
2026-08-18
Rejected Experiment
Pine semantics are frozen and fixture-exact. On 5,391 finite native dates (2005-03-15 through 2026-08-17), the corrected regime is risk-off on 1,812 days (33.61%) with 28 entries. Holding inputs fixed, prior SMA50(raw)<0 differs on 401 days (7.44%); the actual HIGN/LOWN legacy di
2026-08-18
Investigate-only Experiment
Pine ROC5>4.8 frozen tick-for-tick (L7 ffill, 57 triggers 186 active). Generic head-to-head on 2002-12-18→2026-07-24 same window/costs/lag next_close +10bps via next_close 10bps: SMA200 Δ47.39% (6.6394→9.7858), SMA50 Δ34.63%, cross Δ50.21%, trailing Δ62.83%, BH Δ0%. Signal is spa
2026-08-18
completed Experiment
Re-audited the Pine cumulative NH-NL z50 regime on its maximal native span, quantifying 401 of 5,391 same-input date mismatches (7.44%) and 711 of 5,359 actual-legacy mismatches (13.27%), then published rejected experiment qm-kdnj.4 with 257 real monthly equity/signal points, 56
2026-08-18
completed Investigation
Recorded Berg proprietary-data boundary gap at research/findings/qm-zzdt-berg-proxy-boundary-gap.md: lists 30k Berg proprietary feeds as non-redistributable per qm-zfl5/qm-m1ib/qm-is3q with 4 miltonberg.com citations, public proxies HIGN/LOWN/S5FI/UVOL/DVOL already persisted in d
2026-08-17
Rejected Experiment
No. Primary SPY rolling 252d percentile <=5th proxy (389 signals 1994-2026, 4.77% sparse) beats unconditional overall (mean fwd20 T+1 1.45% vs 0.92% delta +0.52pp hit 62.7% false 37.3% vs near-boundary event pct5-10th -0.51% hit 49.3% delta +1.96pp) and retains at T+2 (-0.04pp t
2026-08-17
Rejected Experiment
No. Primary SPY 1-day return <= -2.5% capitulation proxy (183 signals 1993-2026, 2.17% sparse) beats unconditional overall (mean fwd20 T+1 2.03% vs 0.92%, delta +1.12pp, hit 67.2% false 32.8% vs event -1.5% to -2.5% 1.15% delta +0.88pp; event -1% to -2.5% same) and retains at T+2
2026-08-17
Rejected Experiment
No. Primary HL Zweig breadth thrust proxy (10d HIGN/(HIGN+LOWN) low 0.40 -> high >=0.615 within 10d, 221 signals 2001-2026, 3.5% sparse) beats unconditional overall (mean fwd20 1.47% vs 0.92%, delta +0.55pp, hit 72.9% false 27.1% vs event high-only 0.73% vs 0.73% event n=4192) an
2026-08-17
Rejected Experiment
No. Proxy count>=2 composite (dist>4% & |z|>1.5, vol_z>2, |ret10|>5%) beats unconditional (mean fwd20 1.86% vs 0.94%, hit 64.8% false 35.2% n=358, 4.4% sparse) and event 1-of-3 (0.63%) overall, but fails regime gate: 1994-2007 no edge (0.86% vs 0.87% uncond false 43.2%), 2020+ dr
2026-08-17
Completed Experiment
Reproduced: meta-max-sharpe base 10.64% vs lev2 10.32% on same 1991-385m window (mechanical 2x would be 21.78%). No display/annualization bug (diff 0.0). Order: sleeve levered path returns before aggregation, post-filter renorm. Selection changes ~31% months (38->10 sleeves). Gap
2026-08-16
completed Research qm-p0m
Extended the Signals/risk-off aggregate to start at the earliest constituent, computing per-date contemporaneous maximum with stepped max line, shaded unavailable region and both raw count and normalized % (so 7 of 8 is distinct from 7 of 10) to keep charts readable as coverage g
2026-08-16
completed Research qm-p0m
Added per-tile enable/disable controls that immediately recompute the top aggregate and contemporaneous maximum from the selected set, showing k-of-n selected plus select-all/clear/restore defaults with normalized risk over enabled signals only (static, no server). Commit 5922b39
2026-08-16
completed Research qm-p0m
Replaced the indicator dropdowns with always-visible sortable tiles showing compact red/green histories and producer-computed hit rates, % time off/on, firing frequency and event counts (e.g. 67% (20/30)) at an explicit horizon so metrics are comparable and default ordering is do
2026-08-16
completed Research qm-5aw
Track retired task routes in shared artifacts (qm-5aw) (#821)
2026-08-16
completed Research qm-j3z
Require comprehensive Markdown PR descriptions (#815)
2026-08-16
completed Research qm-cyt
reopen stale worker assignments (#814)
2026-08-15
Insufficient evidence Experiment
Insufficient evidence: hypothesis, vol definition (annualized vol + MaxDD/downside rationale), distinctness, and frozen protocol complete; kernel extension not yet executed so quantitative evaluation pending via qm-7ad/qm-5ak.
2026-08-15
completed Research qm-xz0
Made SPYST a first-class refresh source on its real publication cadence — retrieve → extract → parse → validate → save → allocation → strategy/Meta rebuild — with expected-cadence modeling, late-mail distinction from no-update, explicit carry-forward policy and alerts on Gmail/fo
2026-08-15
completed Research qm-xz0
Kept representative historical email/chart fixtures across consensus states to test the full email → image → parsed signal → target allocation path offline, so a publisher layout change fails loudly without hitting Gmail or the tracked SQLite cache. Commit f99650c2 added 386-line
2026-08-15
completed Research qm-xz0
Ran the parser over historical emails with known interpretations to measure state/allocation accuracy, success count and manual-review rate; ambiguous, out-of-range or layout-changed mail is flagged for review and corrections are retained as fixtures so a publisher layout change
2026-08-15
completed Research qm-xz0
Kept allocation out of the image parser by verifying that parser consensus/signal fields reproduce historical SpystConsensus/SpystVixConsensus weights on fixtures, with documented thresholds, transitions and hysteresis. Commit 65223265 added research/spyst_signals/allocation.py (
2026-08-15
completed Research qm-7ad
Added run_max_cagr_at_vol_walk_forward to research/optimizer3_meta.py and ASMetaTargetCAGR classes to backtest/meta_strategy.py, wiring runners and making the export produce two new strategy payloads with weight invariants and vol-band checks. Commit 6048fd68 touched 5 files (601
2026-08-15
completed Research qm-xz0
Added deterministic SPYST chart extraction handling attachments, inline MIME and referenced images with provenance (id, timestamp, sender, subject, chart, parser version) and a versioned schema for consensus state, long/neutral/defensive and confidence — keeping portfolio rules o
2026-08-15
completed Research qm-p0m
Made every risk-on/buy trigger unambiguous by adding aligned underlying-indicator panes (same X range) beneath each risk-on chart showing the series vs threshold (e.g. Fed WSHOSHO ROC vs 4.8%) with crossings lined up to SPY markers. Commit 6682b536 extended docs/assets/js/charts.
2026-08-15
completed Research qm-rjo
Removed the low-value Compare surface (docs/compare.html, docs/assets/js/comparison.js and Compare nav links/Home/Catalog shortcuts) leaving only reusable helpers still referenced, with no broken links. Commit efa1b9e1 deleted 428 lines of comparison.js, 47 lines of compare.html
2026-08-14
completed Experiment qm-03q
fix shared artifact manifest expectation drift (include experiments payl
2026-08-14
completed Research qm-mli
rebuild dependents and commit only successful refreshes (#794)
2026-08-14
completed Research qm-9b0
extract signals from newly ingested SPYST Gmail messages (#792)
2026-08-14
completed Research qm-arn
capacity and financing at levered scale — cost band and ADV gates (#79
2026-08-14
completed Research qm-2jmc
prototype commodity/trend sleeve without DBC/PDBC (gap 3) - CTA ETF exa
2026-08-14
completed Research qm-arn
gate weak sleeves by levered marginal contribution (#788)
2026-08-14
completed Research qm-mli
document one due-source refresh command for cron and humans (#785)
2026-08-13
completed Research qm-95x
Visualize research execution pipeline (qm-95x) (#782)
2026-08-13
completed Research qm-vck
Build process-driven research execution graph (qm-vck)
2026-08-13
completed Research qm-4bx
auxiliary buy overlay integration framework — max-long takeover acros
2026-08-12
Rejected Experiment
TL;DR VIX term-structure backwardation (spot VIX > VIX3M) and a 4-point curve ensemble (VIX9D 9d, VIX 30d, VIX3M 93d, VXV 6M synthetic) are classic risk-off signals. After maximal Yahoo+TradingView ingest (1990-2026), OLS synthetic extension for VIX3M/VIX9D pre-history (R² 0.95/
2026-08-12
Rejected Experiment
TL;DR Net new highs minus new lows (NH-NL) breadth SMA50<0 as SPY risk-off (cash/SH) was tested as daily nextclose +10bps sleeve. After maximal TV ingest (INDEX:HIGN/INDEX:LOWN 2001-06-05→2026-08-11, 6331/6312 rows) plus synthetic 52-week high/low reconstruction from 9 sector SP
2026-08-12
Rejected Experiment
TL;DR NYSE ADL Volume Ratio USI:UVOL / USI:DVOL daily >22 is a sparse (24 triggers in 30y, 0.3% days, 3.4% active at 20d holding) buy-only capitulation impulse that forces max long SPY for a holding window. After maximal TV ingest (UVOL 1996-04-19→2026-08-11 7616 rows, DVOL 1992
2026-08-12
Rejected Experiment
TL;DR S&P 500 breadth washout (INDEX:S5FI % above 50dma) with HMA20 crossing up through 8.5% after washout or under 0% (mega washout) is a buy-only capitulation impulse that forces max long SPY for a holding window. After maximal TV ingest (2006-12-29→2026-08-11, 4956 rows) plus
2026-08-12
Rejected Experiment
TL;DR Fed balance-sheet liquidity impulse (WSHOSHO 5-day ROC >4.8%) is a buy-only auxiliary overlay that forces max long SPY for a holding window. After maximal FRED ingest, weekly→daily forward-fill with publication lag L=7–10d, and daily nextclose+L causality via runbacktest,
2026-08-12
completed Experiment qm-z5o
audit and fix Experiments hub — per-experiment graphs/stats, filter to t
2026-08-12
completed Research qm-dol
leverage-friendly re-evaluation with relaxed edge-retention gates (#774)
2026-08-11
completed Research qm-4bx
Route research framework improvements (qm-4bx.8) (#749)
2026-08-11
completed Research qm-q40
Document SCHD VEIPX history no-go (qm-q40) (#743)
2026-08-11
completed Research qm-wwl
Evaluate exact leverage candidates (qm-wwl.2) (#741)
2026-08-11
completed Research qm-wwl
Evaluate conditional leverage variants (qm-wwl.3) (#740)
2026-08-11
completed Research qm-yln
Prefer daily paths for maximum drawdown (qm-yln) (#738)
2026-08-10
completed Research qm-4bx
Finalize candidate integration decision (qm-4bx.7) (#736)
2026-08-10
completed Research qm-4bx
Evaluate GTAA production mix walk-forward (qm-4bx.7.1) (#735)
2026-08-10
completed Research qm-4bx
Evaluate defensive regime candidates (qm-4bx.4) (#732)
2026-08-09
Rejected Experiment
Decision
2026-08-09
completed Research qm-2cn
Distinguish failed leverage feeds from empty cohorts (qm-2cn.5) (#728)
2026-08-09
completed Research qm-2cn
Add leverage surface browser regression suite (qm-2cn.7) (#726)
2026-08-08
Rejected Experiment
Decision
2026-08-08
completed Research qm-4bx
Evaluate cross-sectional factor candidates (qm-4bx.5) (#718)
2026-08-08
completed Research qm-4bx
Evaluate GTAA momentum candidates (qm-4bx.3) (#716)
2026-08-08
completed Research qm-shd
Preserve Beads JSON stdout for cron claims (qm-shd). (#714)
2026-08-08
completed Research qm-pft
Register labelled Turbulence and Macro-aware RP proxies (qm-pft.3). (#713)
2026-08-08
completed Research qm-bc5
Clip risk-off-spy ITD to common full-panel gauge start (qm-bc5). (#707)
2026-08-07
completed Research qm-sal
Add quiet CLI wrappers for noisy agent shells (qm-sal.3). (#700)
2026-08-07
completed Research qm-sal
Document quieter/narrower tool-call context savings (qm-sal). (#684)
2026-08-07
completed Research qm-djb
require consumer-needed entry fields at load (qm-djb). (#689)
2026-08-07
completed Research qm-sal
Lean bd prime bootstrap via .beads/PRIME.md (qm-sal.1). (#687)
2026-08-06
completed Research qm-1ed
Refresh shared canary sixty-forty payload after taxable_stats export (qm-1ed). (
2026-08-06
completed Research qm-99b
Refresh shared canary sixty-forty payload for SWR export (qm-99b). (#670)
2026-08-06
completed Research qm-e49
Replicate Varadi Inflation Compass Original against AS (qm-e49). (#667)
2026-08-06
completed Research qm-zkc
Add AS discover-new pipeline for untracked strategies (qm-zkc). (#666)
2026-08-06
completed Research qm-9kt
Add Python financial-planning/v2 engine with local web API (qm-9kt.4.3). (#663)
2026-08-06
completed Research qm-9kt
Drive Plan projections from monthly return series (qm-9kt.4.7). (#660)
2026-08-06
completed Research qm-1fy
Ship sigmoid risk-off→SPY mapping after qm-1fy sweep. (#655)
2026-08-06
completed Research qm-9kt
Add Plan chart retirement marker, phase shading, and depletion alert (qm-9kt.4.9
2026-08-06
completed Research qm-6og
Replicate Varadi Inflation Compass Enhanced against AS (qm-6og). (#645)
2026-08-06
completed Research qm-hm8
Add S&P (SPY) overlay to cumulative return charts (qm-hm8). (#637)
2026-08-06
completed Research qm-zl9
Align extended-history proxy tests with qm-zl9.2 SPY/VNQ hops. (#632)
2026-08-06
completed Research qm-zl9
Refresh shared canary after sixty-forty history re-export (qm-zl9.3). (#631)
2026-08-06
completed Research qm-zl9
Shrink tracked market.sqlite with close-only daily bars (qm-zl9.1). (#628)
2026-08-06
completed Research qm-72f
Clarify levered continuous-weight 100% sleeves as post-filter renormalize (qm-72
2026-08-05
completed Research qm-43l
Import Testfol/LazyPortfolio sim history into market.sqlite (qm-43l). (#626)
2026-08-05
completed Research qm-zfn
analyze BND vs BNDX for BNDX-using strategies (qm-zfn) (#625)
2026-08-05
completed Research qm-ynv
Refresh shared canary after trading-costs payload field (qm-ynv). (#607)
2026-08-04
completed Research qm-prd
Close qm-prd daily-variants epic with final inventory. (#594)
2026-08-04
completed Research qm-prd
Ship DAA/AAA/ADM/dual-momentum daily variants for qm-prd.4. (#592)
2026-08-04
completed Research qm-prd
Ship GTT/LAA/RAA/TrendYCMacro daily variants for qm-prd.9. (#591)
2026-08-04
completed Research qm-prd
Ship Faber high-switch / sector RS / Trinity daily variants (qm-prd.10) (#589)
2026-08-04
completed Research qm-prd
Ship PAA/EAA/CAA family daily variants for qm-prd.11. (#588)
2026-08-04
completed Research qm-prd
Ship switching/defense-first/Livingston daily variants for qm-prd.13. (#585)
2026-08-04
completed Research qm-prd
Ship residual misc A daily variants for qm-prd.14. (#584)
2026-08-04
completed Research qm-prd
Ship Faber GTAA daily variants for the qm-prd.5 cohort. (#581)
2026-08-04
completed Research qm-prd
Ship daily cov/opt/MCA/RPTF variants for the qm-prd.6 cohort. (#580)
2026-08-04
completed Research qm-iu0
Document Portfolio Visualizer fit for history extension (qm-iu0). (#564)
2026-08-04
completed Research qm-33x
Document Bogleheads Simba fit for history extension (qm-33x). (#561)
2026-08-04
completed Research qm-2os
Speed up research.reports build export path (qm-2os). (#544)
2026-07-30
done Research t360
Frozen 2021-04 through 2026-06 run classified the rescue branch material: 6/63 targets changed; disabling it changed correlation -0
2026-07-30
done Research t357
Closed the turbulence workstream as a rejected original candidate
2026-07-30
done Research t356
Predeclared 0/5/10/20 pp minimum target-change diagnostic
2026-07-30
done Research t334
Added immutable NAAIM normalization that rejects unresolved duplicates, requires row-specific rationale/evidence, preserves provenance, a...
2026-07-30
done Research t322
Replaced blind response
2026-07-29
done Research t311
Optimizer now retains only the current best exhaustive candidate instead of up to 100,000 metrics dictionaries and avoids the final full-...
2026-07-29
done Research t309
Coalesced identical revision-bound concurrent standard and optimized evaluations; tests prove single execution and failure recovery
2026-07-29
done Research t299
NO-GO: no operator PostgreSQL/provider credentials or fresh destination were available, so no live restore evidence is claimed
2026-07-29
done Research t296
Independent t293 comparison recorded NO-GO: eight of nine boundaries fail or lack evidence; notably 5/20 cold samples, warm p50 5
2026-07-29
done Research t294
Operator selected the existing free Render service
2026-07-28
done Research t264
Synthesized t262-t263 into a scenario hierarchy: preserve pre-tax, choose modeled account settlement, inspect taxable ongoing drag, treat...
2026-07-28
done Research t253
Added fixed-signal single-holding substitution reruns with identical common-window baseline, explicit substitution/as-of/execution/cost a...
2026-07-28
done Research replication t247
Selected Black Box Defense First from the three stored corr<0
2026-07-27
done Research replication t232
Added tested common-window Pearson matrix in selection order, with 1
2026-07-27
done Research t231
Retained t178 Optimum3 defaults after bounded SCZ-gap, rank, and corr-window grid
2026-07-27
done Research t230
Novell-only UNRATE >12m avg +0
2026-07-27
cancelled Research t208
Duplicate of concurrently added t206; keep t206 as the recurring parity-review task
2026-07-26
done Research replication t202
Fixed ITD history deletion: ALFRED econ is preferred where present and revised FRED is used outside vintage coverage
2026-07-24
done Research t178
SCZ prefer gap_at_rank1=0
2026-07-24
done Research t177
near_tie_eps=0
2026-07-24
done Research t174
SCZ←DFISX (1996+, monthly corr ~0
2026-07-24
done Research t173
MTUM←PDP 2007+; monthly corr ~0
2026-07-24
done Research t165
QQQ←^NDX free Yahoo; monthly corr ~0
2026-07-24
done Research t164
TIP←ACITX (1997+, monthly corr ~0
2026-07-24
done Research t163
HYG←VWEHX (1980+); monthly corr ~0
2026-07-24
done Research t162
LQD←DODIX (1988+); monthly corr ~0
2026-07-24
done Research t161
BIL←__IRX_TBILL_TR__ from ^IRX; monthly corr ~0
2026-07-24
done Research t160
Free hop: VNQ←IYR (~2000+, corr 0
2026-07-24
done Research t158
TLT←VUSTX default (corr 0
2026-07-24
done Research replication t168
ITD verify for gtt/link/trendycmacro; status failed OK; no 2015 restore
2026-07-23
done Research replication t126
Aspect dual 1m canary breadth=3: corr 0
2026-07-23
done Investigation t93
Black Box Defense First blocked_proprietary: AS About explicitly cannot disclose developer black-box rules (loosely Carlson DF + BTAL)
2026-07-23
done Investigation t74
GTAA5/13/Ivy disclosed on members pages
2026-07-23
done Investigation t73
EAA Def/Off ±DB disclosed: paper Golden models + AS N=7 SPY/QQQ/IEFA/IEMG/EWJ/HYG/IEF; live June MAE~1-2bps
2026-07-23
done Investigation t70
Confirmed NLX+GB disclosed (live SPY60/IEF40; GB 20%x5 VBR)
2026-07-22
done Research t9
Engine AS alignment: same_close execution, BacktestConfig
1993-01-29
Shipped-as-strategy Experiment
Shipped non-AS catalogue strategy vix-dma-edge using researched defaults from qm-wr6.1: cashonupper + meanortime (edgefreq=0.02, time=5d), nextclose, SPY + ^VIX.
parameter sensitive Research campaign parameter_sensitive useful_as_entry interesting_negative_result data_limited needs_more_research
Documented >22 impulse is sparse (~0.8/yr) and knife-edge versus 15.
interesting negative result Research campaign interesting_negative_result data_limited uninvestable needs_more_research
Exact Berg rules are untestable; public proxies failed subperiod and overlay gates.
regime dependent Research campaign regime_dependent needs_more_research data_limited
Investigate-only in prior work; keep as Research Library, not official.
interesting negative result Research campaign interesting_negative_result useful_as_portfolio_overlay predictive_not_tradable regime_dependent parameter_sensitive
GARCH-family volatility is useful as a risk state, not a standalone precise bottom oracle.
interesting negative result Research campaign interesting_negative_result needs_more_research parameter_sensitive candidate_for_confirmation data_limited
Primary local neighborhood stitched OOS CAGR 12.23% with max drawdown -25.45%; fails the preregistered stitched-path -25% floor.
useful as entry Research campaign useful_as_entry useful_as_exit data_limited fidelity_mismatch needs_more_research
Imported 53 reconstructed signals in 8 classes from the miltonberg workspace into Other → Indicators. Each card is an independent overlay, not an AllocateSmartly replica and not a claim that we replicate proprietary MB Edge internals.
useful as filter Research campaign useful_as_filter redundant interesting_negative_result
Likely redundant with trend; keep as playable negative/weak result.
data limited Research campaign data_limited fidelity_mismatch parameter_sensitive regime_dependent predictive_not_tradable
Six inferred public-proxy variants were executed on the common 2002-07 through 2026-07 monthly panel; the lag-1 12-month liquidity-level proxy is the declared descriptive baseline.
data limited Research campaign data_limited fidelity_mismatch parameter_sensitive regime_dependent predictive_not_tradable
The SHA-verified source preserves a documented 3-of-7 CMHI Diffusion-zero cash advisory, but not a playable native series or BUY/re-entry rule.
data limited Research campaign data_limited fidelity_mismatch parameter_sensitive regime_dependent interesting_negative_result
Five public proxy variants are reproducible over the longest frozen BTC history, but no candidate establishes native RecessionAlert fidelity.
data limited Research campaign data_limited fidelity_mismatch parameter_sensitive needs_more_research candidate_for_confirmation
Seven inferred/proxy variants execute over the longest checked-in SPY/IEF overlap, while the original source-faithful finding remains insufficient_evidence.
needs more research Research campaign needs_more_research fidelity_mismatch data_limited
What can be learned from the four-family BUY-THE-DIP survey using workbook replays and labeled public proxies when native SIGS/Trendex series are absent?
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result parameter_sensitive needs_more_research
The 2014 DeMark SP-500 article discloses modified TD-Setup Class-A/B/C buy and sell rules with RA buy>=8/sell>=9 thresholds and a 1-5 bar reaction hint, but no native setup/summation series or portfolio map.
fidelity mismatch Research campaign fidelity_mismatch data_limited parameter_sensitive interesting_negative_result needs_more_research
The archived article documents a daily CMHI bounded from -1 to +1, qualitative regression de-trending, and +0.3/zero pivot concepts without a complete BUY/SELL rule or native observations.
data limited Research campaign data_limited fidelity_mismatch parameter_sensitive predictive_not_tradable interesting_negative_result
The source describes a Google recession-search fear gauge but provides no machine-readable observations, exact query, native span, or executable market rule.
needs more research Research campaign
What can be learned from documented Gen2 Zig-Zag rank probabilities and diffusion when native probability series are absent from the crawl snapshot?
needs more research Research campaign
What can be learned from the documented S&P 500 vs 200-day average Goodbye Kiss retest family when the native price series, SMA specification, and publication lag are absent from the crawl snapshot?
data limited Research campaign data_limited fidelity_mismatch needs_more_research parameter_sensitive useful_as_portfolio_overlay
The Improved SP-500 Selling Pressure page adds a seventh DeMark BUY-setup component, retains >=5 component buy hints when diffusion drops below 4, and documents manual breadth +1 via Great Trough/Zweig.
data limited Research campaign data_limited fidelity_mismatch parameter_sensitive regime_dependent predictive_not_tradable
The checked-in article discloses two international breadth ideas, source-reported 7- and 10-month leads, a 0.57 R-squared claim, and qualitative dip-buying context, but no source-linked observations or complete state rule.
needs more research Research campaign
SHA-verified dashboard discloses multi-pane gauge semantics without observation tables.
needs more research Research campaign
Parallel five-sleeve proxy reduces some drawdown vs always-long SPY in causal trials but is not RA parity.
needs more research Research campaign
{'tag': 'useful_as_filter', 'text': 'Lag-1 NEWHI-style INDEX:HIGN z-score proxy shows competitive causal risk-adjusted returns among tested families.'}
data limited Research campaign data_limited parameter_sensitive weak_edge needs_more_research
Pinned offline snapshot sha256:d949a5a1… discloses McClellan VMCOS/STL/MTL formulas and an STL zero-cross buy/sell narrative.
data limited Research campaign data_limited fidelity_mismatch needs_more_research parameter_sensitive useful_as_portfolio_overlay
Measuring Selling Pressure (2013-09-10) discloses a six-component SP-500 selling-pressure diffusion, a numeric 4% peak-to-trough correction trigger, BUY when diffusion rises above 4 then falls below 4, and sell warnings on 0->1 and 1->2.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result needs_more_research parameter_sensitive
The MEGA major-bottoms page discloses eight sub-models, partial panic-flush thresholds, and a 15-session 3–4 model agreement rule, but ships no native MEGA SIG series or executable ALGO/PEV/OctaEDGE formulas.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result parameter_sensitive regime_dependent
Source is a multi-tab monthly chart family with cadence only; native series and thresholds are absent.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result needs_more_research predictive_not_tradable
Documented-intent syndrome vote (lag1) Sharpe 0.743, CAGR 0.091, DD -0.428, 14 events, risk-on 0.88 on 1992-01..2026-06; trails SPY buy-hold Sharpe 0.769/CAGR 0.108 but cuts DD from -0.508 to -0.428.
data limited Research campaign data_limited fidelity_mismatch parameter_sensitive regime_dependent predictive_not_tradable
The SHA-verified article discloses monthly component context, four qualitative probability interpretations, a highest-two preference, and Long-/Short-leading views, but not an executable signal.
data limited Research campaign data_limited fidelity_mismatch useful_as_portfolio_overlay needs_more_research
Twenty-five labeled variants executed with lag>=1 causal_primary and lag-0 control_only.
data limited Research campaign data_limited fidelity_mismatch useful_as_portfolio_overlay needs_more_research regime_dependent
Twenty-nine labeled variants executed with lag>=1 causal_primary and lag-0/look-ahead control_only.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result regime_dependent parameter_sensitive
The source is a contextual multi-tab family, not one executable indicator; disclosed formulas and thresholds are preserved separately from inferred proxies.
data limited Research campaign data_limited fidelity_mismatch needs_more_research useful_as_filter interesting_negative_result
Pinned /pro-optimum/ sha256:340dfcfa15d9 has zero on-row assets and no executable formulas.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result parameter_sensitive insufficient_events
RFD is documented as a fifteen-model 0–15 recession-warning count with a strict trigger above five, but the checked-in snapshot has no observation-level native series.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result parameter_sensitive regime_dependent
MODELS SAHM Redux article discloses multiple Sahm constructions but no page-local assets or portfolio map.
data limited Research campaign data_limited fidelity_mismatch parameter_sensitive regime_dependent predictive_not_tradable
The SHA-verified article discloses four monthly cycle families, three ranked characteristics, a composite concept, source-like short/long/2x bands, and optional cash/no-leverage language, but no source-linked signal series, scale conversion, publication clock, or complete executi
data limited Research campaign data_limited fidelity_mismatch useful_as_portfolio_overlay needs_more_research regime_dependent
29 labeled variants executed with lag>=1 causal_primary and lag-0/look-ahead control_only.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result regime_dependent parameter_sensitive
The source is a contextual multi-tab family, not one executable indicator; disclosed formulas and thresholds are preserved separately from inferred proxies.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result needs_more_research parameter_sensitive
The source-backed result is an incomplete support/resistance trend-duration and historical-reversal-probability concept; exact native observations, formula, STOP calculation, threshold, release lag, action mapping, and portfolio semantics are absent.
data limited Research campaign data_limited fidelity_mismatch regime_dependent needs_more_research interesting_negative_result
Twenty-nine labeled variants executed with lag>=1 causal_primary (26) and lag-0/same-close control_only (3).
data limited Research campaign data_limited fidelity_mismatch regime_dependent useful_as_portfolio_overlay needs_more_research
Executed 28 labeled variants across seven exploratory families.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result needs_more_research parameter_sensitive
The source-backed result is a documented weekly macro growth-index concept, not a playable native indicator: exact observations, formula, threshold, action mapping, native span, and recurring point-in-time release are absent.
data limited Research campaign data_limited fidelity_mismatch interesting_negative_result needs_more_research parameter_sensitive
The source-backed result is a warning concept only: native WLEI/WLEI Diffusion observations, exact historical rank construction, release lag, threshold, state machine, and buy/sell action are not disclosed in the selected snapshot.
useful as entry Research campaign useful_as_entry parameter_sensitive data_limited needs_more_research
HMA dependence is disclosed; SMA/EMA collapse. Sparse rescue-only overlay.
useful as filter Research campaign useful_as_filter regime_dependent needs_more_research
Prior sleeve was investigate-only; keep playable in Research Library.
Investigate-only Experiment
Investigate; do not promote. The candidate is a research-only long/cash proxy, not a registered or published strategy. Its results are sufficient to preserve a reproducible trial and support a separate portfolio-level walk-forward, but not to admit it from this evaluation.
Rejected Experiment
No variant cleared the improvement bar versus researcheddefaults (cashonupper + meanortime, edgefreq=0.02, time=5d). Catalog defaults and VixDmaEdge.researcheddefaults() stay unchanged.
Rejected Experiment
No implementation bugs found. Probability / Kelly / SH variant params change signal exits and position sizing (weight series differ). Headline metrics still look nearly identical because Kelly defensive stakes are economically small and edge days are sparse — genuinely similar, n
Rejected Experiment
No blog-fidelity accept for qm-pft.1 (search complete). Catalog registration of a labelled proxy is handled separately in qm-pft.3 as turbulence-index-proxy (search baseline defaults) — still not a Sharpe~2.20 claim. Frozen rejected t352–t356 (OriginalTurbulenceIndex) remains unp
Investigate-only Experiment
No JPMaQS/blog-panel fidelity accept for qm-pft.2. Catalog registration of the labelled US ETF + FRED proxy is handled in qm-pft.3 as macro-aware-rp-us-proxy (disclosed non-AS research variant).
Shipped-as-strategy Experiment
Ship cashonupper + meanortime (edgefreq=0.02, meanrevert=0.5%, timeexit=5d) with nextclose execution on SPY + ^VIX.