The 3% hysteresis blocked the IBIT crypto sleeve (target 2.3% < 3%) from ever entering. Hysteresis
is for damping rebalances of existing positions; first entry from zero should use a small floor.
Now all 6 instruments deploy. Verified live against the cluster ib-gateway paper account ($1M NLV):
all 6 orders present (SPY/IEF/GLD/PDBC/DBMF/IBIT). Connected via kubectl port-forward svc/ib-gateway 4002.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Runs the book on IBKR PAPER (realistic fills, no capital): gets target weights from the harness
(Yahoo), connects to IB Gateway/TWS paper, rebalances the ETF book (SPY/IEF/GLD/PDBC/DBMF + IBIT
for crypto = no exchange counterparty tail). Default dry-run (shows intended orders); 'rebalance'
places on paper. Hysteresis 3% of NLV. User runs Gateway + logs in (their creds); bot connects on
127.0.0.1:4002 (paper Gateway) / 7497 (TWS). Best paper-forward: realistic fills + real API, zero
risk. Setup steps in the docstring.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Faster confidence without waiting forward: long-history (2006-2026, 20y incl all crises) on
SPY/IEF/GLD/DBC+trend (conservative, no DBMF/crypto). Full Sharpe +0.96, maxDD -9.9%; survived
EVERY crisis (2008 +1.1, 2020 +1.4, 2022 -0.2), shallow DDs; 16/21 yrs positive. Block-bootstrap
CI: Sharpe p5 +0.62 / median +0.99 / p95 +1.34, P(>0.5)=99%. 2006-2018 quasi-OOS held +1-2/yr.
This is the weaker version (full book +1.20/+1.41 OOS). Robust across 20y + every crisis with
positive CI floor -- strongest/fastest-confirmed deliverable. Faster-confidence levers: longer
history, bootstrap, micro-live.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
User wanted to download a small open LLM and test news. Did it: FinBERT scoring 10408 FNSPID
headlines (7 tickers, 1332 obs). corr(sentiment, same-day ret) +0.082 (weak, contemporaneous);
next-day +0.026 (~0); next-day trade net 10bp OOS Sharpe +0.05 (dead). News real but reaction
INSTANT (HFT-captured); no tradeable next-day drift for retail; net of cost = nothing. Matches
Lopez-Lira/Tang + FinGPT research. Model was never the constraint -- market structure is. Closes
the news/LLM thread; deployable answer remains the adaptive multistrat book (news = risk-managed).
(note: pin transformers<5 for torch 2.6.)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
What to do with diversification? Tested sqrt(N) lever: base-6 vs expanded-12 (+REITs/TIPS/HY/intl/
EM/vol-premium). Expanded WORSE (+1.20->+1.04, 2022 +0.1->-1.4): candidates are equity/bond-beta in
disguise -> concentrate not diversify. Trust layer manages edge-health not redundancy. Genuine
uncorrelated net-positive streams are scarce; base-6 already spans the distinct premia. Diversification
is maxed in the deployable book; the lever is capital, not more streams.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
User intuited markets are connected -> exploitable? Measured equity/bond/gold/commod/trend/crypto
(2019-26): contemporaneous corr low (+0.03 avg; equity-crypto +0.43, equity-trend -0.28), crisis
corr STABLE (didn't spike -> diversification held in stress), lead-lag ~0 (trade OOS Sharpe -1.01).
Connectedness is priced-in -> value is diversification (already in the book, validates it beating
60/40 low-DD), not a predictive signal. Same efficient wall for cross-market alpha.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replaces the ~0.5-0.7 estimate with the validated 2019-2026 real-ETF backtest: +1.20 Sharpe
(realistic fwd ~0.8-1.0), -5.4% maxDD, positive every year incl 2022, beats 60/40 (+0.87/-21%)
on Sharpe AND drawdown. Robust signals: low maxDD + every-year-positive.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Backtested the EXACT live pipeline on REAL ETFs (SPY/IEF/GLD/PDBC/DBMF+BTC), 2019-2026 multi-regime.
Adaptive unlevered: Sharpe +1.20, ann +6.1%, maxDD -5.4%, positive EVERY year incl 2022. Beats
60/40 (+0.87, -21%) and equity (+0.85, -34%) with ~1/4 the drawdown. Better than the ~0.7 framing
because real ETFs (DBMF/PDBC) >> roll-zeroed futures proxies + adaptive risk layer. Caveats: Sharpe
partly low-vol-flattered (maxDD -5.4% + every-year-positive are the robust signals); 2019-26 favorable
for premia; mild param-contamination -> realistic fwd ~0.8-1.0. Modest absolute return (~.1k/yr on
5k, very smooth); lever for $ is capital. The genuine deliverable of the search, validated on real
instruments across regimes.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
User asked if advanced architectures help. Tested ML vol-nowcaster (GB proxy) vs EMA for risk-layer
de-lever timing: GB OOS vol-corr +0.09 < EMA +0.18 (EMA captures clustering better); downstream
identical Sharpe +0.72, GB maxDD slightly worse. ML doesn't help -> CfC/Mamba2 won't either (more
overfit). Return-prediction already dead (IC 0.004); TLOB's order-book signal is latency-gated.
Fancy architectures add nothing; engine value = simple adaptive risk/allocation. Simple beats fancy,
confirmed once more. Adaptive multistrat book (EMA-vol, ~0.72 Sharpe, -8.5% maxDD) is the answer.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The +14.9 OOS Sharpe was the max-min optimism (assumes daily free re-positioning to optimal venue
pair). Honest fixed-pair version (hold the entry-chosen pair, book its actual funding diff): OOS
Sharpe collapses +14.9->+0.8, OOS ann +15.3%->+1.1% (realistic ~breakeven net of cost), 0/12
configs robust OOS, feb month -8.2. Capture 0.68 was the tell (32% reshuffle loss). Cross-venue
arb joins the cost-walled/in-sample-only list. User's OOS insistence caught it. Only deployable
thing remains simple 60/40 (~0.7). Every crypto-funding variant marginal once honestly tested.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The hysteresis params were chosen by looking at the data = in-sample. Clean OOS protocol (same
that killed PEAD): pick best config on first 60% by IS Sharpe, apply EXACT config blind to last
40%. Reports IS-best -> OOS Sharpe, robustness (configs IS>2 that also OOS>1), OOS per-month.
Decisive: OOS holds -> real; OOS collapses -> in-sample fit. Monitor armed.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
(1) Live cross_venue_funding.py paper harness now uses HYSTERESIS (enter >10bp/day, hold until
spread decays <5bp) instead of naive daily top-K -> tracks the deployable low-turnover version
(naive was cost-killed -4.5 Sharpe; hysteresis nets +10-14%/yr). State reset. (2) fetch_xvenue_hist2
now paginates Binance fundingRate -> full ~330d history (was 67d) so Binance-HL overlap = full year
(330 days) for the regime test across ~11 months. Monitor armed for the full-year backtest.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Backtested the cross-venue funding arb on historical funding (Binance/OKX/Hyperliquid). Gross
+21%/yr, spreads persist (capture 0.71), but NAIVE daily rebalance is cost-killed (net Sharpe
-4.5, negative every month). HYSTERESIS (hold winners until spread decays, entry>10bp/exit>5bp)
flips net to +10-14%/yr market-neutral (Sharpe +11-15, but inflated by ~1% vol + idealized fills;
realistic ~3-6 / return ~10-14%). Turnover is the swing factor. First edge of the whole search to
survive the net-of-cost horde -- market-neutral, persistent, no spot leg (solves hedgeability),
operational not predictive. Caveats: 94d/one period, idealized fills, counterparty. Next: switch
live harness to hysteresis, deepen history to full year, micro-live.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Short high-funding-venue perp + long low-funding-venue perp (same coin) = price-neutral, collect
the funding DIFFERENCE, NO spot leg needed -> fixes the single-venue hedgeability block. Binance/
Bybit/Hyperliquid bulk funding, normalized to daily (HL is hourly!). Sanity-filtered (liquid >$10M
both legs, exclude |funding|>50bp/day distress/artifacts -- raw scan top was 9000%/yr delisting
junk). Clean spreads: ETH ~20%, ARB/ONDO ~20%, up to ZEC 167%; 16 coins >5bp/day. scan/run/status,
idempotent daily, cron 9/12/15/18 UTC. Decisive open question = PERSISTENCE (snapshot != edge;
paper-forward measures whether spreads last long enough to collect net of ~10bp fees).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
3 omnisearch researchers + clean PEAD test answer 'why does AI4Finance find what we cant':
they dont. FinRL flagship (Sharpe 1.30) = single-split, slippage-free, no-deflation, bull-market,
survivorship, hand-coded crash rule; their own people (Gort/Liu AAAI'23) published the overfitting
rebuttal; zero live track record. ML-trading decays 73%+ backtest->live, faster for complexity.
PEAD tested properly (real Nasdaq surprises x DBEQ, leak-free, 23bp cost, OOS): full-sample looked
good (20d +0.29% t=2.9) but pure in-sample bull-beta -> OOS NEGATIVE every horizon; surprise-size
signature fails. Strongest classic anomaly dies OOS. Untested real pulse left: prediction markets
(uncorrelated). Tooling: fetch_earnings.py, pead_real.py, dbeq_symbology resolved (17605 tickers).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Local CLI paper-forward test of 60% SPY / 40% IEF (ETF analog of the ES/ZN 60/40 backtest,
+0.72 Sharpe), mirroring the funding harness. Free Yahoo adjusted closes (dividends+coupons =
true total return). Subcommands snapshot/run/status. Books each real trading day once with
catch-up (handles weekends/missed runs); forward-start (no history backfill). Idempotent via
last_date. Daytime cron 12/15/18 UTC. Always-invested baseline -> confirms forward Sharpe
tracks the ~0.7 backtest, the clean no-phantom option available regardless of crypto regime.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase-2 setup (orders command) revealed 0/7 qualifying coins were hedgeable: all perp-only (no
spot leg = cannot build the delta-neutral hedge). Diagnostic: of 191 liquid crypto-native perps,
135 hedgeable / 56 perp-only. HEDGEABLE median funding -0.12bp/day, 0 of 134 clear 5bp (arbed flat
by existing cash-and-carry). PERP-ONLY median +2.59bp/day, all 8 qualifiers live there. The carry
survives ONLY where it can't be hedged. crypto_pit backtest never checked hedgeability -> the
~2-3.6 Sharpe was inflated by un-capturable perp-only funding. Fix: universe() now requires a spot
market (hedgeable only). Current regime: 0/135 hedgeable qualify -> nothing to harvest (deleverage
arbed flat). Real edge = classic basis trade on hedgeable majors: regime-dependent (rich in bull
leverage, ~zero now), more competed, lower true Sharpe than backtest. Phase-2 deploy correctly
BLOCKED by reality, not process. State reset (prior bookings were on un-hedgeable coins).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Nighttime cron (01:17 UTC) silently never fired: workstation suspends at night and standard
cron does not catch up missed jobs on wake (uptime hides suspend). Fix: (1) idempotent
once-per-UTC-day guard in 'run' (last_run_date in state) so multiple attempts cannot double-book;
(2) cron now fires at 09:10/12:10/15:10/18:10 UTC daily -> first attempt while the machine is
awake books the day, the rest no-op. Robust to the machine being off at any single slot.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replace the agent/cloud approach with one self-contained local CLI over Binance's public API.
Subcommands: snapshot (live liveness check), run/paper (daily step, cron-compatible), status
(book + cumulative), gate (Phase-1 -> Phase-2 assessment vs backtest band), log. No key, no
capital, no agents. Crypto-native filter retained. Cron 'paper' alias preserved.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Live Binance fapi now lists tokenized-stock perps (MSTR/CRCL/INTC/AMD/SOXL, underlyingType=
EQUITY) which dominated the high-funding qualifiers (12 of 19) but were NEVER in the validated
crypto_pit backtest. Filter to exchangeInfo underlyingType==COIN (crypto-native) to keep the
paper-forward test measuring the edge we actually proved. Post-filter: 7 of 212 liquid qualify
(thin = current deleverage regime, filter sitting mostly in cash as designed). Tokenized-stock
funding may be a separate unvalidated carry; not contaminating the Phase-1 gate.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Daily no-capital forward test. Pulls live Binance USDT-perp funding (public API, no key),
applies validated filter (liquid + trailing-30d mean daily funding > 5bp, hysteresis), computes
intended equal-weight delta-neutral book, tracks realized funding on prior book -> forward track
record on unseen data. Modes: paper|status. cwd-independent, state-persisted, cron-ready.
Day-1 live run: 19 of 247 liquid perps qualify (regime filter working in real time). Cron added
at 01:17 UTC daily (after 00:00 funding settlement). Validates the one open question: does
positive funding carry persist forward? Honest scope: tracks gross carry + turnover; does NOT
model basis vol (needs live fills) or counterparty risk (un-simulable).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Investigated crypto funding carry (researchers' flagged retail path to >1 Sharpe). DELTA-NEUTRAL
cash-and-carry (short perp+long spot, collect funding, price cancels) -- different from the
directional carry trap. Funding positive 75pct of time. Backtest net of cost: APR 9.9pct, raw
Sharpe +5.68, maxDD -7.4pct, survives to 20bp cost, worst month -1.5pct (delta-neutral held).
Discipline finds: (1) real; (2) 5.68 inflated (funding-only model, 1.8pct vol; real basis vol
-> honest ~2-3 Sharpe = literature's 1.5-2.5); (3) regime-dependent + DECAYING (negative 2022,
2025, 2026). Caveats: counterparty/exchange tail (FTX -100pct, not in backtest = real killer),
decay, operationally real. The ONE genuine path past the 0.7 ceiling -- but it's crypto +
counterparty tail is the price of admission. The journey converges: higher Sharpe exists,
reachable, but lives where the user didn't want to go with a tail the Sharpe doesn't show.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The strategy class we never tried: harvest structural premia + risk system, not predict.
Diversified futures + risk-parity/vol-target/trend; clean 5-asset-class version (ES/ZN/GC/CL/BTC).
Result: plain 60/40 (Sharpe +0.72, 2010-2026) BEATS risk-parity+vol-target (+0.46) and RP+trend
(+0.33, trend hurts); 5-asset+crypto RP only ties 60/40 and loses to buy-hold equity. Meta-pattern
now complete in BOTH games: simple beats/equals sophisticated in prediction AND harvesting.
Constructive deliverable: a simple premium harvest (60/40 / risk-parity) IS a real deployable
robust strategy (~0.5-0.72 Sharpe, low DD, no prediction, minimal complexity). The engine's
sophistication was never the return-generator -- deployable path is light (harvest + risk overlay),
engine's value is infra/discipline/product. (Also: CAISO intraday gate blocked by OASIS plumbing.)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
First repurpose target with real legs. DE day-ahead battery arbitrage (free Energy-Charts,
2019-2025, 2464 days). 4h/1MW/85pct: perfect-foresight e93k/yr/MW (>> e50-80k viability),
naive only e10k -> forecasting/RL gap = 89pct of value. Per-year GROWING (e28k 2019 ->
e141k 2025) = not competed away (batteries slow to build = operational moat). Structurally
opposite of trading: real economic value (not zero-sum), growing (not arbitraged), and 89pct
of value is forecasting/RL = exactly the engine's job. Caveats: perfect-foresight is upper
bound (realistic ~60-85pct capture -> ~e55-80k/yr/MW); needs a battery (capital) or sell the
dispatch software to operators (engine-as-product) or aggregator. NEXT: forecaster + RL
dispatch, measure realized-capture vs foresight.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Ran the quant-fund method (gradboost+ridge+IC+equal combining 13 weak cross-sectional
signals) on liquid US equities. Single-split gradboost looked amazing (OOS +1.14, DSR 0.62)
but leak-free WALK-FORWARD diagnostic: gradboost OOS predictive IC = 0.0041 (statistically
ZERO; no leak; successful equity ML is 0.02-0.05). Single-split was overfit; WF +32 Sharpe
was a variance-degeneracy; equal/ridge/IC all fail OOS. The ML combination does NOT work on
efficient equities -- not because the ML is bad (works perfectly) but because there's no
signal (IC 0.004) to combine. DEFINITIVE answer to 'millions of LOC of ML, why nothing?':
the ML is not the missing piece, MARKET ACCESS is. Pointed the actual RenTech/TwoSigma
method at liquid equities -> IC 0.004 = noise. ML amplifies signal, cannot create it;
efficient markets have none. Crypto (less-efficient) is the one place the same machinery
finds robust signal. Sophistication was never the bottleneck.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Bought XSP (mini-SPX) options ohlcv-1d 2013-2026 = $66.86 (hard-capped $70, get_cost-gated,
year-chunked vs 504, 2025 backfilled) + SPY $0.01. CORRECTION: index VRP is NOT $900 (that was
SPY root); clean instrument XSP $66.86/13y or SPX $143/13y. THREE measurement attempts all gave
spurious NEGATIVE VRP (RV 28-33% vs implied ~16%) = MEASUREMENT ERROR not finding (contradicts
decades of SPX VRP evidence). Bugs: noisy parity underlying; ~469/2800 days survive -> multi-day
gaps inflate RV; SPY!=XSP divergence corrupts ATM. Root: XSP EOD ohlcv too sparse to reconstruct
clean underlying+ATM-IV. Implied (16.7%) reads right. Frontier real+affordable+in-hand but proper
extraction is a real options-quant build (denser SPX +$76 or IV-surface w/ quotes), not a gate.
Did NOT record -2.7 as a result (artifact). Crypto momentum+VRP remains only deploy-grade edge.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Decomposed the equity low-vol +0.74. Deployable half DEAD: long leg (low-vol, borrow-free)
alpha +0.04 / DSR 0.02 = just cohort beta. ALL edge is shorting high-vol decile (needs
expensive borrow). Episodic: top-10 days = 133pct of P&L (a few crash events). Just broke:
2026 = -2.72 (anomaly reversed). Beta-neutral residual +0.98 = genuine betting-against-beta
anomaly but lumpy/short-only/recently-inverted. Turnover low (cost was fair). Verdict: real
anomaly, un-harvestable by a small retail borrow-constrained book. Detail killed the lead
honestly. Crypto momentum+VRP remains the only deploy-grade edge.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Full gauntlet on the lottery-aversion lead (liquid high-vol cohort). BASE L/S +0.74/OOS
+0.72 but: name-bootstrap frac>0 only 0.77 (fragile vs momentum's 1.00); edge lives at
$5-20M floor (smaller names, real spreads > the 10bp assumed), dies at $50M; the L/S edge
is mostly shorting hard-to-borrow hype names (30%/yr borrow -> +0.04 gone); long-only
realistic = +0.33, DSR 0.07 (not significant). corr to crypto book -0.05 (uncorrelated ->
would diversify IF real). DSR 0.22/0.07 -- neither clears 0.5. Closest non-crypto market,
theoretically sound, uncorrelated -- but marginal after realistic borrow+small-name cost,
NOT deploy-grade. A lead on the shelf, not a strategy. Crypto momentum+VRP remains the only
deploy-grade edge. Re-confirms the boundary.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Reasoned about WHERE our edge structure fits (reflexivity+breadth+low-cost overlap) ->
picked the liquid high-vol equity cohort (>$10M/day liquid AND high realized vol =
reflexive story-stocks, ~87 names) = equity analog of crypto's reflexive cohort, avoiding
both walls. Momentum/reversal still negative (regime+efficiency), but LOW-VOL (lottery-
aversion) FITS: L/S net +0.74, OOS +0.72, CPCVmed +0.73, positive 3/4 years, LongOnly +0.33.
First equity signal to survive net cost (broad test had lowvol +0.02). Theoretically sound
(fade overpriced hype/lottery names in the reflexive cohort). LEAD not deploy-grade: DSR
0.28<0.5, short 3.2y data, thin cohort, short-side borrow cost unmodeled. Non-crypto,
low-cost, Databento. Next: full gauntlet (bootstrap/cohort-robustness/borrow/deflation).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
DBEQ.BASIC all US equities daily 2023-2026 ($67.85, 17305 instruments). Small/mid-cap band
(excl top-50 mega, $2M floor, ~576 names/day), weekly rebal+smooth, illiquidity-scaled cost
(30-150bp). NO factor survives net: momentum negative even gross (2023-24 momentum-crash);
reversal gross +0.15 eaten by cost -> NET -0.86 (Amihud paradox); low-vol best but NET ~0
(DSR 0.03). Didn't even charge short-borrow. Confirms Databento tradeable universe (equities+
futures) is efficient+cost-walled -> no retail edge. Honest tension: cheap-to-trade markets too
efficient; the inefficient market with real edge (crypto) is the disliked one. Caveat: 3.2y only.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Fetched Bybit funding (OKX fetch failed, so Binance+Bybit) for 18 majors. Cross-venue
DISPERSION & Binance-premium signals all negative. Only positive = carry_multivenue +0.84
(OOS+0.80, corr_mom+0.01, marg_t+2.58) -- BUT Binance-only control on the SAME 18 majors =
+0.69, proving the edge is MAJOR-COIN SELECTION not the cross-venue angle (multi-venue adds
only +0.15 noise-reduction). This is the known cherry-picked carry trap (majors +0.8 ->
broad-clean -0.03). Almost re-fooled by the seductive number; the Binance-only control
disconfirmed it. Orthogonality doesn't rescue universe-fragility. Databento has no crypto/
on-chain data either. Both orthogonal frontiers closed. Product = residual-momentum + VRP.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Before building deep sequence models, tested whether cost-surviving signal exists at
the minute horizon for them to extract. 12 perps, 60d free 1m klines (OFI proxy from
takerBuyQuote/quoteVol), features -> forward 1/5/15min returns net of 5bp taker. ALL
features negative net (best gross ~0.2bp vs 5bp cost = 25x gap); reversal IC -0.027 and
vol-continuation +0.009 are real but ~25x too small; OFI/taker-imbalance ~zero predictive
power. -> No minute-horizon signal -> Mamba2/CfC/TLOB have nothing to extract -> don't
build (no model lifts IC 25x). Crossing-cost wall holds in crypto (sec-ES 100x, min-crypto
25x); maker=adverse-selection wall, full-LOB=colocation territory. Gate saved a multi-week
GPU build for $0/10min. Product remains the daily two-sleeve book.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Phase-1 upgrade applied to the PoC base sleeve: rank residual momentum (each coin's
return stripped of its rolling beta to the equal-weight market) instead of raw momentum.
Removes high-beta coins dominating the sort by market co-movement. Backtest: gross
+0.82->+0.99, net @$20M +0.40->+0.57, capacity $5M +0.60->+0.78, CPCV-med +0.47->+0.59,
combined two-sleeve book +1.56->+1.66. Same edge, cleaner construction. Live panel depth
bumped to cover the 60d beta window. No lookahead (beta + cumsum use closed bars).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Tested 5 theoretically-distinct new crypto signals (residual-momentum, MAX/lottery,
idiosyncratic-vol, Amihud-illiquidity, acceleration) on PIT top-50 with full gauntlet
(OOS/CPCV/deflation/coin-bootstrap) + correlation to momentum. NO new DISTINCT validated
signal: survivors = momentum + residual-momentum (corr 0.95 = same edge). Others fail
(lottery/accel negative; ivol/amihud fail bootstrap-robustness, amihud closest miss
corr+0.20/boot0.75). DECISIVE: validated signal set is thin (one alpha + VRP diversifier)
-> RL/PPO has no rich interacting set to combine -> would not beat the linear baseline OOS
-> don't build the RL (the falsifiable gate returns NO; avoids the 65th-commit trap).
SMALL WIN: residual (beta-stripped) momentum +0.72 > raw +0.57 -- better base construction.
Product = simple two-sleeve book. RL needs non-price signals to ever justify itself.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
backtest now reports momentum + VRP (tail-managed, corr -0.04) + COMBINED book
(momentum 70% / VRP 30% risk) Sharpe +1.56, all years positive. paper marks BOTH
sleeves + combined equity each run; status shows all three + live Sharpes. VRP gate
('don't sell vol when DVOL rising/elevated') runs live -- currently 'flat (gated)'.
cwd-independence fixes: pit_sweep.load + _vrp_calib now use abs paths so the cron paper
run calibrates VRP correctly from $HOME (was silently falling back to zero-VRP). Live
panel depth bumped to cover the 60d VRP gate window. Honest: VRP +2.85 is the no-Greeks
proxy (real ~1-1.5) so combined is optimistic (~0.8-1.0 realistic) -- still > momentum alone.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Vol-risk-premium (short-vol BTC+ETH, Deribit DVOL implied minus realized, short-variance
daily P&L proxy). VRP Sharpe +1.03, CORRELATION to momentum -0.03 (genuinely uncorrelated),
combined +1.22 (~doubles momentum-alone +0.66). FIRST genuine diversifier found -- has BOTH
edge AND low-corr (futures trend had corr but no edge -> diluted). CAVEATS: (1) catastrophic
negative skew -8.32, worst-day -21sigma (short-vol blowup risk; Sharpe flatters; must
tail-manage + size small) (2) recent decay -- negative 2025/2026 (+1.22 is a 2021-24 artifact).
Real and promising, categorically better than futures, but pursue carefully not naive deploy.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Expanded futures universe 22->39 liquid CME roots ($16.39 credits, 16y daily). (A)
breadth did NOT unlock an edge: XS momentum + TS trend all negative/zero, DSR 0
(efficient market, unlike crypto). (B) diversifier check: futures-trend +0.01,
crypto-momentum +0.88, CORRELATION -0.01 (genuinely uncorrelated) but combined +0.63
< +0.88 -> an uncorrelated sleeve with zero standalone edge DILUTES, not diversifies.
A diversifier needs low-corr AND positive edge; futures trend has only the former.
Caveat: roll-zeroing understates futures trend/carry (floor work ~+0.05-0.14 w/ proper
rolls) -> marginal at best. Crypto momentum still the only real edge.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- Rebalance keyed on FIXED calendar phase (epoch-day%7==0 -> Thursdays) instead of
drifting days[0]%K, so backtest and live agree on rebalance timing.
- STATE path absolute (relative to script) -> paper mode runs from any cwd (cron-safe).
- Backtest unchanged (net +0.40@$20M, CPCV-med +0.47).
Installed system crontab (daily 12:07): marks paper PnL daily, rebalances Thursdays,
logs to data/surfer/paper_runs.log. Forward-test seeded inception 2026-06-06.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
One-file PoC of the validated crypto XS-momentum edge. ONE shared compute_weights()
drives backtest AND live (no skew); no lookahead; funding-as-PnL; sqrt-impact cost.
Backtest reproduces research (gross +0.83, net +0.43@$20M, capacity curve, turnover
9.8%). Regime diagnostic = clean NEGATIVE (no feature predicts momentum favorability,
IC~0 IS/OOS) -> de Prado meta-labeling/regime overlay empirically unwarranted, runs
flat-sized. Paper mode = live forward-test (Binance ASCII perps, market-neutral book,
intended trades + paper PnL persisted). Python is the right tool for weekly crypto MFT;
foxhunt Rust/CUDA is HFT-ES-specific (concepts reused, plumbing not).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
