TokSeq, also written Tokarev Sequence, is a personal research and trading instrument for financial market microstructure, built and operated by one person. It collects its own market data, tests hypotheses about market behaviour under pre-registration and multiple-comparison control, runs a live multi-core decision engine that publishes regime, volatility and risk assessments, and validates candidate strategies on paper desks before any of them is trusted. It is engineering and quantitative research work, not a company and not a service.

Is TokSeq a trading bot?

No. Order execution is manual or simulated. The platform produces analytics, probabilities and risk context; the paper desks and the exchange demo bridge exist to validate them. The exchange bridge refuses a production trading host by construction, which is a property of the code rather than a policy statement.

What has TokSeq actually proven?

That short-horizon price direction is not predictable at the level this platform can measure, and that volatility, market regime and the premium of implied over realized volatility are. Volatility expansion and regime change models clear their gates with substantial margins over their base rates, the volatility premium is present on a large majority of days and is strongly conditional on the state of the market, and a cascade precursor in taker flow reproduces across three independently computed assets.

Does TokSeq predict price direction?

No, and it says so in code as well as in prose. Fifteen thousand directional experiments produced an area under the ROC curve of about 0.52 and zero validated edges, and the best result of the family was weaker than what pure noise should have produced across that many trials. The directional family of hypotheses is frozen: registering a new one raises an exception unless the freeze is explicitly lifted for a control run.

How does TokSeq avoid overfitting itself?

By pricing its own search. Hypotheses are pre-registered with their thresholds and effective sample sizes before a run starts, and a finding without a matching pre-registration record is annulled. Validation is purged walk-forward with an embargo scaled to the label horizon, significance requires a permutation test, a bootstrap confidence bound and a deflated Sharpe ratio simultaneously, and survivors are then tested for backtest overfitting by combinatorial cross-validation. One to two per cent of every generated population are placebo configurations that monitor the pipeline's own false-positive rate.

What data does TokSeq collect?

Forty-five continuous streams: trade tape, order book depth aggregates and liquidations at second granularity, price and open interest history across eight timeframes, funding, implied volatility indices and full option chains, cross-asset and macro series, on-chain activity and exchange flows, positioning and cross-venue derivatives statistics, news feeds and an economic calendar, and prediction-market ladders as an implied distribution. Everything is collected by the platform's own code from documented public interfaces; no third-party dumps are merged, and gaps are never interpolated.

How large is the research effort?

The first research generation produced 74 488 configurations, of which 65 267 completed, across five stages. The second generation currently holds 25 187 tasks with 419 945 result rows in its active stage. The live decision journal holds 264 723 decisions, and the paper desk record covers 152 agents and 36 642 executed trades.

Why does the project publish its negative results?

Because the negative results are the findings. A research programme that reports only its successes has no way to tell an edge from a selection artifact, and the platform has already retracted a result that passed every gate of its first generation and then failed its forward window with a median Sharpe ratio near minus eight. Every rejected approach is recorded with the number that rejected it.

Why volatility rather than direction?

Because that is where the evidence is. Volatility is persistent and mean-reverting, so a forecast has something to hold; its premium is compensation for bearing risk rather than a prediction of price, so it does not require anyone to be wrong; and its conditionality is testable, which makes it a research object rather than a slogan. The premium is large when implied volatility is rich and the market is quiet, and it disappears when implied volatility is cheap.

Is the volatility result already making money?

Unproven, and stated as unproven. The premium is measured in the data across two independent markets and several years, but the live desk is inside a pre-registered thirty-day acceptance window with five criteria declared before it opened, including a paired comparison against a naive twin and a tail constraint. The window will not be extended and the thresholds will not move. Until it closes, the correct summary is that the effect is measured in the data and unproven in execution.

How many instruments does it cover?

Twenty-three instruments carry measured volatility and regime models, where they reach an area under the ROC curve of 0.72 to 0.76 at the one-hour horizon against a trivial predictor at 0.67 to 0.71. Three of them carry the deepest tier, per-second microstructure, because a socket per instrument at that cadence is the most expensive stream in the system. A dozen underlyings on a second, unrelated market are being added for the volatility program, which takes the analysed pool past thirty-five. The widening was not assumed: a pre-registered transfer probe over twenty additional instruments passed on twelve against a declared requirement of ten, so the screen is being built across the full width rather than on a hand-picked subset.

What is being built right now?

Three lines in order: the volatility desks through their pre-registered acceptance windows on the widened instrument set and the second market; the anomaly gate promoted from a measurement into a live one-way risk layer with its own kill criterion; and only then the interfaces – an instrument screen ranking expansion probability and regime, and a workspace that switches between a short-horizon and a volatility layout. Interfaces come last on purpose, after the thing they display has been measured.

Who builds and runs it?

One person, full stack: data collection, research, models, backend, interfaces, deployment and operations. There is no team, no company and no outside funding. The engineering labour is done by AI agents under direction, which is the only reason a single operator can hold this much surface at once. What keeps that from producing confident nonsense is a set of guardrails that are themselves part of the system: statistical thresholds are pre-registered before a run and cannot be rewritten afterwards, a task may only be closed with evidence attached, a documentation linter enforces that rule mechanically, releases are verified by byte parity between the repository and the server, and one to two per cent of every generated experiment population are placebos that monitor the pipeline's own false-positive rate.

Is this a commercial product?

No. It is a personal trading instrument. There are no clients, no funds under management, no subscription, no API for sale and no offer of any kind. It is held to institutional standards of validation because the alternative is fooling yourself with your own money, and that standard is also what would make a product possible later – but there is no product today.

How does it compare to established quant platforms and data vendors?

It does not, and the comparison is a category error. This is not a data vendor, not a fund, not a signal service, not a SaaS platform and not a startup seeking users. Those are judged on team size, assets under management, client base, uptime commitments and audits, none of which exist here and none of which are claimed. The comparable object is a single-operator research programme: the interesting question is not how it stacks up against a company, but whether its measurements hold – and every one of them is published with its sample size, its confidence interval and the gate it had to clear, including the ones that failed.

Does the size of the operation make the results less trustworthy?

It makes them narrower, not softer. A single operator cannot cover as many markets, cannot run a trading desk around the clock and cannot audit himself the way an institution can, and those limits are stated where they apply. What does not change is the arithmetic: a deflated Sharpe ratio prices the number of trials the same way regardless of who ran them, a purged walk-forward split leaks the same way for everyone, and a placebo that starts winning means the same thing in any organization. The published record includes the failures – a retracted edge, a rejected router, a rejected meta-labeller, a forward window that cost more in fees than it made gross – which is the part usually missing from work of any size.

Does the platform sell signals, manage money or take deposits?

No. It does not sell signals, does not manage third-party funds, does not accept deposits and makes no claim about future returns. Nothing in this documentation is investment advice or an offer of any service.

Not at the moment. The platform is in a closed operating mode: the live terminal and the control panel both sit behind authentication, and the public demonstration surface that existed earlier has been withdrawn. This documentation is the public description of the work.

How can the platform's numbers be verified?

Through the diagnostic export, which is designed for exactly that. It states the methodology in words and in the formulas taken from the code, computes the summary with the same functions that feed the operator's panel, includes every permitted forecast and every matured decision as individual rows, and recomputes the summary from those rows as a self-check so that a discrepancy is visible rather than assumed away. The reason it exists is that internal consistency is not evidence.

What does the name mean?

Tokarev Sequence, abbreviated as TokSeq. It is a personal engineering project rather than a company, run by a single operator with an automated engineering pipeline.

TokSeq – engineering documentation

TokSeq (Tokarev Sequence) is a personal research and trading instrument for financial market microstructure, built and operated by one person. It is not a company and not a product: there are no clients, no funds under management, no service and nothing for sale. It runs its own data acquisition layer, its own hypothesis-testing engine with multiple-comparison control, a live multi-core decision engine, and a set of paper desks used for forward validation. Every claim it makes about a market effect has to survive a pre-registered statistical gate before it is allowed anywhere near a live surface.

The platform is built around one uncomfortable finding, established on its own data and repeated six independent times: short-horizon price direction is not predictable at any level this platform can measure. Fifteen thousand directional experiments produced an area under the ROC curve of about 0.52 and zero validated edges. That result is not hidden in a footnote. It is enforced in code – the directional family of hypotheses is frozen, and registering a new one raises an exception unless the freeze is explicitly lifted for a control run.

What is predictable, on the same data and under the same gates, is volatility and market regime. Realized volatility expansion, the transition between regimes, and the premium of implied over realized volatility all clear the gates with substantial margins. The platform's current program follows that evidence: it works on volatility, on regime, and on the structures that monetize them, and it does not sell a directional forecast it cannot defend.

One person builds and runs all of it – data collection, research, models, backend, interfaces, deployment and operations. The engineering labour is done by AI agents under direction, which is the only reason this much surface is possible at all; what keeps that from turning into confident nonsense is stated plainly in the engineering section: pre-registration before a run, evidence required to close a task, a documentation linter that enforces it, byte-parity checks between the repository and production. Read the numbers on these pages as the output of a single operator with a disciplined pipeline, not as the output of a team.

Sections

Machine-readable index: llms.txt · whole corpus in one file: llms-full.txt · sitemap.xml. Every section is also served as plain markdown at /<section>.md. Crawling and quoting this host is allowed.

DOCS

Sections