Quant Research

Name: Quant Research
Author: abhayjnayakk

ai.avasis/quant-research

BLOCKgrade D · trust 69/100

Statistical tests for whether a backtest means anything: deflated Sharpe, PBO, purged CV, reality checks, attestation verification.

backtestingdeflated sharpemcpoverfittingpythonquantitative financeresearch integritystatistics

Overview

From the repository's own README, as read at the audited commit.

<div align="center"># quant-integrity**Statistical tests for whether a backtest means anything.**[![PyPI](https://img.shields.io/pypi/v/quant-integrity?color=FFB224&label=pypi)](https://pypi.org/project/quant-integrity/)[![Python](https://img.shields.io/pypi/pyversions/quant-integrity?color=FFB224)](https://pypi.org/project/quant-integrity/)[![Licence](https://img.shields.io/badge/licence-AGPL--3.0--or--later-FFB224)](LICENSE)[![CI](https://github.com/abhayjnayakk/quant-integrity/actions/workflows/ci.yml/badge.svg)](https://github.com/abhayjnayakk/quant-integrity/actions/workflows/ci.yml)[![Typed](https://img.shields.io/badge/typing-py.typed-FFB224)](src/)</div>> **This library will not find you a profitable strategy. Its function is to reject> them.** Everything here exists to answer one question: given how many> configurations you tried before reporting this one, does the result survive?```bashpip install quant-integrity```---## The problem, in one pictureA moving-average crossover on BTC-USD hourly bars. After sweeping parameters, thebest configuration returned an annualised Sharpe of **0.95** — and aProbabilistic Sharpe of 0.86, which reads as *"probably beats zero"*.That is where most backtests stop. Here is the same result next to the bar that28 attempts actually sets:![Observed Sharpe against the bar set by the trial count](docs/figures/deflation.svg)The best of 28 tries is large **even when every underlying edge is exactlyzero**. Against that bar the deflated Sharpe is 0.157. The observed result is notmarginal; it is below half of what luck alone produces.A high PSR with a low DSR is the signature of an overfit search, not a borderlineedge.## What the search was actually selecting onThe cause was visible in the trials themselves. Sorting the 28 recorded runs bytrade count against Sharpe:![Sharpe against trade count across every trial](docs/figures/turnover.svg)Every configuration that traded less looked better, at ρ = **−0.96**. That is nota signal being dis

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code

claude mcp add quant-integrity -- uvx quant-integrity

claude-desktop

{
  "mcpServers": {
    "quant-integrity": {
      "command": "uvx",
      "args": [
        "quant-integrity"
      ]
    }
  }
}

Details

Source: abhayjnayakk/quant-integrity
PyPI: quant-integrity
Transports: streamable-http
Tools: Registered at runtime; the list could not be read from source.
License: AGPL-3.0
Stars: 1 · pushed 9d ago

Trust audit

Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	FAIL
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED