Skip to content
@holdout-labs

holdout-labs

Holdout

Evidence infrastructure for financial AI research and AI-generated outputs.

What we do

We build a governance suite that makes research easier to audit and harder to overstate.

  • ashare-data-immunity for data quality and snapshots
  • pit-adjuster for point-in-time price meaning
  • lookahead-free for timing checks
  • factor-qc for backtest quality
  • falsification-ledger for claims and evidence trails
  • lesson-book for surfaced past mistakes
  • holdout-governance for AI-assisted research receipts

The backbone is one flow:

data -> adjust -> timing -> backtest -> falsify -> review -> publish

holdout-governance sits across that flow as the release gate. It checks what was used, what passed, what is missing, and whether a human approved the result.

Flow stage Repository What it does
entry / release gate holdout-governance the wrapper: one artifact, one verdict (also gov mcp for agents)
data ashare-data-immunity A-share daily-bar quality, snapshots, SHA-256 manifests
adjust pit-adjuster point-in-time back-adjustment with drift detection
timing lookahead-free verifiable look-ahead-freedom for pipelines
backtest factor-qc fail-closed backtest quality gate (DSR/PBO/MinTRL)
falsify falsification-ledger pre-registration, hash-chained ledger, adjudication
learn (loop-back) lesson-book surfaced past mistakes become the next round's checks

The pinned repositories on this profile follow this order: release gate first, then the data pipeline in flow order — read the org alphabetically and you miss the chain; read it as pinned and the pipeline reads top-down.

Why the name

A holdout set is the data you don't touch until the very end — it keeps your story honest. A holdout juror is the one who refuses to go along until the evidence is in. Every research claim deserves both.

What we do not do

  • We do not place orders.
  • We do not change trading rules.
  • We do not give investment advice.
  • We do not treat one passing check as proof of profit.

Start here

If you are doing AI-assisted financial research, start with holdout-governance. It records the evidence cutoff, checks that passed, the AI identity, and the human review state in one manifest.

Field notes

  • Three data incidents in one night — a production watchdog caught a ×100 scale corruption, then the same investigation surfaced a missing corporate-action event and a mixed-source unit defect. No single check caught all three — the layers did. Both failure signatures are reproducible offline in pit-adjuster's examples.

Maintaining this profile

GitHub lists an org's repositories alphabetically and offers no custom ordering, so the profile pins carry the design order. Keep the pinned repositories in flow order (max 6):

  1. holdout-governance — entry / release gate
  2. ashare-data-immunity — data
  3. pit-adjuster — adjust
  4. lookahead-free — timing
  5. factor-qc — backtest
  6. falsification-ledger — falsify

To pin: https://github.com/orgs/holdout-labs/repositories → pin each repo in that order (the pinned section shows them top-down in pin order). lesson-book (learn / loop-back) and .github are intentionally not pinned; their role is documented in the flow table above. When a new family member arrives, decide its flow stage first, then update the table and the pins together — the alphabetical list below is not the message.

Popular repositories Loading

  1. pit-adjuster pit-adjuster Public

    PIT 前视无偏复权引擎:复权因子链、复权口径漂移检测、快照等价校验。Point-in-time fixed-basis back-adjustment for daily prices, with convention-drift detection.

    Python

  2. falsification-ledger falsification-ledger Public

    量化研究预注册与证伪账本:哈希链防篡改、一次性裁决、命中率统计。Hash-chained pre-registration ledger for research claims.

    Python

  3. factor-qc factor-qc Public

    回测质量闸门:DSR、PBO、Harvey-Liu 多重检验折减与 MinTRL,P0/P1/P2 分级,默认不放行。Fail-closed quality gate for backtests in one NumPy engine.

    Python

  4. lesson-book lesson-book Public

    本地优先的交易经验记账本:记录错误代价,相似情境再现时提醒。Local-first tuition memory for traders.

    Python

  5. lookahead-free lookahead-free Public

    时序无前视验证:声明式数据流程检查,线性时间证明决策未使用当时不可知的数据。Verifiable look-ahead-freedom for data pipelines.

    Python

  6. ashare-data-immunity ashare-data-immunity Public

    A 股日线数据质量检查:OHLCV 清洗、按板块识别涨跌停/停牌、上市与连续性审计、SHA-256 快照。Data immunity for A-share daily bars: cleaning, board-aware price limits and suspensions, audits, snapshot manifests.

    Python

Repositories

Showing 8 of 8 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…