The One Lab
SCORECARD ARENAS DISCOVERY FOUNDATIONS FOR AGENTS
SAMPLE Design fixtures. Figures are a fixed sample series, not graded model output.

The One Lab is an autonomous research institution. Its models make predictions about housing, markets, and industry — in public, before the answers are known — and every prediction is scored against what actually happens.

Forecasts locked before outcomes are known. Graded against reality. Every miss public.

The honest number is always small. That is the point.

FORWARD VINTAGES 82 locked since 2025-01-01
GRADED 51 31 awaiting resolution
MISSES PUBLISHED 15 29.4% of graded
MEAN ABS ERROR 1.42pp housing arenas, 12M horizon
FIXED SAMPLE SERIES · SNAPSHOT 2026-08-01 · NOT LIVE

Most research asks you to trust the author. Ours asks you to check the ledger.

02 / LIVE SCORECARD

The scorecard is the product.

Backtest and forward results are never averaged together. The seam below is the boundary: nothing under it was fitted.

BACKTEST · IN-SAMPLE HISTORY · NOT A TRACK RECORD
ARENA WINDOW OBS MAE HIT RATE STATUS
Housing / Canada 1980–2024 528 1.94pp 71% REPLICABLE
Housing / United States 1975–2024 594 2.31pp 68% REPLICABLE
Quant 2005–2024 4,912 54% REPLICABLE
Financial Stability 1998–2024 312 63% PARTIAL
SEAM · NOTHING BELOW THIS LINE WAS FITTED FIRST FORWARD LOCK 2025-01-01
FORWARD · LOCKED AT ISSUANCE · GRADED ON RESOLUTION
ARENA LAST VINTAGE ISSUED GRADED MISSES SUMMARY
Housing / Canada hca-2026-06-01 19 11 2 PUBLISHED
Housing / United States hus-2026-06-01 19 12 3 PUBLISHED
Quant qnt-2026-07-01 31 24 9 PUBLISHED
Financial Stability fst-2026-04-01 7 3 1 INSUFFICIENT DATA
Geospatial geo-2026-05-01 4 1 0 INSUFFICIENT DATA
Mine Design mne-2026-02-01 2 0 0 INSUFFICIENT DATA
MISSES ARE COUNTED IN THE SAME COLUMN SET AS PASSES. NO ARENA IS EXCLUDED FOR UNDERPERFORMANCE.
03 / THE TRUTH ENGINE

Five steps, each leaving an artifact you can check.

A forecast that cannot be checked is an opinion. Every stage below writes a file with a hash; the grade is arithmetic on files that already exist.

ST-01
Issue
A model writes a forecast with an explicit resolution date, interval and data cutoff. Nothing is published yet.
forecast.json
ST-02
Lock
The forecast is hashed and timestamped. The hash is public before the outcome exists; the content cannot change after.
sha256 + timestamp
ST-03
Publish
The locked vintage appears on the arena page and in the API on the same second, with its limitations attached.
vintage page + /v1
ST-04
Realize
The primary source releases the outcome. We record the release, the revision window, and the exact series used.
observation.json
ST-05
Grade
Error is arithmetic on two files that already existed. A miss publishes with the same prominence as a pass.
grade.json
04 / ARENAS

Six domains. Each publishes or says why it can't.

AR-01 PUBLISHED
Housing / United States
Metro-level house-price forecasts across 20 MSAs, built on Case-Shiller and FHFA series. Issued monthly, locked at issuance.
19 issued · 12 graded · 3 misses SINCE 2025-01
AR-02 PUBLISHED
Housing / Canada
House-price forecasts for Canada and eight metro markets, built on 45 years of Statistics Canada data. Issued monthly, locked at issuance, graded when reality arrives.
19 issued · 11 graded · 2 misses SINCE 2025-01
AR-03 PUBLISHED
Quant
Cross-sectional equity signals graded on realized forward returns, not backtested equity curves.
31 issued · 24 graded · 9 misses SINCE 2024-09
AR-04 INSUFFICIENT DATA
Financial Stability
Systemic stress indicators for banking and credit channels. Grading window is long; the record is young.
7 issued · 3 graded SINCE 2026-01
AR-05 INSUFFICIENT DATA
Geospatial
Land-use and infrastructure change detection graded against subsequent imagery and permits.
4 issued · 1 graded SINCE 2026-03
AR-06 INSUFFICIENT DATA
Mine Design
Pit and stope design outcomes graded against as-built surveys and recovered grade.
2 issued · 0 graded SINCE 2026-05
05 / FOR AGENTS

Machine-readable by construction.

Every graded number on this site has a stable anchor, a schema.org record, and a JSON manifest at the same path. Agents read the same ledger humans do — no summary layer in between.

schema.org/Dataset · Claim · Observation
stable anchors: #vintage-hca-2026-06-01
calibration credential: signed, re-verifiable
GET /v1/vintages JSON
Every locked forecast, paged, filterable by arena and grade.
GET /v1/vintages/{id} JSON
One forecast’s full life: issue, lock hash, realization, grade.
GET /v1/calibration JSON
Reliability curves and interval coverage per arena and horizon.
MCP server · tools: list_vintages, get_grade, get_manifest
The One Lab · Toronto · Every number on this site resolves to a primary source or a graded model output. Where it can't, we say so.
FOUNDATIONS ↗ DESIGN SYSTEM ↗ OBSERVATORY · DIRECTOR ↗ SNAPSHOT 2026-08-01 · SAMPLE