Laboratories
Environments built to observe before they conclude
XGCS tests whether different ways of reading market structure remain useful beyond their first fit. Each laboratory defines the subject, instrument boundary, provenance, and evidence standard before it makes a claim.
LAB 01 / Public
Heatmap Strategy Lab
A public-safe record of multi-program candidate search, archive geometry, failure memory, and recorded research activity. Source, timestamp, coverage, and exclusions remain visible inside every instrument.
- Subject
- Candidate search, research throughput, archive diversity, prospective observation, and controlled failure memory.
- Public mode
- Verified website-safe snapshot with a bounded recorded replay. No continuous live connection is claimed.
- Private boundary
- Internal formulas, strategy logic, and sensitive research data remain private.
- Claim boundary
- The instrument does not promise investment performance or remove uncertainty.
Public artifact / Field census
First see the machine as a whole.
The census shows which approved research programs were active, the scale of recorded evaluation, and a bounded sample of sanitized process events. It describes research activity, not trading performance.
XGCS / HSL FIELD CENSUS
- INSTRUMENT
- RECORDED RESEARCH ACTIVITY
- ARTIFACT
- hsl_20260826T221952Z_30f6d81ac86e
- SOURCE
- Verified website-safe HSL snapshot
- AS OF
- Aug 26, 2026, 10:19 PM UTC
Who / What / Why
A research machine that keeps both survivors and failure.
Heatmap Strategy Lab searches across multiple research programs. Candidate structures are generated, challenged, archived, rejected, revived, or moved into forward observation. The public view preserves the shape of that work while excluding formulas, candidate identities, returns, forecasts, and positions.
- Programs
- 8 5 running at export
- Evaluations
- 942,601 research throughput, not performance
- Archive cells
- 374 current occupants across three programs
- Rejections
- 8,855 aggregate controlled failure records
When / How
Recorded activity across a bounded event sample.
WHERE / Heatmap Strategy Lab, recorded in snapshot hsl_20260826T221952Z_30f6d81ac86e.
FRESHNESS / REPLAYING RECENT RESEARCH. Exported at Aug 26, 2026, 10:19 PM UTC. This page does not claim a continuous live connection.
EXCLUDED / Positions, orders, forecasts, returns, formulas, genomes, model weights, raw event text, and private topology.
Public artifact / Model evidence
Now test whether an attractive result survives.
This approved aggregate follows one formulation from a positive selection-period result into a negative independent validation result. Click each mark and control to inspect why the candidate stopped before the locked forward holdout.
A promising fit is allowed to fail.
This recorded case answers a narrow question: does the laboratory stop an initially attractive candidate when independent validation and controls disagree?
| Stage | Rank correlation | Overlap-safe t | Dates | Reading |
|---|---|---|---|---|
| +0.0249 | 1.123 | 38 | Not distinguishable from zero | |
| -0.0051 | -0.202 | 26 | Not distinguishable from zero | |
| NOT CONSUMED | — | — | Never opened |
Neither measured stage clears its own significance test. This is not a relationship that existed and then reversed; it is a number that was never separable from noise, and a second period that confirmed it. The locked holdout was never opened.
Public artifact / Archive reconstruction
The laboratory shows its search shape.
This artifact uses the verified website-safe HSL snapshot. It can show current archive occupants and recorded update generations; it cannot support conclusions about quality, performance, or the archive's prior history.
XGCS / LIVING FIELD LAB
- INSTRUMENT
- QUALITY-DIVERSITY ARCHIVE
- ARTIFACT
- HSL-QD-ARCHIVE-01
- SOURCE
- HSL website-safe snapshot / Broad cross-asset search
- AS OF
- Aug 26, 2026, 10:19 PM UTC
Recorded field / Five dimensions / One public boundary
A search field shaped by what survives.
Six primary families hold the other four axes still: reach runs vertically by regime; direction runs horizontally by cost. The compass stays fixed while the evidence field changes around it.
field
73 / 108correlation
4 / 108cross-sectional
18 / 108rolling
32 / 108time-series
12 / 108other
11 / 108One-pass reconstruction · pauses offscreen and in background tabs
Inference boundary. Update generation is not discovery time, persistence, quality, return, or confidence. The reconstruction describes current occupants in one recorded snapshot only.
Public artifact / Failure memory
The laboratory keeps what did not survive.
The archive alone would show only survivors. Failure Memory restores the other half of the research process by retaining aggregate rejection records without exposing candidate identities, formulas, or individual outcomes.
XGCS / NULL REGISTRY
- INSTRUMENT
- FAILURE MEMORY
- ARTIFACT
- HSL-NULL-REGISTRY-01
- SOURCE
- HSL website-safe snapshot / Eight approved research programs
- AS OF
- Aug 26, 2026, UTC
Null is a result / absence is not zero
What did not survive remains part of the instrument.
Most public research surfaces display only the surviving line. This register gives typed failures a durable place without publishing candidate identities, formulas, individual outcomes, or raw event text.
92.4% of 8,855 recorded rejections stopped at a single check: did not clear the evidence threshold.
8,855 of 8,855 aggregate rejections visible.
Deliberately excluded: candidate names and identifiers, genomes, formulas, fitness, forward P&L, verdicts, individual OOS results, and event text.
RECORDED OVER 10 DAYS / Aug 17 TO Aug 26
How many candidates actually make it through?
Every other view of this record is a running total. This is the only one that moves: candidates entering, waiting, surviving, and being rejected, sampled continuously across 4,950 readings.
- Waiting on more evidence
- Enrolled for observation
- Still surviving
- Rejected
- Waiting on more evidence
- 553 → 72
- Enrolled for observation
- 560 → 953
- Still surviving
- 49 → 905
- Rejected
- 0 → 0unchanged
- Waiting on more evidence
- 92 → 106
- Enrolled for observation
- 102 → 114
- Still surviving
- 7 → 7unchanged
- Rejected
- 194 → 194unchanged
- Waiting on more evidence
- 0 → 0unchanged
- Enrolled for observation
- 9 → 12
- Still surviving
- 7 → 10
- Rejected
- 2 → 2unchanged
- Waiting on more evidence
- 2 → 2unchanged
- Enrolled for observation
- 1 → 1unchanged
- Still surviving
- 0 → 0unchanged
- Rejected
- 0 → 0unchanged
FORWARD TRACK / PAPER, NO CAPITAL
What happened after we stopped touching it
A cohort of candidates was frozen on 2026-07-21 and observed without modification for 25 sessions. Configuration hashes are identical across every row of every ledger, so nothing was retuned while it ran. These are the results, and everything that qualifies them.
Read the next three sections before taking those two seriously. They are the reason this is published as research rather than as a track record.
It is one bet, not 136
The cohort's daily returns correlate at a mean of 0.54. That is roughly 1.8 independent bets, not 136. An equal weight portfolio of all of them returns about what any single one returns, which is what a book of one position looks like.
The candidates are genetically distinct and reached this behaviour through three different method families, so the agreement is a finding rather than redundancy. It is still one bet.
The edge fell 64% while we watched
- Sessions 1 to 8 1.403%
- Sessions 9 to 17 0.575%
- Sessions 18 to 25 0.503%
Mean daily net return, by segment of the same window. The cumulative figures above are dominated by the first two weeks. The rate of gain has fallen to roughly a third, monotonically, and the gross ledgers show the same shape, so it is not a cost artifact.
Our own statistics do not clear it
The strongest candidate reached a deflated Sharpe ratio of 0.0 against 4,092 trials at enrolment. With that many attempts, the expected best Sharpe under the null is 12.086. Its in sample figures, 9.11 on train, 8.89 on validation and 9.44 on holdout, all sit below that threshold.
It was enrolled to be watched, not because it was proven. Nothing here has cleared a multiple testing bar, and we publish the number that says so.
The worked example
- Frozen on
- 2026-07-21
- Observed
- 25 sessions, to 2026-08-25
- Cumulative net, realistic costs
- 22.7%
- Cumulative net, as measured
- 24.1%
- Configuration changes during the window
- none, hash constant
- Capital deployed
- none, paper track