Gate B on self-built bars: a sample that grows, and whether it agrees

resultgatesealing exemption

Question

Whether Gate B's calibration verdict holds on a self-built, growing bar sample instead of the static panel.

Verdict

[sample: self-built bars (recorder snapshots, 2h grid)] NO OVERSTATEMENT MEASURED — the median item's bar-derived fill count differs from recorded depth by +0.00 percentage points of attempted cycles, and the two agree at the median; 48% of items overstate. ... This is a FIRST calibration over 51.9 hours of recorded depth, 413 items, 7,787 resolvable attempted cycles, not a settled constant.

In plain language (1 term)

This site's own explanation of the words above. The verdict itself is published exactly as the research index records it and is not rewritten here.

attempted cycle: One full attempt at the strategy: place a buy order, wait, and sell if it fills. Attempts that never filled are counted too, so an average per attempted cycle cannot be flattered by dropping the ones that did not work.

Population: 413 items, self-built 2h-grid bars from recorder snapshots.
Resolution: 2-hour patience, self-built 2h grid; touch-only fill rule.
Cutoff: Recorder history 2026-08-04 22:00 -> 2026-08-06 23:59 UTC, read under the named sealing exemption gate_b_self_built_bars (#65).
Baseline: gate-b-calibration.md's static-panel sample, compared on weighted prices to a pre-declared 25bps materiality line.

Limitations

FIRST calibration over 51.9 hours / 7,787 resolvable attempted cycles -- not a settled constant; the self-built sample is biased OPTIMISTIC vs. the panel at the bid-side extreme.

Notes

Agrees with gate-b-calibration.md's static-panel sample on weighted prices to within a pre-declared 25bps materiality line. Regenerated in place twice for the same two reasons as gate-b-calibration.md (#67, then #126); same inline-supersession note applies.

Source

Citation: po-research:gate-b-self-built:6acf25d3c3c51c75
Write-up: docs/research/gate-b-self-built.md
Data: docs/research/gate-b-self-built.json, docs/research/gate-b-self-built.csv
Artifact: research-index.json v1 — sha256:cb3d976779a5cbcb4188039a8d26d5e558a2d844030a638c2f16fe5a8eb0a2fe
Build data cutoff: 2026-08-12
Issues: #63, #65, #67, #69, #70, #126