48,726 Sealed Predictions: USTA Permit Ledger — June 2026

This is a transparency post, not an accuracy claim. US Tech Automations Research maintains a public prediction ledger for residential building permits: every prediction is hashed, timestamped, and sealed in a content-addressed store before any outcome is observable, then scored against public records later. The June 2026 ledger holds 48,726 sealed predictions across 8 jurisdictions, accumulated over 72 seal runs in the window June 7 – June 11, 2026.

The number of property transfers observed against those predictions so far is exactly 0. The observation horizon is young, so this post makes no claim of predictive performance — none is possible yet. What it documents is the discipline: what was sealed, when it was sealed, and how the first resolution pass joined sealed records back to public permit data.

Key Findings

• 48,726 predictions sealed across 72 seal runs in 8 jurisdictions, per the sealed ledger tables.

• Ledger window: June 7 – June 11, 2026 — every record was hashed and timestamped before any outcome could be known.

• First resolution pass matched 6,465 of 6,555 records, a 98.6% match rate — a record-join rate against public permit data, not a measure of predictive accuracy.

• Transfers observed so far: 0 — no property transfers have yet been observed against any sealed prediction, so no success-rate claim is made.

• Underlying snapshot: 7,334 residential permits, $688.3M reported valuation, 84% coverage, drawn from the May 11 – June 9, 2026 reporting window.

48,726 predictions sealed · 72 seal runs · 8 jurisdictions · ledger window June 7 – June 11, 2026 · transfers observed: 0.

The Ledger at a Glance

Each row above is a literal count from the sealed ledger tables. The match rate deserves a plain-English caveat that we will repeat throughout this post: it measures whether a sealed record could be re-identified in public permit data on the resolution date. It says nothing about whether any prediction came true. The row that governs that question — property transfers observed — currently reads 0.

The predictions themselves are derived from the same sealed permit snapshots that power our metro reports, such as the Los Angeles building permit report and the Chicago building permit report. The underlying edition snapshot looks like this:

Scope matters here: these figures cover residential building permits (single-family and small multi-family); commercial and sub-trade permits are excluded at ingest. This is not a count of all construction permits issued in each city. All figures are computed directly from US Tech Automations' sealed daily permit snapshots; nothing is estimated, modeled, or extrapolated.

How Sealing Works

The point of sealing is simple: make it impossible to quietly rewrite a prediction after the outcome arrives. The pipeline is deterministic and runs on a fixed daily cadence.

1. Snapshot. Raw permit records are pulled from official municipal open-data portals for each covered jurisdiction and staged without modification, alongside the prediction records generated from them.

2. Hash. Every staged record is content-addressed: a cryptographic digest is computed over the exact bytes of the record, so any later edit — even a single character — produces a different digest.

3. Seal. The digests and records are committed to an append-only ledger with a timestamp. A seal run is one such commit; the current ledger reflects 72 of them. Sealed entries are never updated or deleted.

4. Resolve. On a later resolution date, sealed records are joined against fresh public data — permit records now, county assessor and transfer records as the horizon lengthens — and the join result is recorded next to the original seal.

5. Publish. The joined result is published as-is, including the uncomfortable rows. A ledger that only surfaced flattering numbers would be marketing, not a ledger.

Because the hash is computed before outcomes exist, a third party can verify that a published prediction is byte-identical to what was sealed. That verifiability — not any performance number — is the product of this exercise.

It is worth naming what this edition deliberately does not contain. There are no trend lines, no comparisons to earlier periods, and no growth claims, because this is a cross-sectional edition: the historical depth needed for honest comparisons does not exist yet, and we will not simulate it. There are also no model details dressed up as results. A sealed prediction is a claim waiting to be graded, and until grading is possible, describing it any other way would overstate what the ledger has earned.

First Resolution Pass

The first resolution pass ran on June 7, 2026. It took a subset of sealed records — 6,555 of them — and attempted to re-identify each one in current public permit data. Of those, 6,465 matched, a 98.6% match rate.

On June 7, 2026, the first resolution pass checked 6,555 sealed records and matched 6,465 — a 98.6% match rate. Property transfers observed: 0.

Two things must be said plainly. First, the 98.6% figure is a data-plumbing result: it confirms that sealed records can be reliably joined back to the public records they were derived from. It is not precision, recall, accuracy, or a success rate of any kind, and we make no such claim.

Second, the transfers-observed count is exactly 0. The predictions in this ledger concern outcomes — such as property transfers — that take time to appear in public records, and the ledger window only opened on June 7, 2026. Nothing has had time to resolve. Until transfers accumulate in assessor data and are joined against sealed predictions, the honest scorecard for this ledger is: sealed, verifiable, and unscored.

We publish at this stage anyway, because publishing only after results are known is exactly the selection bias the seal is designed to prevent. The records that will eventually be scored are already locked; readers can hold us to them.

Future resolution passes will be reported against this same fixed set as transfer records accumulate in assessor data. Each pass will state the same plain quantities reported here — records checked, records matched, transfers observed — and whatever those numbers turn out to be, they will be published next to the original seals. If the predictions perform poorly, that result will appear in this ledger in the same format as everything else. That is the deal a sealed ledger makes with its readers, and it only means something if it is kept when the numbers are unflattering.

Frequently Asked Questions

Q: Why seal predictions before outcomes are known?
A: Because 48,726 predictions sealed before outcomes is the only setup that prevents cherry-picking later. If predictions were published after results arrived, there would be no way to prove the misses were not quietly deleted. Sealing — hashing and timestamping each record in an append-only store — fixes the full set in advance, so the eventual scorecard covers everything that was claimed, not a curated highlight reel.

Q: What does the 98.6% match rate actually measure?
A: It is a record-join rate, nothing more. On June 7, 2026, the resolution pass checked 6,555 sealed records against current public permit data and re-identified 6,465 of them. That confirms the plumbing works: sealed records remain joinable to their public-data sources. It is not a measure of whether any prediction came true, and this post makes no accuracy, precision, or success-rate claim.

Q: Why is the transfers-observed count 0?
A: Because the observation horizon is young. The ledger window is June 7 – June 11, 2026, and the outcomes being predicted — property transfers — take time to surface in county records. As of the first resolution pass, the count of transfers observed against sealed predictions is exactly 0. Reporting that number plainly, rather than waiting for a flattering one, is the point of the ledger.

Q: What data feeds the predictions?
A: Sealed daily snapshots of residential building permits from official portals across 8 metros: 7,334 permits in the May 11 – June 9, 2026 window, with $688,331,017 in total reported valuation and 84% of permits carrying a reported value. Scope is residential only — single-family and small multi-family; commercial and sub-trade permits are excluded at ingest — so this is not a count of all construction permits issued in each city.

Q: Can a third party verify a sealed prediction?
A: Yes — that is the design goal. Each record is content-addressed: its cryptographic digest was computed and committed across 72 seal runs before any outcome existed. Given a published prediction and its digest, anyone can recompute the hash and confirm the record is byte-identical to what was sealed. Verification requires no trust in us, only in arithmetic.

Q: What value does an unscored ledger have?
A: It establishes the rules before the game is scored. The 48,726 sealed predictions define, in advance and immutably, exactly what will be graded when outcomes arrive. Future resolution passes will be published against this same fixed set, whatever they show. A young ledger proves discipline; only time can prove anything else, and we will not pretend otherwise.

Why We Publish Our Ledger

Verifiable data discipline is the product. Contractors, suppliers, lenders, and agencies who use permit intelligence have no shortage of vendors making confident claims; they have a shortage of vendors who seal their claims before the answers come in. Publishing the ledger — including a transfers-observed count of 0 — is how US Tech Automations earns the right to be checked rather than merely believed.

The same sealed snapshots behind this ledger drive our per-metro research, including the Seattle building permit report and the Scottsdale building permit report, and the live corpus is browsable at permits.ustechautomations.com. Teams that want sealed permit signals wired into their own workflows — monitoring, lead routing, outreach drafting — can contact us to talk through what the data can and cannot support. We will tell you the second part too.

Source: US Tech Automations Research — computed from sealed daily permit snapshots, June 7 – June 11, 2026.