> ## Documentation Index
> Fetch the complete documentation index at: https://docs.signa.so/llms.txt
> Use this file to discover all available pages before exploring further.
# Deadlines You Can Docket Against
> Verifying computed trademark deadlines against 300,000 register records
Signa Research ยท July 2026
## Abstract
Most trademark data errors cost analysis quality. Deadline errors cost the
trademark: a missed renewal or maintenance filing does not degrade a
registration, it cancels it. Signa computes these deadlines (renewal cycles,
declarations of use, grace periods, restoration windows, and opposition
periods) from statutory rules modeled for 22 jurisdictions, with every rule
citing its legal sources and the full rule set published through the API for
inspection.
This study measures those computations against the register itself. We froze
a sample of 31,547 registrations across ten trademark offices, then a
tenfold expanded same-seed sample of 306,896 (a strict superset of the
first, drawn with the same seed), and compared our computed deadlines against
the dates offices publish on their own records, against 27,562 renewal and
maintenance filings that actually took place, and against 34,132 real
opposition proceedings.
On the full population, the computed renewal deadline matched the office's
own published date exactly in 96.08 percent of 282,393 comparisons; weighting
the pure statutory computation by how often each kind of record occurs in
production raises that to 98.55 percent. On a narrower modeled population,
defined after analysing why disagreements happen (a post hoc subgroup that
sets aside three documented categories of record), agreement is 99.74
percent. For the schedule the API actually serves, which anchors on the
office's own stated date, production-weighted agreement is 99.89 percent;
because that number uses the office's date as an input, it is not by itself
evidence that the rules are right. Every disagreement was investigated and
classified by cause; after that classification, the unexplained residual is 3
records out of 282,393. The study also worked in both directions: it caught
and fixed defects in our own rules, each published with results from before
and after the fix, and it identified 311 records classified as register-data
errors, with per-record evidence, where the register, not the computation,
carries the wrong date.
This is a first-party evaluation: Signa selected the metrics, wrote the
evaluator, corrected the system under test, and classified the
disagreements. It has not been independently audited. The artifacts (frozen
manifests, samples, events, oppositions, and per-record results) are
published at [github.com/signa-so/research](https://github.com/signa-so/research)
so any reader can check the work.
Complete methodology, per-office results, every fix with its legal basis,
and the classification of every disagreement.
## Results at a glance
| What was measured | Result |
| ---------------------------------------------------------------------------------------------------------- | ------------------------------------ |
| Full-population exact agreement with office-published dates (primary) | **96.08%** of 282,393 comparisons |
| Production-weighted exact agreement, pure statutory computation | **98.55%** |
| Exact agreement on the modeled population (post hoc subgroup) | **99.74%** of 282,393 comparisons |
| Agreement for the office-date-anchored schedule the API serves (uses the office's stated date as an input) | **99.89%**, production-weighted |
| Real renewal and maintenance filings inside computed windows | **93.1%** of 27,562 (99.4% at USPTO) |
| Real opposition filings inside computed opposition windows | **90.2%** of 23,751 (98.1% at EUIPO) |
| Unexplained residual after investigating every disagreement | **0.001%** (3 records) |
## What the study found
1. **The statute and the register audit each other.** Where a computed
deadline disagreed with the register, investigation attributed the
disagreement to the register more often than to the computation: 311
records classified as register-data errors, with per-record evidence,
against no further rule defect identified among the investigated
residuals. Computing deadlines from the law catches register errors that
a system echoing stored dates would repeat.
2. **Verification improved the product, in public.** The study surfaced
defects in our own rules and data handling. Each was fixed, tied to its
statute, and published with agreement measured before and after. No
correction was accepted on empirical fit alone; each required a statutory
or documented-data-source justification.
3. **Deadlines are computed fresh, never stored.** Every correction
applied to every record instantly. The frozen evaluation now runs on
every code change, so a change that moves even one date in the sample
blocks release until it is re-verified.
4. **You can check the rules yourself.** Every deadline rule, with its
legal citations and the date it was last verified, is available through
the API, and any deadline in the study can be recomputed with an API
key. See the [deadline rules guide](/guides/deadline-rules).
## Scope and limitations
Deadline rules currently cover 22 jurisdictions; for offices not yet
modeled (Japan, Korea, and China among them) the API states that plainly
rather than guessing. Opposition verification is strongest where the
underlying data is cleanest, and the report documents where it is bounded
by data quality rather than by the rules. Ground truth is the register
itself, which contains errors; the report treats that honestly in both
directions rather than assuming either side is right.
The full report contains the complete methodology, per-office tables,
statistical protocol, and every limitation stated plainly.