Proprietary Timing Integrity — Pilot
Results-only. Method proprietary. Patent pending (priority Feb 2026).
Evaluation frame (definitions only)
What is transformed: an agreed primary clock-comparison or residual series from your submission (definition fixed at onboarding or in the pilot agreement)—we return post-processed outputs and statistics; we do not disclose internal processing.
What you compare to: Before = same stream, same metric (typically RMS on that primary series), before our confidential post-process. After = identical metric on what we return. Same inputs, same metric definition—no moved goalposts.
What “% improvement” means: relative reduction in that agreed primary statistic from before to after; where we cite holdout results, no refit on the evaluation window (see technical note §3). Full alignment with this frame: technical note.
What Tare returns (form only, no mechanics): Evaluation outputs—corrected time-aligned traces (series/residuals) and a written pack; summary statistics (principally RMS, plus any metrics named in onboarding); consistency- or deviation-style indicators where specified; optional review-level signals for internal use—not formal confidence/uncertainty statements unless explicitly included in your agreement.
1. GNSS clock comparison
On real-world GNSS data (including IGS final combined clock products), our correction delivers typical held-out RMS reduction around ~45%, with strict-window runs up to ~81%, and post-correction residuals in the 17-22 ns range. Validated across multiple years and analysis centers; no refit on the test window.
Full results and validation protocol (no method disclosure): Technical note — banlys.com/tare.
2. Event ordering
Illustration only—not a second empirical field claim. In a simple controlled ordering exercise, two events are separated by 50 ns; the task is which occurred first. Two representative timing-uncertainty regimes (one fine, one coarse—orders of magnitude apart) recover correct order ~99% vs ~64% of the time in this exercise. It shows why residual scale matters for sequence calls; it does not describe our correction, inputs, or how outputs are produced. Quantitative GNSS clock-comparison claims remain only in the technical note.
Illustrative: correct event order under two timing-uncertainty regimes (50 ns separation exercise)
3. Pilot invitation
We provide results-only access; the method remains proprietary. Suitable for labs, HFT desks, telecom, and PPP deployments. You send comparison data (or run a defined protocol); we return corrected results and before/after metrics under confidentiality. No formulas, parameters, or code are disclosed.
Pilot objective: decision-grade evidence on your own data. We evaluate against a predefined metric set agreed in onboarding and return a clear before/after package your technical and procurement teams can review—still no method disclosure.
Standard deliverables (exact naming and file layout in your pilot agreement; no algorithm or parameters):
- Before/after comparison on the primary residual or comparison series you submit—principally RMS and the agreed summary statistics.
- Corrected series or equivalent outputs as specified at onboarding (format in the agreement).
- A short written summary suitable for internal technical and procurement review.
This cohort runs May 1–July 30, 2026. Ten places are available. Pilot fee: $45,000 (academic) or $195,000 (commercial) for the 90-day period (see FAQ). Applications reviewed individually. Pilot participants will receive priority access to licensing discussions if the technology proceeds to commercial deployment.