Rule 1
Show the error bar
No ranking without uncertainty. A confident wrong answer is the most expensive kind.
Validation and security
Forgite reports error and uncertainty next to every number, keeps a full record of how each result was made, and protects chemistry your competitors would like to see.
Abstract
01 · Principles
Rule 1
No ranking without uncertainty. A confident wrong answer is the most expensive kind.
Rule 2
Accuracy is measured on structures the model never saw, chosen before training.
Rule 3
Every result records its inputs, model version, settings and seed.
Rule 4
Models propose; named people approve anything that costs lab time.
02 · Method
Hold out structures by composition family, not at random, so the test reflects new chemistry.
Report energy, force and stress errors on the held-out set.
Confirm predicted uncertainty matches observed error.
Where measurements exist, compare predicted properties with them.
03 · Context
| Area | Reference | How Forgite relates |
|---|---|---|
| Data | FAIR data principles | Results stored with identifiers, metadata and provenance for reuse |
| Structures | CIF, POSCAR, OPTIMADE | Read and write standard formats; OPTIMADE queries Planned |
| Information security | ISO/IEC 27001 | Controls designed with it in mind; certification Planned |
| Service controls | SOC 2 Type II | Audit Planned |
| Export control | Applicable export regulations | Customer responsibility for controlled chemistry; on-premises option available |
04 · Audit trail
result: cand-0118/sigma value: 12.4 mS/cm # ± 2.1, 95% interval from: structure: cand-0118.cif@sha256:9f2c… potential: equiva/battery-ft@0.3.1 md: { T_K: [500, 600, 700], seeds: 3, time_ps: 1000 } campaign: sse-li-argyrodite-r1 approved_by: program-lead@customer measured: pending
05 · Security
06 · Questions
No. We have not completed any certification or audit. SOC 2 Type II and ISO/IEC 27001 are planned before general availability.
Forgite supports the evidence work by recording how each result was produced, but it does not certify materials or properties. Measurements from your lab remain the evidence.
By default, nobody. Support access is granted per incident, time-limited and logged.
Next step
Send the property you care about and the reference data you trust. We will describe the held-out test before we train anything.