Flynn  /  Validation
Validated across five domains · Same source · Same flags

One binary.
Infinite telemetry.

Footprint
8,480bytes

Eight thousand four hundred and eighty bytes — not 8 MB, not 8 GB. It fits on the microcontroller already inside the machine.

Calibration
1,700samples

Learns normal behavior in 1,700 samples — under two seconds at kilohertz rates — then locks. No labels, no tuning.

Heap allocations
0

Zero dynamic allocation after initialization. Safety-critical firmware forbids the heap; Flynn meets that rule by construction.

Delivery
Binary

Flynn ships as a compact binary, compiled for your hardware. Deterministic and verifiable against published test vectors; full source available to certifying authorities under NDA.

False positives
0/ 120 h

Zero false positives across 120 hours of soak testing, with a 95%-confidence ceiling of 0.025 per hour.

Behaviour
Bit-identical

Deterministic across runs and silicon. Replayable. Auditable. Eligible for safety-certified voting architectures.

Samples required for complete enrollment will vary by equipment type, state, and operational envelope.


Domain 01 · Bearing vibration

The industry-standard bearing benchmark.

The CWRU bearing dataset spans 27 fault pairs across inner-race, ball, and outer-race faults at three severity levels. The recommended operating point produces the deployed numbers below, with no oracle threshold and no per-fault tuning.

Protocol

Dataset
Case Western Reserve University bearing data
Fault pairs
27 (inner race · ball · outer race × 3 severities)
Threshold
Self-calibrated · locked at deployment
Configuration
Default operating point
Default mode
Precision
0.988
of alarms raised, share correct
F1 score
0.829
harmonic mean
Recall
0.996
share of real faults caught
Tandem mode (single compile flag)
Precision
0.972
Recall
0.996
Use case
Rotating machinery

Domain 02 · Run-to-failure

Caught two failing bearings. Stayed silent on the healthy ones.

An industry-standard run-to-failure dataset spans more than 30 days of continuous vibration from four bearings, two of which failed and two of which survived. Flynn ran on all eight accelerometer channels simultaneously — zero configuration changes between them.

Channels
8
simultaneous · zero config
Failing bearings detected
2 / 2
both before documented failure
Lead time
~17 d
ahead of failure date
Healthy bearings
2 / 2
silent across full window
Duration
30+ days
continuous vibration
False alarms
0
across healthy channels

Protocol

Dataset
NASA IMS Bearing dataset
Setup
4 bearings · 8 accelerometer channels
Outcome
2 failed · 2 survived
Sampling
Continuous, multi-day
Configuration
Same source, same flags across channels
Lee, J., Qiu, H., Yu, G., Lin, J. and Rexnord Technical Services (2007). IMS, University of Cincinnati. "Bearing Data Set", NASA Prognostics Data Repository, NASA Ames Research Center, Moffett Field, CA.
In recent testing of an updated build, the healthy-bearing channels were not perfectly silent: Flynn surfaced a low-magnitude signal on those channels that directly correlated with the failing bearings — consistent with accelerometer cross-talk bleeding from the failing-bearing channels, not an independent fault on the healthy bearings. Reported here as correlated cross-talk rather than a false positive.

Domain 03 · Ambient & diurnal

Operationally compatible with shift-cycle review.

336 hours of ambient time-series covering temperature, environmental, and process-control signals — slow-changing data with strong day-night cycles. Flynn maintains a false-positive rate that fits the cadence of normal operator review.

Protocol

Duration
336 hours
Signal types
Temperature · environmental · process-control
Review cadence
Shift-cycle compatible
FP / hour
0.074 – 0.080
across 336 hours
Alerts / day
~1.8 – 1.9
reviewable in normal rhythm
Tuning
None
same source as bearing

Domain 04 · Electrical grid stability

Electrical-bus stability with no domain assumptions.

10,000 instances across 12 features of electrical-grid stability data — a signal domain that shares nothing with rotating-machinery vibration. Same source, same flags, no per-domain configuration.

F1 score
0.532
no per-domain config
Instances
10,000
Features
12

Domain 05 · Soak testing

The number operators ask for first.

The false-alarm rate is the first thing operators ask about. Across 120 simulated hours of synthetic vibration — 5 random seeds × 24 hours each — Flynn produced zero false positives, with a 95%-confidence ceiling of 0.025 per hour. On bearing normal-operation traces, zero across 1.2 million samples.

Protocol

Synthetic soak
120 hours · 5 seeds × 24 hours
Bearing soak
1.2 million normal-operation samples
Confidence
95% CI bound on FP rate
FP · synthetic
0
120 hours
FP · bearing
0
1.2 M samples
95% CI bound
< 0.025/h
false-positive rate

Zero false positives on bearing data. Operationally low on diurnal. The numbers operators actually care about.


Reproduce these numbers

Benchmarks, source, reproduction.

Flynn's empirical claims are reproducible from committed benchmarks and committed source code. Artifacts and reproduction instructions are available to evaluation licensees.

Read the whitepaper
Email
tripp@entromorphic.com
Available
Source code · benchmarks · scripts · datasets manifest
Under
Evaluation license · NDA required