Measured, not promised.

Every result below was written down before the data existed, run on held-back data, and recomputed independently.

CapabilityResultScope
Picks better experiments than the standard toolsBeat adaptive L#, L# and KV on 7 of 7 held-out implementations (p 4.5e-5)real TLS and OPC-UA implementations
Holds up on live systemsBeat the same tools across all 4 behaviour classeslive MQTT brokers
Makes an AI a better predictorDeepSeek Flash predicted much better from Ekmageion's experiments than from its own: +1.11 nats, 13 of 14 systems, preregisteredlive MQTT brokers
Stays right on bigger systemsScored 0.657 vs 0.870 for a retrained Transformer, 5 of 5 sealed seeds, at 30–125 KB vs 14.4 MBsystems 4× larger, episodes 4× longer than training
Gets better with useA growing library beat a frozen one (50 vs 20 models) and store-everything memory, at 0.6 KB vs 39 KBlibrary growth over a run
Predicts unseen quantum devicesAlone, out-predicted a frontier AI model on 15 of 18 devices no AI had seensimulated quantum devices
Runs smallAn ordinary CPU, models in kilobytes, no GPUinside your network

Preregistration

Each test is written down before its data exists: the systems, the comparison, the threshold that counts as a pass and the number of seeds. The record is sealed, and the result is read against it, not the other way round.

Sealed data

Held-back systems and seeds stay unseen until the test runs. Ekmageion is tuned on other systems and other seeds, so a pass means the behaviour carried over to data nobody used while building it.

Scrambled-twin controls

Every claimed gain is run again against a twin whose structure has been scrambled. If the twin does as well, the gain came from something other than the structure Ekmageion found, and the claim does not stand.

Independent recompute

Scores are recomputed from the raw logs by a separate evaluator with fixed thresholds and seeds. A result that cannot be rebuilt from the logs is not published.