Performance

Current implementation, supported use and explicit qualification limits.

Experimental Feature

This feature is experimental and may change significantly in future versions.

Current release status

Public document hashing and exact integer aggregation are live with signed results. Native consensus, mining, issuance, COMPUTE payments and rewards are inactive. Independent operation is not yet demonstrated.

No production throughput claim

No authenticated aggregate workload/minute, daily volume, uptime or network-latency measurement is published. The website does not substitute random counters or static latencies.

Recorded tests

Existing Linux AMD64 tests used emulation on a founder-controlled host. Software execution/hash timings are not bare-metal Gamma rates, WAN capacity, ASIC/rental costs or an economic-security budget.

How to qualify

Measure actual accepted useful work/resource throughput, propagation/loss, catch-up, concentration, sustained costs and recovery on consenting independently administered hosts. Gateway RTT alone is not peer propagation or consensus finality.

Observe without inventing telemetry

A gateway request has a time and round trip. That measurement is useful, but it is not global peer latency, validator uptime or consensus health.

BoundaryImplementation / evidenceMeaning
Gateway observationActual health/policy response + browser timestampAvailability of that request only
Workload observationActual job ID and signed resultNo fabricated throughput or global daily total
Configured host metadataKnown Seed/Gamma recordsNot independently measured online operators
Independent resource evidenceConsenting hosts / own keys / WAN tracesNot yet supplied by local identities or containers

Practical procedure

  1. 1Record source, timestamp, scope and actual response.
  2. 2Separate configured addresses from measured reachability.
  3. 3Retain errors and missing measurements as unavailable.
  4. 4For outside qualification, measure resource throughput, propagation, recovery and actual costs.
Technical reference · scope is explicit
Observation = source + time + actual measurement + limitation
Gateway RTT ≠ validator latency
Signing keys ≠ independently controlled operators
Historical height ≠ advancing production consensus

Limits and failure cases

  • No invented uptime percentage, eight-region map, 47-peer total or confidence score.
  • A resource benchmark is not a guaranteed attacker-cost lower bound.
  • No arbitrary outside-operator count proves founder-independent security.