accuracy

std.nn.accuracy · Level L2

Classification accuracy: the share of rows whose largest logit is at the position of the largest label entry (one-hot labels).

(1/n)·Σᵢ [argmaxⱼ Zᵢⱼ = argmaxⱼ Yᵢⱼ]

Signature

accuracy(logits: f64[n, c], labels: f64[n, c]) → f64[]

Structure

The function as NOVA stores it: one box per input, operation and output, and arrows that carry values. A double border marks another library function this one runs — called once, or by Scan once per element; select it to open that function.

logitsf64[n, c]labelsf64[n, c]ArgMaxguessArgMaxtruthEqualhitMeanaccaccf64[]
  • input
  • operation
  • constant
  • call
  • output

Verification

  • Signature proven by NOVA’s shape solver, for every size.
  • Equal to the reference np.mean(np.argmax(logits, 1) == np.argmax(labels, 1)) in exact rational arithmetic, on all 40 test cases.
  • All 40 float64 results inside the running error bound; the closest uses 17% of it.
  • Interpreter and NumPy backend return bit-identical results.
  • At float32 too: the 40 test cases rounded to float32, and 40 of them inside the running error bound at u = 2⁻²⁴; the closest uses 17% of it.
Accuracy in detail
correctly rounded (the float64 nearest the exact value)
100%
largest error, in units in the last place
0.40

Identity

Calls
—
Called by
—
sha256:7c273578d51117fc08bb69929b672ae4b7772d9a142da05acc8b7b8ae0590cbf

The semantic hash of the graph. It changes when the program changes, and never when only its documentation does.

Control handle

Symbol
Ω:std.nn.accuracy · Ω:accuracy
Pins
sha256:f09742eb623f371ab1900d34bf3607c94bda766d2db55dbffc0164687484ee5bthis graph alone
Evidence
sha256:4ffa87f060eb28890e6fe4cc2c9f52ec8cf7fd3a935b0b03a461a4bf8680ed80the hash of its verification record
Needs
no capability: a pure function

Through NOVA’s control layer, the symbol launches this function only while the program still matches what it pins: a change to this graph, or to any graph it reaches, needs a migration first.

ΣEML 2026

Efficient New Language — a high-density semantic overlay for humans and AI agents.

This site’s demos run on the real EML toolchain, in your browser.

© 2026 EveMissLab (一言諾科技有限公司) / Neo.K. All rights reserved.