mse

std.loss.mse · Level L0

Mean squared error.

(1/n)·Σᵢ (yᵢ − tᵢ)²

Signature

mse(y: f64[n], t: f64[n]) → 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.

yf64[n]tf64[n]SubtractdMultiplyddMeanllf64[]
  • input
  • operation
  • constant
  • call
  • output

Verification

  • Signature proven by NOVA’s shape solver, for every size.
  • Equal to the reference np.mean((y - t) ** 2) in exact rational arithmetic, on all 40 test cases.
  • All 40 float64 results inside the running error bound; the closest uses 30% 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 28% of it.
Accuracy in detail
correctly rounded (the float64 nearest the exact value)
78%
largest error, in units in the last place
1.51

Identity

Calls
—
Called by
—
sha256:beb47019027c534e6e3fdb812e6f289ba99bb5c636648b5701afb7b648d60bd6

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

Control handle

Symbol
Ω:std.loss.mse · Ω:mse
Pins
sha256:549006f5061f17cf030f01f393ce99e60c09f9049605fda9658f76a7bea5f5fdthis graph alone
Evidence
sha256:83de8fd4946abe1bd51e838b71b22b7c80bd2a7c370d117f37d293436e4b20dcthe 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.