embedding_bag_mean

std.nn.embedding_bag_mean · Level L3

The mean of the embeddings of a bag of ids: one vector for a whole set of tokens. Calls embedding_lookup.

(1/k)·Σᵢ E[idsᵢ]

Signature

embedding_bag_mean(E: f64[v, d], ids: i64[k]) → f64[d]

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.

Ef64[v, d]idsi64[k]embedding_lookuprowsMeanyyf64[d]
  • input
  • operation
  • constant
  • call
  • output

Verification

  • Signature proven by NOVA’s shape solver, for every size.
  • Equal to the reference np.take(E, ids, axis=0).mean(axis=0) in exact rational arithmetic, on all 40 test cases.
  • All 176 float64 results inside the running error bound; the closest uses 41% 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 57% of it.
Accuracy in detail
correctly rounded (the float64 nearest the exact value)
88%
largest error, in units in the last place
3.00

Identity

Calls
Called by
—
sha256:4bc030f9a184e3f41494effa660121c89a37bd09daec804433eb2550f2b4eb27

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.embedding_bag_mean · Ω:embedding_bag_mean
Pins
sha256:b4516c6262bae3d0091fe9483ad7de950d4e760a22558f3c6e1c7e485c49ff05this graph and the 1 it reaches through calls
Evidence
sha256:7ac341c8a9b8b929d737fbe5a0940890fa321c30930a0e13b82f3b968fb1a4b7the 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.