embedding_lookup
std.nn.embedding_lookup · Level L3Embedding lookup: the rows of the table E at the integer ids, in order (repeats allowed).
Yᵢ = E[idsᵢ]
Signature
embedding_lookup(E: f64[v, d], ids: i64[k]) → f64[k, 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.
- 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)in exact rational arithmetic, on all 40 test cases. - All 598 float64 results are exact: the error is zero.
- Interpreter and NumPy backend return bit-identical results.
- At float32 too: the 40 test cases rounded to float32, and 40 of them exact, with zero error.
Accuracy in detail
- correctly rounded (the float64 nearest the exact value)
- 100%
- largest error, in units in the last place
- 0
Identity
sha256:368b6e6fa17aa116e98faacc219cd8b85757f1295e48055aa42f211a6b14dbb4The 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_lookup · Ω:embedding_lookup
- Pins
sha256:101cb0ac41491c65cdbad14c524c6885d9cdccf39168181a5e15d6914aab2e45this graph alone- Evidence
sha256:8fb5e24d645cc5375f3a9da218361d0dd09b2c35867cbf4f0d94189bfb8202acthe 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.