SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.00710 · ICLR · 2021

Nearest Neighbor Machine Translation

Mike Lewis, Luke Zettlemoyer, Urvashi Khandelwal, Angela Fan, Dan Jurafsky

arXiv · PDF · Open in the Atlas

Code that ran

4 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2010.00710.json · badge: /api/ran/2010.00710.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
urvashik/knnmt canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
urvashik/knnlm canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
neulab/knn-transformers community
Papers with Code archive
1 ran · 3 no recorded run
hubreb/imitkd_ast community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
ActivationCapturer Ran
ran on a synthesized input · constructed an object; no result was computed
neulab/knn-transformers/knnlm.py
code served (permissive licence) · get_code("41c932a1879b6eca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, ActivationCapturer: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import nn

torch.manual_seed(0)

# Create a simple layer to capture from
layer = nn.Linear(4, 3)

# The ActivationCapturer is used as a hook callback, so we need to verify
# it works when called with (module, input, output) signature
# The forward method expects:
# - module: the module being hooked
# - input: tuple of input tensors
# - output: output tensor

ARGS = {
    "layer": layer,
    "capture_input": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ActivationCapturer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ActivationCapturer output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_dstore_path Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from neulab/knn-transformers
pointer only · get_code("05520f6527f04bde")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_index_path Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from neulab/knn-transformers
pointer only · get_code("918cf1d7f24a77f5")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_symbols_to_strip_from_output Ran
ran; our contract draft was wrong, not the code
urvashik/knnmt/fairseq_cli/generate.py
pointer only (licence: NONE) · get_code("88ce019380f10478")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, urvashik/knnmt when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

DIST Not yet run
unverified (harvested, no recorded run)
neulab/knn-transformers/knnlm.py
code served (permissive licence) · get_code("4f270d89f02eecd7")
How it ran

no invocation recorded.

KEY_TYPE Not yet run
unverified (harvested, no recorded run)
neulab/knn-transformers/knnlm.py
code served (permissive licence) · get_code("bf7d9cb24001654f")
How it ran

no invocation recorded.

KNNWrapper Not yet run
unverified (harvested, no recorded run)
neulab/knn-transformers/knnlm.py
code served (permissive licence) · get_code("0e7bf9fbf9dd8617")
How it ran

no invocation recorded.

KNN_Dstore Not yet run
unverified (harvested, no recorded run)
urvashik/knnlm/fairseq/knnlm.py
code served (permissive licence) · get_code("22d23f04ff2d14de")
How it ran

no invocation recorded.

KNN_Dstore Not yet run
unverified (harvested, no recorded run)
urvashik/knnmt/fairseq/knnlm.py
pointer only (licence: NONE) · get_code("d1ecba343e9e4ddb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, urvashik/knnmt when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

KNN_Dstore Not yet run
unverified (harvested, no recorded run)
hubreb/imitkd_ast/fairseq/fairseq/knnlm.py
code served (permissive licence) · get_code("dc707b421046950e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 7 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_symbols_to_strip_from_output 13 other papers
13 later
2105.05498 (2021-05)
Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction
2105.13022 (2021-05)
Adaptive Nearest Neighbor Machine Translation
2106.06751 (2021-06)
Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation
and 10 more not named here
get_dstore_path
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later · 1 only as an assembly brick
1911.00172 (2019-11)
Generalization through Memorization: Nearest Neighbor Language Models
2201.12431 (2022-01)
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
2402.17840 (2024-02)
Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
and 1 more not named here
get_index_path
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later · 1 only as an assembly brick
1911.00172 (2019-11)
Generalization through Memorization: Nearest Neighbor Language Models
2201.12431 (2022-01)
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
2402.17840 (2024-02)
Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems
and 1 more not named here
ActivationCapturer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2201.12431 (2022-01)
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
DIST
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2201.12431 (2022-01)
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
KEY_TYPE
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2201.12431 (2022-01)
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval
KNNWrapper
brick of this paper's assembly: entry
1 other paper
1 later
2201.12431 (2022-01)
Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce k-nearest-neighbor machine translation (kNN-MT), which predicts tokens with a nearest neighbor classifier over a large datastore of cached examples, using representations from a neural translation model for similarity search. This approach requires no additional training and scales to give the decoder direct access to billions of examples at test time, resulting in a highly expressive model that consistently improves performance across many settings. Simply adding nearest neighbor search improves a state-of-the-art German-English translation model by 1.5 BLEU. kNN-MT allows a single model to be adapted to diverse domains by using a domain-specific datastore, improving results by an average of 9.2 BLEU over zero-shot transfer, and achieving new state-of-the-art results-without training on these domains. A massively multilingual model can also be specialized for particular language pairs, with improvements of 3 BLEU for translating from English into German and Chinese. Qualitatively, kNN-MT is easily interpretable; it combines source and target context to retrieve highly relevant examples.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2010.00710")
get_code_for_paper("2010.00710")
have("2010.00710")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2010.00710.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2010.00710.svg)](https://syntology.ai/paper/2010.00710)

Connect an agent — have() is free.