SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.04667 · ICML · 2022

Linear Complexity Randomized Self-attention Mechanism

Chong Wang, Lingpeng Kong, Lin Zheng

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 2 have no contract verdict; 2 failures of our instrument; 2 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/2204.04667.json · badge: /api/ran/2204.04667.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
hkunlp/efficient-attention community
Papers with Code archive
4 ran · 2 no recorded run
FunctionStatusWhere it lives
FlattenTranspose Ran
ran on a synthesized input
hkunlp/efficient-attention/efficient-attention/efficient_attention/lara.py
code served (permissive licence) · get_code("23536350c4d837de")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

INIT_ARGS = {}

x = torch.randn(2, 3, 4, 5)

ARGS = {'x': x}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
MultiheadAttention Ran
ran on a synthesized input · constructed an object; no result was computed
hkunlp/efficient-attention/efficient-attention/efficient_attention/lara.py
code served (permissive licence) · get_code("bd857b15ac85b005")
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, MultiheadAttention: 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
import torch.nn as nn
from argparse import ArgumentParser

torch.manual_seed(0)

ARGS = {
    'dim': 64,
    'num_heads': 4,
    'fp32': False,
    'qkv_bias': True,
    'attn_drop': 0.1,
    'proj_drop': 0.1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MultiheadAttention — 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 MultiheadAttention 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
prm_projection Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hkunlp/efficient-attention/efficient-attention/efficient_attention/lara.py
code served (permissive licence) · get_code("0c94a009ab2a3631")
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 Tensor, ndim 3, dtype family float, shape (2, 5, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
import torch.nn.functional as F

torch.manual_seed(0)

# Construct valid arguments for prm_projection
batch_size = 2
seq_len = 3
data_dim = 4
projection_dim = 5

# Create data tensor: shape (..., n, d) where n is sequence length, d is data dimension
data = torch.randn(batch_size, seq_len, data_dim)

# Create projection matrix: shape (..., m, d) where m is projection dimension, d is data dimension
projection_matrix = torch.randn(projection_dim, data_dim)

ARGS = {
    "data": data,
    "projection_matrix": projection_matrix,
    "normalize": True,
    "diagonal": False,
    "return_exp": False,
    "is_query": False,
    "eps": 1e-8
}
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 Tensor, ndim 3, dtype family float, shape (2, 5, 3) — shape (2, 5, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
remove_prefix Ran
ran; our contract draft was wrong, not the code
hkunlp/efficient-attention/efficient-attention/efficient_attention/lara.py
code served (permissive licence) · get_code("1fad32a65ad69c27")
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 str. 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

torch.manual_seed(0)

# Analyze the function:
# def remove_prefix(text, prefix):
#     return text[text.startswith(prefix) and len(prefix):]
#
# The function takes:
# - text: a string that has the .startswith() method
# - prefix: a string that has len() callable on it
#
# The function returns text[boolean_result and len(prefix):]
# where boolean_result is from text.startswith(prefix)
# This slices text starting from index (boolean_result and len(prefix))

ARGS = {
    "text": "hello_world",
    "prefix": "hello"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
LinearRA Not yet run
unverified (harvested, no recorded run)
hkunlp/efficient-attention/efficient-attention/efficient_attention/lara.py
code served (permissive licence) · get_code("f1033e63692c7a57")
How it ran

no invocation recorded.

add_nested_argument Not yet run
unverified (harvested, no recorded run)
hkunlp/efficient-attention/efficient-attention/efficient_attention/lara.py
code served (permissive licence) · get_code("42be9b05d3fbd3b9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 5 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
remove_prefix
brick of this paper's assembly: helper
1 other paper
1 later
2211.14688 (2022-11)
High-throughput ab initio reaction mechanism exploration in the cloud with automated multi-reference validation

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

Recently, random feature attentions (RFAs) are proposed to approximate the softmax attention in linear time and space complexity by linearizing the exponential kernel. In this paper, we first propose a novel perspective to understand the bias in such approximation by recasting RFAs as selfnormalized importance samplers. This perspective further sheds light on an unbiased estimator for the whole softmax attention, called randomized attention (RA). RA constructs positive random features via query-specific distributions and enjoys greatly improved approximation fidelity, albeit exhibiting quadratic complexity. By combining the expressiveness in RA and the efficiency in RFA, we develop a novel linear complexity selfattention mechanism called linear randomized attention (LARA). Extensive experiments across various domains demonstrate that RA and LARA significantly improve the performance of RFAs by a substantial margin.

For agents

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

get_harvested_code_for_paper("2204.04667")
get_code_for_paper("2204.04667")
have("2204.04667")

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

curl https://syntology.ai/api/ran/2204.04667.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.04667.svg)](https://syntology.ai/paper/2204.04667)

Connect an agent — have() is free.