SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.10644 · ACL · 2024

Linear Transformers with Learnable Kernel Functions are Better In-Context Models

Nikita Balagansky, Daniil Gavrilov, Yaroslav Aksenov, Sofia Lo, Cicero Vaina, Boris Shaposhnikov, Alexey Gorbatovski

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 0 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/2402.10644.json · badge: /api/ran/2402.10644.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
corl-team/rebased canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
fft_conv Ran
ran; our contract draft was wrong, not the code
corl-team/rebased/src/mixers/convolution.py
code served (permissive licence) · get_code("8def605349357890")
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, 4, 8) 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
from einops import rearrange

torch.manual_seed(0)

# Create small tensors with distinct dimensions
batch_size = 2
dim = 4
seqlen = 8

# u: input tensor, shape (batch, dim, seqlen)
u = torch.randn(batch_size, dim, seqlen, dtype=torch.float32)

# k: kernel tensor, shape (dim,) or (dim, seqlen)
k = torch.randn(dim, seqlen, dtype=torch.float32)

# dropout_mask: optional mask, shape (batch, dim) or None
dropout_mask = torch.ones(batch_size, dim, dtype=torch.float32)

# k_rev: optional reversed kernel, same shape as k or None
k_rev = torch.randn(dim, seqlen, dtype=torch.float32)

# gelu: boolean flag
gelu = True

ARGS = {
    "u": u,
    "k": k,
    "dropout_mask": dropout_mask,
    "gelu": gelu,
    "k_rev": k_rev,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, 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, 4, 8) — shape (2, 4, 8) 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
import_from_str Ran
ran; our contract draft was wrong, not the code
corl-team/rebased/src/utils.py
code served (permissive licence) · get_code("c849028785a49d49")
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 type. 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

# Test valid imports
valid_path_class = "torch.nn.Linear"
valid_path_function = "torch.sum"
valid_path_module = "os.path.join"

# Create ARGS dict with a valid string path to import
# Using a built-in module/class that definitely exists
ARGS = {
    "path": "torch.nn.Linear"
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
init_feature_map Ran
ran; our contract draft was wrong, not the code
corl-team/rebased/src/mixers/rebased.py
code served (permissive licence) · get_code("684a4794c1e731b4")
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 TaylorExp. 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 math

torch.manual_seed(0)

ARGS = {
    'feature_map': 'taylor_exp',
    'input_dim': 4,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
opt_einsum, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TaylorExp — a TaylorExp output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TaylorExp 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
init_feature_map Ran
ran; our contract draft was wrong, not the code
corl-team/rebased/flash_linear_attention/fla/layers/rebased.py
code served (permissive licence) · get_code("e8f74b2adeb59c06")
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 TaylorExp. 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 math

torch.manual_seed(0)

ARGS = {
    'feature_map': 'taylor_exp',
    'input_dim': 4,
    'temp': 1.0,
    'head_dim_idx': -1,
    'eps': 1e-12,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
opt_einsum, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TaylorExp — a TaylorExp output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TaylorExp 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
init_feature_map Ran
ran; our contract draft was wrong, not the code
corl-team/rebased/flash_linear_attention/fla/layers/rebased_fast.py
code served (permissive licence) · get_code("2101df8aafbd7a12")
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 TaylorExp. 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 math

torch.manual_seed(0)

ARGS = {
    'feature_map': 'taylor_exp',
    'input_dim': 4,
}
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 TaylorExp — a TaylorExp output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TaylorExp 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
init_feature_map Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
corl-team/rebased/src/mixers/based.py
code served (permissive licence) · get_code("b91fbb3bff1255fb")
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 TaylorExp. 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 math

torch.manual_seed(0)

ARGS = {
    'feature_map': 'taylor_exp',
    'input_dim': 4,
    'parabola_coeffs': [1.0, 1.0, 1.0],
    'memory_save_forward': True,
    'temp': 1.0,
    'head_dim_idx': -1,
    'eps': 1e-12,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
opt_einsum, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TaylorExp — a TaylorExp output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TaylorExp 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

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 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 1 the same month, 2 later) and 1 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
fft_conv 1 other paper
1 later
2406.02528 (2024-06)
Scalable MatMul-free Language Modeling
import_from_str 1 other paper
1 the same month
2402.18668 (2024-02)
Simple linear attention language models balance the recall-throughput tradeoff
init_feature_map 1 other paper
1 later
2407.14207 (2024-07)
Longhorn: State Space Models are Amortized Online Learners

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

Advancing the frontier of subquadratic architectures for Language Models (LMs) is crucial in the rapidly evolving field of natural language processing. Current innovations, including State Space Models, were initially celebrated for surpassing Transformer performance on language modeling tasks. However, these models have revealed deficiencies in essential In-Context Learning capabilities -a domain where the Transformer traditionally shines. The Based model emerged as a hybrid solution, blending a Linear Transformer with a kernel inspired by the Taylor expansion of exponential functions, augmented by convolutional networks. Mirroring the Transformer's in-context adeptness, it became a strong contender in the field. In our work, we present a singular, elegant alteration to the Based kernel that amplifies its In-Context Learning abilities evaluated with the Multi-Query Associative Recall task and overall language modeling process, as demonstrated on the Pile dataset.

For agents

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

get_harvested_code_for_paper("2402.10644")
get_code_for_paper("2402.10644")
have("2402.10644")

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

curl https://syntology.ai/api/ran/2402.10644.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.10644.svg)](https://syntology.ai/paper/2402.10644)

Connect an agent — have() is free.