SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.04749 · ICLR · 2023

Toeplitz Neural Network for Sequence Modeling

Zhen Qin, Dongxu Li, Yiran Zhong, Yuchao Dai, Lingpeng Kong, Xiaodong Han, Weixuan Sun, Bowen He

arXiv · PDF · Open in the Atlas

Code that ran

2 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 1 has no contract verdict; 1 failure of our instrument; 4 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/2305.04749.json · badge: /api/ran/2305.04749.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
Doraemonzzz/tnn-pytorch marked official in Papers with Code
Papers with Code archive
2 ran · 4 no recorded run
FunctionStatusWhere it lives
ActLayer Ran
ran on a synthesized input · constructed an object; no result was computed
Doraemonzzz/tnn-pytorch/tnn_pytorch/tno.py
code served (permissive licence) · get_code("31fbf829f9032e39")
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, ActLayer: 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
import logging

# Set up logging
logging.basicConfig(level=logging.INFO)

# Set seed for reproducibility
torch.manual_seed(0)

# Define ARGS with all parameters for ActLayer.__init__
ARGS = {
    'act_fun': 'gelu'
}
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 ActLayer — 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 ActLayer 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_activation_fn Ran
ran; our contract draft was wrong, not the code
Doraemonzzz/tnn-pytorch/tnn_pytorch/tno.py
code served (permissive licence) · get_code("9a369f7c4e13695c")
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 builtin_function_or_method. 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.functional as F
import logging

torch.manual_seed(0)

logger = logging.getLogger('print_config')

# The function get_activation_fn takes a single parameter: activation (a string)
# It returns a callable (activation function) based on the activation name
# The function doesn't actually use the returned function in its body,
# it just returns it, so we only need to provide valid activation strings

ARGS = {
    'activation': 'gelu'
}
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 builtin_function_or_method — a builtin_function_or_method output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a builtin_function_or_method 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
Rpe Not yet run
unverified (harvested, no recorded run)
Doraemonzzz/tnn-pytorch/tnn_pytorch/tno.py
code served (permissive licence) · get_code("2d64d80da2d57529")
How it ran

no invocation recorded.

Tno Not yet run
unverified (harvested, no recorded run)
Doraemonzzz/tnn-pytorch/tnn_pytorch/tno.py
code served (permissive licence) · get_code("a27f103f1053957d")
How it ran

no invocation recorded.

get_norm_fn Not yet run
unverified (harvested, no recorded run)
Doraemonzzz/tnn-pytorch/tnn_pytorch/tno.py
code served (permissive licence) · get_code("2595765cbd58bb82")
How it ran

no invocation recorded.

print_params Not yet run
unverified (harvested, no recorded run)
Doraemonzzz/tnn-pytorch/tnn_pytorch/tno.py
code served (permissive licence) · get_code("956837d2bafefb1b")
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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Sequence modeling has important applications in natural language processing and computer vision. Recently, the transformer-based models have shown strong performance on various sequence modeling tasks, which rely on attention to capture pairwise token relations, and position embedding to inject positional information. While showing good performance, the transformer models are inefficient to scale to long input sequences, mainly due to the quadratic space-time complexity of attention. To overcome this inefficiency, we propose to model sequences with a relative position encoded Toeplitz matrix and use a Toeplitz matrix-vector production trick to reduce the space-time complexity of the sequence modeling to log linear. A lightweight sub-network called relative position encoder is proposed to generate relative position coefficients with a fixed budget of parameters, enabling the proposed Toeplitz neural network to deal with varying sequence lengths. In addition, despite being trained on 512-token sequences, our model can extrapolate input sequence length up to 14K tokens in inference with consistent performance. Extensive experiments on autoregressive and bidirectional language modeling, image modeling, and the challenging Long-Range Arena benchmark show that our method achieves better performance than its competitors in most downstream tasks while being significantly faster. The code is available at https://github.com/OpenNLPLab/Tnn.

For agents

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

get_harvested_code_for_paper("2305.04749")
get_code_for_paper("2305.04749")
have("2305.04749")

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

curl https://syntology.ai/api/ran/2305.04749.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.04749.svg)](https://syntology.ai/paper/2305.04749)

Connect an agent — have() is free.