SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.01638 · ICML · 2023

Sequence Modeling with Multiresolution Convolutional Memory

Emily Fox, Jiaxin Shi, Ke Wang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 8 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; 2 failures of our instrument; 5 no recorded run), measured 2026-11-22; 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/2305.01638.json · badge: /api/ran/2305.01638.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
thjashin/multires-conv canonical (classifier label)
classifier basis: classifier_2025
3 ran · 5 no recorded run
FunctionStatusWhere it lives
MultiresLayer Ran
ran on a synthesized input · constructed an object; no result was computed
thjashin/multires-conv/layers/multireslayer.py
code served (permissive licence) · get_code("c27418dba9fbd66d")
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, MultiresLayer: 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 math

torch.manual_seed(0)

ARGS = {
    'd_model': 4,
    'kernel_size': 3,
    'depth': 2,
    'wavelet_init': None,
    'tree_select': 'fading',
    'seq_len': None,
    'dropout': 0.1,
    'memory_size': None,
    'indep_res_init': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pywt, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MultiresLayer — 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 MultiresLayer 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
forward_uniform Ran
ran; our contract draft was wrong, not the code
thjashin/multires-conv/layers/multireslayer.py
code served (permissive licence) · get_code("88f02c31c56c7058")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 16) 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 as nn

torch.manual_seed(0)

# Parameters for forward_uniform
batch_size = 2
channels = 4
seq_length = 16
depth = 2
kernel_size = 3
memory_size = 8

# Input signal x: (batch, channels, time)
x = torch.randn(batch_size, channels, seq_length)

# Wavelet filters h0 (lowpass) and h1 (highpass): (channels, 1, kernel_size)
h0 = torch.randn(channels, 1, kernel_size)
h1 = torch.randn(channels, 1, kernel_size)

# Reconstruction weights w: (channels, latent_dim)
# latent_dim needs to be large enough to hold all coefficients
# After depth iterations, we have depth+1 coefficient layers
# The latent dimension grows as: 1, then 1+1=2, then 2+2=4, then 4+4=8, etc.
# For depth=2: we get 1 + 1 + 2 = 4 layers, plus final reconstruction weight
latent_dim = 16
w = torch.randn(channels, latent_dim)

ARGS = {
    'x': x,
    'h0': h0,
    'h1': h1,
    'w': w,
    'depth': depth,
    'kernel_size': kernel_size,
    'memory_size': memory_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 4, 16) — shape (2, 4, 16) 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
masked_meanpool Ran
ran; our contract draft was wrong, not the code
thjashin/multires-conv/classification.py
code served (permissive licence) · get_code("d34b5691b224ae80")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# Create a small batch of sequences with different lengths
batch_size = 2
feature_dim = 4
max_length = 5

# x should be shape (batch_size, feature_dim, max_length)
x = torch.randn(batch_size, feature_dim, max_length)

# lengths should be shape (batch_size,) with actual sequence lengths
lengths = torch.tensor([3, 4], dtype=torch.long)

ARGS = {
    "x": x,
    "lengths": lengths,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
eval Not yet run
unverified (harvested, no recorded run)
thjashin/multires-conv/autoregressive.py
code served (permissive licence) · get_code("32d5fef9113aac56")
How it ran

no invocation recorded.

forward_fading Not yet run
unverified (harvested, no recorded run)
thjashin/multires-conv/layers/multireslayer.py
code served (permissive licence) · get_code("a50200f714b086df")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
thjashin/multires-conv/classification.py
code served (permissive licence) · get_code("6bde61fec84781de")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
thjashin/multires-conv/autoregressive.py
code served (permissive licence) · get_code("ad628a83df7e160a")
How it ran

no invocation recorded.

uniform_tree_select Not yet run
unverified (harvested, no recorded run)
thjashin/multires-conv/layers/multireslayer.py
code served (permissive licence) · get_code("b05c3cd049bf812e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

Efficiently capturing the long-range patterns in sequential data sources salient to a given task-such as classification and generative modeling-poses a fundamental challenge. Popular approaches in the space tradeoff between the memory burden of brute-force enumeration and comparison, as in transformers, the computational burden of complicated sequential dependencies, as in recurrent neural networks, or the parameter burden of convolutional networks with many or large filters. We instead take inspiration from waveletbased multiresolution analysis to define a new building block for sequence modeling, which we call a MULTIRESLAYER. The key component of our model is the multiresolution convolution, capturing multiscale trends in the input sequence. Our MULTIRESCONV can be implemented with shared filters across a dilated causal convolution tree. Thus it garners the computational advantages of convolutional networks and the principled theoretical motivation of wavelet decompositions. Our MULTIRESLAYER is straightforward to implement, requires significantly fewer parameters, and maintains at most a O(N log N ) memory footprint for a length N sequence. Yet, by stacking such layers, our model yields state-of-the-art performance on a number of sequence classification and autoregressive density estimation tasks using CIFAR-10, ListOps, and PTB-XL datasets.

For agents

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

get_harvested_code_for_paper("2305.01638")
get_code_for_paper("2305.01638")
have("2305.01638")

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

curl https://syntology.ai/api/ran/2305.01638.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.01638.svg)](https://syntology.ai/paper/2305.01638)

Connect an agent — have() is free.