SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.10633 · 2021

ResLT: Residual Learning for Long-tailed Recognition

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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, 1 violated it and 0 have no contract verdict; 4 failures 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/2101.10633.json · badge: /api/ran/2101.10633.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
jiequancui/ResLT canonical (classifier label)
classifier basis: classifier_2025
4 ran · 4 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from skyz215/proco
pointer only; the stored copy get_code serves, from skyz215/proco, is pointer only (licence: NONE) · get_code("b793b278a771fd52")
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.

crossEntropy Ran
ran; our contract draft was wrong, not the code
jiequancui/ResLT/Inat/iNaturalTrain_reslt.py
code served (permissive licence) · get_code("e3b2c8f412a7b141")
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 0, dtype family float, shape () 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
import torch.nn.functional as F

torch.manual_seed(0)

# Parameters for crossEntropy function
batch_size = 2
num_classes = 4
input_dim = 3

# softmax: a callable that takes logits and returns probabilities
softmax = nn.Softmax(dim=1)

# logit: tensor of shape (batch_size, num_classes) - raw model outputs
logit = torch.randn(batch_size, num_classes)

# label: tensor of shape (batch_size,) with class indices
label = torch.tensor([0, 2], dtype=torch.long)

# weight: tensor of shape (batch_size,) - per-sample weights
weight = torch.tensor([1.0, 1.5], dtype=torch.float32)

# num_classes: integer
num_classes_val = 4

ARGS = {
    "softmax": softmax,
    "logit": logit,
    "label": label,
    "weight": weight,
    "num_classes": num_classes_val
}
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 0, dtype family float, shape () — shape () 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
label_smoothing Ran
ran, violated the contract we drafted
jiequancui/ResLT/ImageNetLT/ImageNetTrain_reslt.py
code served (permissive licence) · get_code("9dadc657844ac856")
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 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
import torch.nn as nn

torch.manual_seed(0)

# Construct the arguments
batch_size = 2
num_classes = 4

# y_batch_tensor: one-hot encoded labels of shape (batch_size, num_classes)
y_batch_tensor = torch.nn.functional.one_hot(
    torch.tensor([0, 2]), num_classes=num_classes
).float()

# num_classes: integer representing number of classes
num_classes_arg = 4

# delta: smoothing factor (typically small, like 0.1)
delta = 0.1

ARGS = {
    "y_batch_tensor": y_batch_tensor,
    "num_classes": num_classes_arg,
    "delta": delta,
}
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 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
mixup_criterion Ran
ran; our contract draft was wrong, not the code
jiequancui/ResLT/CIFAR/cifarTrain_reslt_cifar10.py
code served (permissive licence) · get_code("9b2fdcdcc7de945a")
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 0, dtype family float, shape () 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)

# Create a simple criterion (loss function)
criterion = nn.CrossEntropyLoss()

# Create predictions tensor (batch_size=2, num_classes=4)
pred = torch.randn(2, 4)

# Create target tensors for y_a and y_b (batch_size=2, class indices)
y_a = torch.tensor([0, 2])
y_b = torch.tensor([1, 3])

# Create lambda weight
lam1 = 0.7

ARGS = {
    "criterion": criterion,
    "pred": pred,
    "y_a": y_a,
    "y_b": y_b,
    "lam1": lam1
}
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 0, dtype family float, shape () — shape () 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
mixup_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiequancui/ResLT/CIFAR/cifarTrain_reslt_cifar10.py
code served (permissive licence) · get_code("760098c40816bbe8")
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 tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 numpy as np

torch.manual_seed(0)
np.random.seed(0)

# Create small tensors for x and y
batch_size = 2
feature_dim = 4
x = torch.randn(batch_size, feature_dim)
y = torch.tensor([0, 1])

ARGS = {
    'x': x,
    'y': y,
    'alpha': 1.0,
    'use_cuda': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
crossEntropy Not yet run
unverified (harvested, no recorded run)
jiequancui/ResLT/CIFAR/cifarTrain_reslt_cifar10.py
code served (permissive licence) · get_code("dfb9a2fb0f62176c")
How it ran

no invocation recorded.

crossEntropy Not yet run
unverified (harvested, no recorded run)
jiequancui/ResLT/ImageNetLT/ImageNetTrain_reslt.py
code served (permissive licence) · get_code("1a5cea782c37726a")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
jiequancui/ResLT/ImageNetLT/ImageNetTrain_reslt.py
code served (permissive licence) · get_code("1402adb1ad919a47")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
jiequancui/ResLT/Inat/iNaturalTrain_reslt.py
code served (permissive licence) · get_code("b9c94d8815e978c1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 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.

FunctionAlso present inEarliest-datedOthers named
accuracy 2 other papers
2 later
2209.00183 (2022-09)
ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classification
2402.18133 (2024-02)
Classes Are Not Equal: An Empirical Study on Image Recognition Fairness

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

Deep learning algorithms face great challenges with long-tailed data distribution which, however, is quite a common case in real-world scenarios. Previous methods tackle the problem from either the aspect of input space (re-sampling classes with different frequencies) or loss space (re-weighting classes with different weights), suffering from heavy over-fitting to tail classes or hard optimization during training. To alleviate these issues, we propose a more fundamental perspective for long-tailed recognition, i.e., from the aspect of parameter space, and aims to preserve specific capacity for classes with low frequencies. From this perspective, the trivial solution utilizes different branches for the head, medium, and tail classes respectively, and then sums their outputs as the final results is not feasible. Instead, we design the effective residual fusion mechanism -- with one main branch optimized to recognize images from all classes, another two residual branches are gradually fused and optimized to enhance images from medium+tail classes and tail classes respectively. Then the branches are aggregated into final results by additive shortcuts. We test our method on several benchmarks, i.e., long-tailed version of CIFAR-10, CIFAR-100, Places, ImageNet, and iNaturalist 2018. Experimental results manifest the effectiveness of our method. Our code is available at https://github.com/jiequancui/ResLT.

For agents

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

get_harvested_code_for_paper("2101.10633")
get_code_for_paper("2101.10633")
have("2101.10633")

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

curl https://syntology.ai/api/ran/2101.10633.json

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

[![Syntology run record](https://syntology.ai/api/ran/2101.10633.svg)](https://syntology.ai/paper/2101.10633)

Connect an agent — have() is free.