SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.03231 · 2019

Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates

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 (0 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 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/1910.03231.json · badge: /api/ran/1910.03231.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
weijiaheng/Multi-class-Peer-Loss-functions reimplementation (classifier label)
classifier basis: classifier_2025
4 ran · 2 no recorded run
FunctionStatusWhere it lives
f_alpha Ran
ran, honoured the contract we drafted
weijiaheng/Multi-class-Peer-Loss-functions/MNIST/runner.py
code served (permissive licence) · get_code("4e50a2821ea4d47b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float64, 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 numpy as np

# The function f_alpha takes an epoch parameter (an integer index)
# It creates two arrays and concatenates them, then returns the value at the given epoch index
# epoch should be an integer in the range [0, 299] based on the concatenated array length

epoch = 150

ARGS = {
    'epoch': epoch
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
test Ran
ran, honoured the contract we drafted
weijiaheng/Multi-class-Peer-Loss-functions/CIFAR-10/runner.py
code served (permissive licence) · get_code("400ca42b786ad4aa")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. 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, 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)

# Define a minimal model that satisfies the function's usage
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)  # input dim 4, output dim 3 (for classification)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = SimpleModel()

# Create test_loader as a list of batches
# Each batch is a tuple of (idx, input, target)
# The function expects:
# - idx: some identifier (not used in function body)
# - input: array-like that can be converted to torch.Tensor
# - target: array-like with .float() method and .size(0) attribute
test_loader = [
    (0, [[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], torch.tensor([0.0, 1.0])),
    (1, [[2.0, 3.0, 4.0, 5.0], [6.0, 7.0, 8.0, 9.0]], torch.tensor([2.0, 0.0])),
]

ARGS = {
    'model': model,
    'test_loader': test_loader,
}
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 float, 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
test Ran
ran, honoured the contract we drafted
weijiaheng/Multi-class-Peer-Loss-functions/CIFAR-100/runner.py
code served (permissive licence) · get_code("c2d3e976a74b0705")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. 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, 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)

class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.fc = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.fc(x)
    
    def eval(self):
        self.training = False
        return self

model = SimpleModel()

# Create a test_loader as a list of (idx, input, target) tuples
# Each batch has 2 samples, input dimension is 4, output classes are 3
test_loader = [
    (torch.tensor([0, 1]), torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.tensor([2, 3]), torch.randn(2, 4), torch.tensor([2, 0])),
    (torch.tensor([4, 5]), torch.randn(2, 4), torch.tensor([1, 2])),
]

ARGS = {
    'model': model,
    'test_loader': test_loader
}
Setup block drafted by
a language model, Claude Sonnet 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 float, 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
test Ran
ran, honoured the contract we drafted
weijiaheng/Multi-class-Peer-Loss-functions/MNIST/runner.py
code served (permissive licence) · get_code("ad3fb425de0113bf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. 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, 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.utils.data

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.fc = nn.Linear(5, 3)
    
    def forward(self, x):
        return self.fc(x)
    
    def eval(self):
        self.training = False
        return self

model = SimpleModel()

class SimpleDataset(torch.utils.data.Dataset):
    def __init__(self):
        self.data = [
            (0, torch.randn(5), torch.tensor(0)),
            (1, torch.randn(5), torch.tensor(1)),
            (2, torch.randn(5), torch.tensor(2)),
            (3, torch.randn(5), torch.tensor(0)),
        ]
    
    def __len__(self):
        return len(self.data)
    
    def __getitem__(self, idx):
        return self.data[idx]

dataset = SimpleDataset()
test_loader = torch.utils.data.DataLoader(dataset, batch_size=2, shuffle=False)

ARGS = {
    'model': model,
    'test_loader': test_loader
}
Setup block drafted by
a language model, Claude Sonnet 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 float, 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
f_alpha Not yet run
unverified (harvested, no recorded run)
weijiaheng/Multi-class-Peer-Loss-functions/CIFAR-10/runner.py
code served (permissive licence) · get_code("5c4c1cf669bba6f1")
How it ran

no invocation recorded.

f_alpha Not yet run
unverified (harvested, no recorded run)
weijiaheng/Multi-class-Peer-Loss-functions/CIFAR-100/runner.py
code served (permissive licence) · get_code("40f44575d8b0abb0")
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 5 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 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.

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

Learning with noisy labels is a common challenge in supervised learning. Existing approaches often require practitioners to specify noise rates, i.e., a set of parameters controlling the severity of label noises in the problem, and the specifications are either assumed to be given or estimated using additional steps. In this work, we introduce a new family of loss functions that we name as peer loss functions, which enables learning from noisy labels and does not require a priori specification of the noise rates. Peer loss functions work within the standard empirical risk minimization (ERM) framework. We show that, under mild conditions, performing ERM with peer loss functions on the noisy dataset leads to the optimal or a near-optimal classifier as if performing ERM over the clean training data, which we do not have access to. We pair our results with an extensive set of experiments. Peer loss provides a way to simplify model development when facing potentially noisy training labels, and can be promoted as a robust candidate loss function in such situations.

For agents

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

get_harvested_code_for_paper("1910.03231")
get_code_for_paper("1910.03231")
have("1910.03231")

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

curl https://syntology.ai/api/ran/1910.03231.json

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

[![Syntology run record](https://syntology.ai/api/ran/1910.03231.svg)](https://syntology.ai/paper/1910.03231)

Connect an agent — have() is free.