SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.01376 · NeurIPS · 2023

Towards Distribution-Agnostic Generalized Category Discovery

Joey Zhou, Yang Feng, Jian Wu, Zuozhu Liu, Jianhong Bai, Hualiang Wang, Ruizhe Chen, Lianrui Mu, Xiaomeng Li, Haoji Hu

arXiv · PDF · Open in the Atlas

Code that ran

10 of 17 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 6 failures of our instrument; 7 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2310.01376.json · badge: /api/ran/2310.01376.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
jianhongbai/bacon canonical (classifier label)
classifier basis: classifier_2025
9 ran · 7 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_mean_lr Ran
ran, honoured the contract we drafted
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("c62a45794431e9b7")
How it ran

Ran in Syntology's jail 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 comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T02:48:59Z). 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
from torch import optim
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer with the model's parameters
optimizer = optim.SGD(model.parameters(), lr=0.01)

# Add another param group with a different learning rate
optimizer.add_param_group({'params': [torch.nn.Parameter(torch.randn(2, 2))], 'lr': 0.02})

ARGS = {
    'optimizer': optimizer
}
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
DistillLoss Ran
ran on a synthesized input · constructed an object; no result was computed
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("37030cbebb0d0129")
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, DistillLoss: 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 numpy as np

torch.manual_seed(0)

# Build the DistillLoss class (provided in the function)
class DistillLoss(nn.Module):

    def __init__(self, warmup_teacher_temp_epochs, nepochs, ncrops=2, warmup_teacher_temp=0.07, teacher_temp=0.04, student_temp=0.1, args=None):
        super().__init__()
        self.args = args
        self.student_temp = student_temp
        self.ncrops = ncrops
        self.teacher_temp_schedule = np.concatenate((np.linspace(warmup_teacher_temp, teacher_temp, warmup_teacher_temp_epochs), np.ones(nepochs - warmup_teacher_temp_epochs) * teacher_temp))

    def forward(self, student_output, teacher_output, epoch):
        """
        Cross-entropy between softmax outputs of the teacher and student networks.
        """
        student_out = student_output / self.student_temp
        student_out = student_out.chunk(self.ncrops)
        temp = self.teacher_temp_schedule[epoch]
        teacher_out = torch.nn.functional.softmax(teacher_output / temp, dim=-1)
        teacher_out = teacher_out.detach().chunk(2)
        total_loss = 0
        n_loss_terms = 0
        for iq, q in enumerate(teacher_out):
            for v in range(len(student_out)):
                if v == iq:
                    continue
                loss = torch.sum(-q * torch.nn.functional.log_softmax(student_out[v], dim=-1), dim=-1)
                total_loss += loss.mean()
                n_loss_terms += 1
        total_loss /= n_loss_terms
        return total_loss

# Create a minimal args object
class ArgsStandIn:
    pass

args = ArgsStandIn()

# Set up parameters
warmup_teacher_temp_epochs = 2
nepochs = 5
ncrops = 2
warmup_teacher_temp = 0.07
teacher_temp = 0.04
student_temp = 0.1

# Create sample tensors
# student_output: batch size 2, ncrops*something features -> needs to be chunked into ncrops parts
# Each chunk should have shape (batch, dim)
batch_size = 2
feature_dim = 4
student_output = torch.randn(batch_size, ncrops * feature_dim)

# teacher_output: batch size 2, features (will be chunked into 2)
teacher_output = torch.randn(batch_size, 2 * feature_dim)

epoch = 0

ARGS = {
    'warmup_teacher_temp_epochs': warmup_teacher_temp_epochs,
    'nepochs': nepochs,
    'ncrops': ncrops,
    'warmup_teacher_temp': warmup_teacher_temp,
    'teacher_temp': teacher_temp,
    'student_temp': student_temp,
    'args': args,
}
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 DistillLoss — 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 DistillLoss 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
SemiConLoss Ran
ran on a synthesized input
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("95c5de44324291cf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 0, dtype family float; no output shape is stated. 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 and ndim 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

class SemiConLoss(nn.Module):

    def __init__(self, temperature=0.07, contrast_mode='all', base_temperature=0.07, args=None):
        super(SemiConLoss, self).__init__()
        self.temperature = temperature
        self.contrast_mode = contrast_mode
        self.base_temperature = base_temperature
        self.args = args

    def forward(self, features, soft_mask=None, ambiguous_mask=None):
        device = torch.device('cuda') if features.is_cuda else torch.device('cpu')
        if len(features.shape) < 3:
            raise ValueError('`features` needs to be [bsz, n_views, ...],at least 3 dimensions are required')
        if len(features.shape) > 3:
            features = features.view(features.shape[0], features.shape[1], -1)
        batch_size = features.shape[0]
        contrast_count = features.shape[1]
        contrast_feature = torch.cat(torch.unbind(features, dim=1), dim=0)
        if self.contrast_mode == 'one':
            anchor_feature = features[:, 0]
            anchor_count = 1
        elif self.contrast_mode == 'all':
            anchor_feature = contrast_feature
            anchor_count = contrast_count
        else:
            raise ValueError('Unknown mode: {}'.format(self.contrast_mode))
        anchor_dot_contrast = torch.div(torch.matmul(anchor_feature, contrast_feature.T), self.temperature)
        logits_max, _ = torch.max(anchor_dot_contrast, dim=1, keepdim=True)
        logits = anchor_dot_contrast - logits_max.detach()
        if not len(logits) == len(soft_mask):
            soft_mask = soft_mask.repeat(anchor_count, contrast_count)
        logits_mask = torch.scatter(torch.ones_like(soft_mask), 1, torch.arange(batch_size * anchor_count).view(-1, 1).to(device), 0)
        soft_mask = soft_mask * logits_mask
        exp_logits = torch.exp(logits) * logits_mask
        log_prob = logits - torch.log(exp_logits.sum(1, keepdim=True))
        mean_log_prob_pos = (soft_mask * log_prob).sum(1) / soft_mask.sum(1)
        loss = -(self.temperature / self.base_temperature) * mean_log_prob_pos
        loss = loss.view(anchor_count, batch_size).mean()
        return loss


INIT_ARGS = {
    'temperature': 0.07,
    'contrast_mode': 'all',
    'base_temperature': 0.07,
    'args': None
}

ARGS = {
    'features': torch.randn(2, 3, 4),
    'soft_mask': torch.ones(6, 6),
    'ambiguous_mask': None
}

if __name__ == '__main__':
    model = SemiConLoss(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Loss output: {output}")
    print(f"Output shape: {output.shape}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
SupConLoss Ran
ran on a synthesized input
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("12b38c6451969326")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 0, dtype family float; no output shape is stated. 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 and ndim 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

INIT_ARGS = {
    'temperature': 0.1,
    'contrast_mode': 'all',
    'base_temperature': 0.1
}

# Create synthetic features and labels for testing
batch_size = 2
n_views = 3
feature_dim = 4

# Features shape: [batch_size, n_views, feature_dim]
features = torch.randn(batch_size, n_views, feature_dim)

# Labels shape: [batch_size]
labels = torch.tensor([0, 1], dtype=torch.long)

ARGS = {
    'features': features,
    'labels': labels
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, 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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
compute_est_adjustment Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("cc083b6352f41e6b")
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 1, dtype family float; no output shape is stated. 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 and ndim 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
import torch

torch.manual_seed(0)

class MockArgs:
    def __init__(self):
        # est_dist needs to be a tensor that can be moved to CPU and summed
        # Create a small distribution tensor
        self.est_dist = torch.tensor([0.5, 0.3, 0.15, 0.05], dtype=torch.float32)

ARGS = {
    'tro': 1.0,
    'args': MockArgs()
}
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 Tensor, ndim 1, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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
compute_reg_loss Ran
ran; our contract draft was wrong, not the code
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("5346c05380052e53")
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 math

torch.manual_seed(0)

# Analyze function usage:
# - student_out: used with / 0.1, .softmax(dim=1), .mean(dim=0) -> 2D tensor (batch, classes)
# - est_count: used with ** args.p -> scalar or 0D tensor
# - args: used with args.p -> object with attribute 'p'

# Create student_out as a 2D tensor (batch_size=2, num_classes=4)
student_out = torch.randn(2, 4)

# Create est_count as a scalar tensor
est_count = torch.tensor(5.0)

# Create args with attribute p
class Args:
    def __init__(self):
        self.p = 0.5

args = Args()

ARGS = {
    "student_out": student_out,
    "est_count": est_count,
    "args": args
}
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
get_params_groups Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from cvmi-lab/simgcd
pointer only · get_code("ec22c16f1e0653f7")
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.

info_nce_logits Ran
ran; our contract draft was wrong, not the code
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("dc61c49b216cea13")
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 torch.nn.functional as F

torch.manual_seed(0)

# The function takes features (a tensor) and optional parameters
# features should be a 2D tensor where:
# - size(0) is the batch dimension (must be even for n_views=2)
# - size(1) is the feature dimension

# Create a small batch of features: batch_size=4 (2 views × 2 samples), feature_dim=8
batch_size = 4
feature_dim = 8
features = torch.randn(batch_size, feature_dim)

ARGS = {
    'features': features,
    'n_views': 2,
    'temperature': 1.0,
    'device': 'cpu'
}
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 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
split_cluster_acc_v2 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("e2b8c1d1e98d7709")
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. 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 numpy as np
import torch

torch.manual_seed(0)

# Create a small stand-in class for args
class ArgsStandIn:
    def __init__(self):
        # k_cls_idx needs a .max() method that returns something with .item()
        self.k_cls_idx = torch.tensor([0, 1, 2, 3])
        
        # These will be used in calculate_acc
        # They need to be torch tensors with .numpy().tolist() capability
        self.known_many_cls = torch.tensor([0, 1])
        self.known_median_cls = torch.tensor([2])
        self.known_few_cls = torch.tensor([3])
        
        # These can be None or tensors
        self.unknown_many_cls = torch.tensor([4, 5])
        self.unknown_median_cls = torch.tensor([6])
        self.unknown_few_cls = torch.tensor([7])

args = ArgsStandIn()

# Create minimal train_loader (not actually used in the function body, but required as parameter)
train_loader = []

# Create y_true: ground truth labels (numpy array)
y_true = np.array([0, 1, 2, 3, 0, 1, 4, 5, 6, 7, 4, 5])

# Create y_pred: predicted labels (numpy array)
y_pred = np.array([0, 1, 2, 3, 0, 1, 4, 5, 6, 7, 4, 5])

# Create mask: True for old classes, False for new classes
# First 6 samples are old (indices 0-5), last 6 are new (indices 6-11)
mask = np.array([True, True, True, True, True, True, False, False, False, False, False, False])

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
    "mask": mask,
    "train_loader": train_loader,
    "args": args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, 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
split_cluster_acc_v2_balanced Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("50edbf115e750bdd")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# Set random seed for reproducibility
np.random.seed(0)

# Create small synthetic data for clustering evaluation
n_samples = 10
n_classes = 4

# y_true: ground truth labels
y_true = np.array([0, 0, 1, 1, 2, 2, 3, 3, 0, 1], dtype=np.int64)

# y_pred: predicted cluster labels
y_pred = np.array([0, 0, 1, 1, 2, 2, 3, 3, 0, 1], dtype=np.int64)

# mask: True for old classes (indices 0-5), False for new classes (indices 6-9)
# This distinguishes between instances from old classes vs new classes
mask = np.array([True, True, True, True, True, True, False, False, True, True], dtype=bool)

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
    "mask": mask,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
calculate_acc Not yet run
unverified (harvested, no recorded run)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("4e2fa0271f1222c9")
How it ran

no invocation recorded.

compute_softconloss Not yet run
unverified (harvested, no recorded run)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("71b073ad89637020")
How it ran

no invocation recorded.

dist_est Not yet run
unverified (harvested, no recorded run)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("6888e6e64755786e")
How it ran

no invocation recorded.

log_accs_from_preds Not yet run
unverified (harvested, no recorded run)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("7d0eb85e7e70c3b3")
How it ran

no invocation recorded.

set_args_mmf Not yet run
unverified (harvested, no recorded run)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("031f432787f1623b")
How it ran

no invocation recorded.

test Not yet run
unverified (harvested, no recorded run)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("fa3d31a3392a1b08")
How it ran

no invocation recorded.

train_dual Not yet run
unverified (harvested, no recorded run)
jianhongbai/bacon/model/bacon.py
code served (permissive licence) · get_code("b150a7dd8f9c24c0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 5 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 5 later) and 12 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
get_params_groups
brick of this paper's assembly: helper
10 other papers
3 dated earlier, 7 later · 1 only as an assembly brick
2104.14294 (2021-04)
Emerging Properties in Self-Supervised Vision Transformers
2211.11727 (2022-11)
Parametric Classification for Generalized Category Discovery: A Baseline Study
2308.12112 (2023-08)
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
and 7 more not named here
info_nce_logits
brick of this paper's assembly: helper
7 other papers
1 dated earlier, 6 later · 1 only as an assembly brick
2211.11727 (2022-11)
Parametric Classification for Generalized Category Discovery: A Baseline Study
2403.04272 (2024-03)
Active Generalized Category Discovery
2403.09974 (2024-03)
GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
and 4 more not named here
get_mean_lr 2 other papers
1 dated earlier, 1 later
2110.06207 (2021-10)
Open-Set Recognition: A Good Closed-Set Classifier is All You Need
2512.16202 (2025-12)
Open Ad-hoc Categorization with Contextualized Feature Learning
SupConLoss
brick of this paper's assembly: loss
1 other paper
1 later
2403.04272 (2024-03)
Active Generalized Category Discovery
split_cluster_acc_v2_balanced
brick of this paper's assembly: helper
1 other paper
1 later
2504.03755 (2025-04)
ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery

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

Data imbalance and open-ended distribution are two intrinsic characteristics of the real visual world. Though encouraging progress has been made in tackling each challenge separately, few works dedicated to combining them towards real-world scenarios. While several previous works have focused on classifying close-set samples and detecting open-set samples during testing, it's still essential to be able to classify unknown subjects as human beings. In this paper, we formally define a more realistic task as distribution-agnostic generalized category discovery (DA-GCD): generating fine-grained predictions for both close-and open-set classes in a long-tailed open-world setting. To tackle the challenging problem, we propose a Self-Balanced Co-Advice contrastive framework (BaCon), which consists of a contrastive-learning branch and a pseudo-labeling branch, working collaboratively to provide interactive supervision to resolve the DA-GCD task. In particular, the contrastive-learning branch provides reliable distribution estimation to regularize the predictions of the pseudo-labeling branch, which in turn guides contrastive learning through self-balanced knowledge transfer and a proposed novel contrastive loss. We compare BaCon with state-of-the-art methods from two closely related fields: imbalanced semi-supervised learning and generalized category discovery.

For agents

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

get_harvested_code_for_paper("2310.01376")
get_code_for_paper("2310.01376")
have("2310.01376")

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

curl https://syntology.ai/api/ran/2310.01376.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.01376.svg)](https://syntology.ai/paper/2310.01376)

Connect an agent — have() is free.