SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.04129 · ICLR · 2024

OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning

Hsiang Hsu, Richard Chen, Wei-Cheng Huang

arXiv · PDF · Open in the Atlas

Code that ran

19 of 27 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 14 failures of our instrument; 8 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/2402.04129.json · badge: /api/ran/2402.04129.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
pprp/timm canonical (classifier label)
classifier basis: census
13 ran · 4 no recorded run
jpmorganchase/ovor community
Papers with Code archive
3 ran · 4 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
GT-RIPL/CODA-Prompt community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
CodaPrompt Ran
ran on a synthesized input · constructed an object; no result was computed
GT-RIPL/CODA-Prompt/models/zoo.py
code served (permissive licence) · get_code("e1716fdcd4486b32")
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, CodaPrompt: the run constructed the object and did not call it, so no result was computed. 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 as nn

torch.manual_seed(0)

ARGS = {
    "emb_d": 64,
    "n_tasks": 2,
    "prompt_param": [10, 8, 0.01],
    "key_dim": 32,
}
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 CodaPrompt — 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 CodaPrompt 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
CosineSchedule Ran
ran on a synthesized input · constructed an object; no result was computed
jpmorganchase/ovor/learners/prompt.py
code served (permissive licence) · get_code("fb5af0c577ee3e37")
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, CosineSchedule: 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
from torch.optim import SGD

torch.manual_seed(0)

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

# Create an optimizer with the model's parameters
optimizer = SGD(model.parameters(), lr=0.1)

# Define K parameter for CosineSchedule
K = 100

# Construct ARGS dictionary
ARGS = {
    'optimizer': optimizer,
    'K': K
}
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 CosineSchedule — 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 CosineSchedule 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
NPOS Ran
ran on a synthesized input · constructed an object; no result was computed
jpmorganchase/ovor/learners/prompt.py
code served (permissive licence) · get_code("cd90daeda39e4548")
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, NPOS: the run constructed the object and did not call it, so no result was computed. 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 math
import numpy as np
from torch.nn import functional as F
from torch.distributions import MultivariateNormal
from torch.utils.data import DataLoader, TensorDataset

torch.manual_seed(0)

# Create a minimal config dictionary
config = {
    'K': 5,
    'sample_from': 10,
    'select': 3,
    'cov': 1.0,
    'num_per_class': 2,
    'id_bsz': 2,
    'thres_id': -15.0,
    'thres_ood': -3.0,
    'lmda': 0.1,
    'huber': False,  # Use MSELoss instead of HuberLoss to avoid CUDA
}

ARGS = {
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
faiss, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type NPOS — 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 NPOS 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
accuracy Ran
ran; our contract draft was wrong, not the code
jpmorganchase/ovor/learners/prompt.py
code served (permissive licence) · get_code("14e1f6edf047e2fe")
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 float, ndim 0, 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 torch

torch.manual_seed(0)

# The function expects:
# - output: a tensor that supports topk operation (model predictions/logits)
# - target: a tensor of ground truth labels that supports size(0) and view operations

# Create small tensors
batch_size = 2
num_classes = 4

# output: logits tensor of shape (batch_size, num_classes)
# The function calls output.topk(1, 1, True, True), so it needs at least 2D with num_classes > 1
output = torch.randn(batch_size, num_classes)

# target: ground truth class indices of shape (batch_size,)
# Values should be in range [0, num_classes)
target = torch.tensor([0, 2])

ARGS = {
    "output": output,
    "target": target,
}
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 float, ndim 0, dtype family float — no output shape is stated: observe_signature.py could not observe it (no_result)
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
adaptive_avgmax_pool2d Ran
ran; our contract draft was wrong, not the code
pprp/timm/timm/layers/adaptive_avgmax_pool.py
code served (permissive licence) · get_code("bbb0ade8018ebd05")
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 4, dtype family float, shape (2, 4, 1, 1) 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.functional as F

torch.manual_seed(0)

# Create a small 4D tensor (batch_size=2, channels=4, height=3, width=5)
x = torch.randn(2, 4, 3, 5)

# Define output_size parameter
output_size = 1

# Construct ARGS dict with all parameters
ARGS = {
    'x': x,
    'output_size': output_size
}
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 4, dtype family float, shape (2, 4, 1, 1) — shape (2, 4, 1, 1) 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
adaptive_catavgmax_pool2d Ran
ran; our contract draft was wrong, not the code
pprp/timm/timm/layers/adaptive_avgmax_pool.py
code served (permissive licence) · get_code("c98e5e298f086636")
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 4, dtype family float, shape (2, 8, 1, 1) 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 input tensor
# Shape: (batch=2, channels=4, height=3, width=5)
x = torch.randn(2, 4, 3, 5)

# Define output_size parameter
output_size = 1

ARGS = {
    "x": x,
    "output_size": output_size,
}
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 4, dtype family float, shape (2, 8, 1, 1) — shape (2, 8, 1, 1) 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
adaptive_pool_feat_mult Ran
ran, honoured the contract we drafted
pprp/timm/timm/layers/adaptive_avgmax_pool.py
code served (permissive licence) · get_code("01c6892d9a801397")
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 int, ndim 0, dtype family int, 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)

ARGS = {
    'pool_type': 'avg'
}
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 int, ndim 0, dtype family int, 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_condconv_initializer Ran
ran; our contract draft was wrong, not the code
pprp/timm/timm/layers/cond_conv2d.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from facebookresearch/depthshrinker, is pointer only (licence: NOASSERTION) · get_code("816ebe82b6b6275f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from facebookresearch/depthshrinker, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

hard_sigmoid_jit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pprp/timm/timm/layers/activations_jit.py
code served (permissive licence) · get_code("91c27523dde7eb4a")
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; 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 torch

torch.manual_seed(0)

# The function hard_sigmoid_jit takes:
# - x: a tensor (used with clamp, div operations)
# - inplace: a bool (default False)

# Create a small tensor for x
x = torch.randn(2, 4)

# Set inplace parameter
inplace = False

ARGS = {
    "x": x,
    "inplace": inplace,
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
mish Ran
ran; our contract draft was wrong, not the code
pprp/timm/timm/layers/activations.py
code served (permissive licence) · get_code("801c85b8903bfff5")
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.functional as F

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

# Define ARGS dict with all parameters
ARGS = {
    'x': x,
    'inplace': False
}
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
mish_jit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pprp/timm/timm/layers/activations_jit.py
code served (permissive licence) · get_code("14eddd8cc4c65fe0")
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; 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 torch
from torch.nn import functional as F

torch.manual_seed(0)

# Create a small input tensor
x = torch.randn(2, 4)

# Create the ARGS dictionary with all parameters
ARGS = {
    "x": x,
    "_inplace": False,
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
ortho_penalty 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 gt-ripl/coda-prompt
pointer only · get_code("a763dc6f8d5d1498")
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.

sigmoid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pprp/timm/timm/layers/activations.py
code served (permissive licence) · get_code("d83b6ecf3cdc1d6a")
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)

# Create a small tensor for the sigmoid function to operate on
x = torch.randn(2, 4)

# Define ARGS mapping all parameters to values
ARGS = {
    "x": x,
    "inplace": False
}
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
swish Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pprp/timm/timm/layers/activations.py
code served (permissive licence) · get_code("717e4d22b6d103e6")
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

torch.manual_seed(0)

# Create a small tensor for the swish function
x = torch.randn(2, 4)

ARGS = {
    "x": x,
    "inplace": False,
}
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
swish_jit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pprp/timm/timm/layers/activations_jit.py
code served (permissive licence) · get_code("8e341f8585b3fe94")
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; 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 torch

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

# Define ARGS with all parameters for swish_jit
ARGS = {
    'x': x,
    'inplace': False,
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
swish_jit_bwd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pprp/timm/timm/layers/activations_me.py
code served (permissive licence) · get_code("ccf59d4aa2ccacdb")
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; 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 torch

torch.manual_seed(0)

# Create small test tensors
x = torch.randn(2, 4, requires_grad=True)
grad_output = torch.randn(2, 4)

ARGS = {
    "x": x,
    "grad_output": grad_output,
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
swish_jit_fwd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pprp/timm/timm/layers/activations_me.py
code served (permissive licence) · get_code("2d53e47b891cd927")
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; 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 torch

torch.manual_seed(0)

# The function swish_jit_fwd takes a single tensor x and applies swish activation
# (element-wise multiplication with sigmoid)
# We need to provide a small tensor as input

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
swish_me Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pprp/timm/timm/layers/activations_me.py
code served (permissive licence) · get_code("51a2f9920a170144")
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; 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 torch

torch.manual_seed(0)

# Create a small tensor for input
# The function applies SwishJitAutoFn which expects a tensor
x = torch.randn(2, 4, requires_grad=True)

# inplace parameter is defined but not actually used in the function body
inplace = False

ARGS = {
    'x': x,
    'inplace': inplace,
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
tensor_prompt Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from gt-ripl/coda-prompt
pointer only · get_code("3f33843b601c8d4d")
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.

NormalNN Not yet run
unverified (harvested, no recorded run)
jpmorganchase/ovor/learners/prompt.py
code served (permissive licence) · get_code("3e51324f77696213")
How it ran

no invocation recorded.

OnePrompt Not yet run
unverified (harvested, no recorded run)
jpmorganchase/ovor/learners/prompt.py
code served (permissive licence) · get_code("10a3cf3944acb574")
How it ran

no invocation recorded.

Prompt Not yet run
unverified (harvested, no recorded run)
jpmorganchase/ovor/learners/prompt.py
code served (permissive licence) · get_code("94d1744c930d27d6")
How it ran

no invocation recorded.

_LRScheduler Not yet run
unverified (harvested, no recorded run)
jpmorganchase/ovor/learners/prompt.py
code served (permissive licence) · get_code("0da189d1706732b7")
How it ran

no invocation recorded.

conv2d_same Not yet run
unverified (harvested, no recorded run)
pprp/timm/timm/layers/conv2d_same.py
code served (permissive licence) · get_code("8cf70ff8a63b107f")
How it ran

no invocation recorded.

create_classifier Not yet run
unverified (harvested, no recorded run)
pprp/timm/timm/layers/classifier.py
code served (permissive licence) · get_code("f3958c754a8750d7")
How it ran

no invocation recorded.

create_conv2d_pad Not yet run
unverified (harvested, no recorded run)
pprp/timm/timm/layers/conv2d_same.py
code served (permissive licence) · get_code("c7ec3481c1905e5b")
How it ran

no invocation recorded.

rel_logits_1d Not yet run
unverified (harvested, no recorded run)
pprp/timm/timm/layers/bottleneck_attn.py
code served (permissive licence) · get_code("f0b44651e598ca66")
How it ran

no invocation recorded.

Also present in other papers' code

Of 27 samples lifted from this paper's linked repositories, 27 carry a function identity and 0 do not. Of the 27 distinct functions with an identity, 20 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 12 the same month, 19 later) and 7 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
swish 10 other papers
5 dated earlier, 2 the same month, 3 later
2207.14676 (2022-07)
Global-Local Self-Distillation for Visual Representation Learning
Lee_BAAM_Monocular_3D_Pose_and_Shape_Reconstruction_With_Bi-Contextual_Attention_CVPR_2023_paper (2023 (year only))
BAAM: Monocular 3D pose and shape reconstruction with bi-contextual attention module and attention-guided modeling
2308.13177 (2023-08)
How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection
and 7 more not named here
mish 7 other papers
2 dated earlier, 2 the same month, 3 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04744 (2024-02)
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
and 4 more not named here
sigmoid 7 other papers
2 dated earlier, 2 the same month, 3 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04744 (2024-02)
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
and 4 more not named here
hard_sigmoid_jit 6 other papers
2 dated earlier, 2 the same month, 2 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04744 (2024-02)
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
and 3 more not named here
mish_jit 6 other papers
2 dated earlier, 2 the same month, 2 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04744 (2024-02)
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
and 3 more not named here
swish_jit 6 other papers
2 dated earlier, 2 the same month, 2 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04744 (2024-02)
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
and 3 more not named here
tensor_prompt 6 other papers
1 dated earlier, 5 later · 1 only as an assembly brick
2211.13218 (2022-11)
CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning
2403.08568 (2024-03)
Consistent Prompting for Rehearsal-Free Continual Learning
2410.20444 (2024-10)
Vector Quantization Prompting for Continual Learning
and 3 more not named here
swish_jit_bwd 4 other papers
1 dated earlier, 2 the same month, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2402.04744 (2024-02)
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
and 1 more not named here
swish_jit_fwd 4 other papers
1 dated earlier, 2 the same month, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2402.04744 (2024-02)
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
and 1 more not named here
swish_me 4 other papers
1 dated earlier, 2 the same month, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2402.04744 (2024-02)
Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
and 1 more not named here
conv2d_same 3 other papers
1 dated earlier, 1 the same month, 1 later
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
2408.13983 (2024-08)
Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation
get_condconv_initializer 3 other papers
2 dated earlier, 1 the same month · 1 only as an assembly brick
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
rel_logits_1d 3 other papers
1 dated earlier, 1 the same month, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
2404.01882 (2024-04)
Scene Adaptive Sparse Transformer for Event-based Object Detection
CosineSchedule
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2404.00228 (2024-04)
InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning
2410.20444 (2024-10)
Vector Quantization Prompting for Continual Learning
_LRScheduler
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2404.00228 (2024-04)
InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning
2410.20444 (2024-10)
Vector Quantization Prompting for Continual Learning
create_conv2d_pad 2 other papers
1 dated earlier, 1 later
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2408.13983 (2024-08)
Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation
ortho_penalty 2 other papers
1 dated earlier, 1 later
2211.13218 (2022-11)
CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning
2410.20444 (2024-10)
Vector Quantization Prompting for Continual Learning
adaptive_avgmax_pool2d 1 other paper
1 later
2404.01882 (2024-04)
Scene Adaptive Sparse Transformer for Event-based Object Detection
adaptive_catavgmax_pool2d 1 other paper
1 later
2404.01882 (2024-04)
Scene Adaptive Sparse Transformer for Event-based Object Detection
adaptive_pool_feat_mult 1 other paper
1 later
2404.01882 (2024-04)
Scene Adaptive Sparse Transformer for Event-based Object Detection

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

Recent works have shown that by using large pre-trained models along with learnable prompts, rehearsal-free methods for class-incremental learning (CIL) settings can achieve superior performance to prominent rehearsal-based ones. Rehearsalfree CIL methods struggle with distinguishing classes from different tasks, as those are not trained together. In this work we propose a regularization method based on virtual outliers to tighten decision boundaries of the classifier, such that confusion of classes among different tasks is mitigated. Recent prompt-based methods often require a pool of task-specific prompts, in order to prevent overwriting knowledge of previous tasks with that of the new task, leading to extra computation in querying and composing an appropriate prompt from the pool. This additional cost can be eliminated, without sacrificing accuracy, as we reveal in the paper. We illustrate that a simplified prompt-based method can achieve results comparable to previous state-of-the-art (SOTA) methods equipped with a prompt pool, using much less learnable parameters and lower inference cost. Our regularization method has demonstrated its compatibility with different prompt-based methods, boosting those previous SOTA rehearsal-free CIL methods' accuracy on the ImageNet-R and CIFAR-100 benchmarks. Our source code is available at https://github.com/jpmorganchase/ovor.

For agents

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

get_harvested_code_for_paper("2402.04129")
get_code_for_paper("2402.04129")
have("2402.04129")

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

curl https://syntology.ai/api/ran/2402.04129.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.04129.svg)](https://syntology.ai/paper/2402.04129)

Connect an agent — have() is free.