SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2309.01017 · CVPR · 2023

Contrastive Grouping with Transformer for Referring Image Segmentation

Ge Zheng, Jiajin Tang, Sibei Yang, Cheng Shi

arXiv · PDF · Open in the Atlas

Code that ran

22 of 23 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 1 has no contract verdict; 20 failures of our instrument; 1 no recorded run); 3 of them were also run on the host, not in the jail, by the peer-agreement lane that set their 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/2309.01017.json · badge: /api/ran/2309.01017.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
toneyaya/cgformer canonical (classifier label)
classifier basis: census
22 ran · 1 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/activations.py
code served (permissive licence) · get_code("0f786c407fb1ee4c")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 2026-09-04T22:33:52Z). 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)

# The function swish takes a single parameter 'x' which is used with:
# - torch.sigmoid(x) - requires a tensor
# - x * ... - requires a tensor that supports multiplication
# So x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
whitespace_tokenize Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/tokenization_bert.py
code served (permissive licence) · get_code("cf9ffa02a42184af")
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 list, ndim 1, dtype family float; no output shape is stated. 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 2026-09-05T02:55:57Z). 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

def whitespace_tokenize(text):
    """Runs basic whitespace cleaning and splitting on a piece of text."""
    text = text.strip()
    if not text:
        return []
    tokens = text.split()
    return tokens

# Setup code
torch.manual_seed(0)

# The function takes a single parameter: text (a string)
# It performs basic whitespace cleaning and splitting
# We need to provide a valid string argument

ARGS = {
    "text": "  hello world  this is a test  "
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
toneyaya/cgformer/model/backbone.py
code served (permissive licence) · get_code("144d10b49baeb8a6")
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 Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) 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 2026-09-04T22:38:58Z). 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 tensor with shape (B, H, W, C)
# B=2 (batch), H=8 (height), W=8 (width), C=4 (channels)
# Using distinct sizes: 2, 8, 8, 4
x = torch.randn(2, 8, 8, 4)

# window_size must divide both H and W evenly
# H=8, W=8, so window_size=4 works (8 // 4 = 2)
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) — shape (8, 4, 4, 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
calc_banned_bad_words_ids Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
toneyaya/cgformer/bert/generation_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from upper9527/gerea, is pointer only (licence: NONE) · get_code("e3ead4161d5e3d4a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from upper9527/gerea, and GitHub detected no licence in that repository when it was checked. 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.

calc_banned_ngram_tokens Ran
ran on a synthesized input
toneyaya/cgformer/bert/generation_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from shmsw25/AmbigQA, is pointer only (licence: NONE) · get_code("8d77347cfa15b834")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shmsw25/AmbigQA, and GitHub detected no licence in that repository when it was checked. 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.

conv_layer Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/model/layers.py
pointer only (licence: MIT); the stored copy get_code serves, from franciszzj/tp-sis, is pointer only (licence: NONE) · get_code("dbfe3357dc25ca5f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from franciszzj/tp-sis, and GitHub detected no licence in that repository when it was checked. 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.

dice_loss Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/model/segmenter.py
code served (permissive licence) · get_code("206e880de1f589bc")
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

torch.manual_seed(0)

# Create small test tensors for dice_loss
# inputs: predictions (logits before sigmoid), shape (batch_size, features)
# targets: binary labels, shape (batch_size, features)
batch_size = 2
feature_dim = 4

inputs = torch.randn(batch_size, feature_dim)
targets = torch.randint(0, 2, (batch_size, feature_dim)).float()

ARGS = {
    "inputs": inputs,
    "targets": targets,
}
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
find_pruneable_heads_and_indices Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/modeling_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from lsan2401/rmsin, is pointer only (licence: NONE) · get_code("b239247b87d4f3dc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lsan2401/rmsin, and GitHub detected no licence in that repository when it was checked. 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.

gelu_fast Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/activations.py
code served (permissive licence) · get_code("a4475703ff58ecf9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# gelu_fast takes a single parameter 'x' which is used in arithmetic operations
# It should be a tensor that supports multiplication, addition, and tanh operations
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gelu_new Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/activations.py
code served (permissive licence) · get_code("dc9ffc0f29e7fa3d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import math

torch.manual_seed(0)

# The function takes a single parameter 'x' which should be a tensor
# It performs mathematical operations on it: tanh, pow, multiplication, addition
# So we need a 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
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
hard_softmax Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/model/layers.py
code served (permissive licence) · get_code("cb0acca1ea9ead1e")
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 logits tensor (batch_size=2, num_classes=4)
logits = torch.randn(2, 4)

# The dim parameter specifies which dimension to apply softmax/argmax along
dim = 1

ARGS = {
    "logits": logits,
    "dim": dim,
}
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
hf_bucket_url Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/file_utils.py
code served (permissive licence) · get_code("070b5bdeecd71825")
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 str. 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.

# Setup code for hf_bucket_url function

ARGS = {
    "model_id": "bert-base-uncased",
    "filename": "pytorch_model.bin",
    "use_cdn": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
is_remote_url Ran
ran, violated the contract we drafted
toneyaya/cgformer/bert/file_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from vis-nlp/ChartQA, is pointer only (licence: GPL-3.0) · get_code("899d1e2736236351")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from vis-nlp/ChartQA, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

l2norm Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/model/layers.py
code served (permissive licence) · get_code("1f0f760eab66c082")
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 testing
# Shape: (batch_size=2, features=4)
X = torch.randn(2, 4)

ARGS = {
    "X": X,
    "dim": -1,
    "eps": 1e-12,
}
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
load_vocab Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/tokenization_bert.py
code served (permissive licence) · get_code("e7fbc7a74a3457c7")
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 OrderedDict. 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 collections
import tempfile
import os

# Create a temporary vocabulary file
temp_dir = tempfile.mkdtemp()
vocab_file = os.path.join(temp_dir, 'vocab.txt')

# Write some sample tokens to the vocab file
sample_tokens = ['[PAD]', '[UNK]', '[CLS]', '[SEP]', 'the', 'quick', 'brown', 'fox']
with open(vocab_file, 'w', encoding='utf-8') as f:
    for token in sample_tokens:
        f.write(token + '\n')

ARGS = {
    'vocab_file': vocab_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
mish Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from lsan2401/rmsin, is pointer only (licence: NONE) · get_code("22b41155e451683b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lsan2401/rmsin, and GitHub detected no licence in that repository when it was checked. 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.

prune_conv1d_layer Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/modeling_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from lsan2401/rmsin, is pointer only (licence: NONE) · get_code("b3ee64494a3b6d38")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lsan2401/rmsin, and GitHub detected no licence in that repository when it was checked. 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.

prune_linear_layer Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/modeling_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from lsan2401/rmsin, is pointer only (licence: NONE) · get_code("a37615738b3ddcd3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lsan2401/rmsin, and GitHub detected no licence in that repository when it was checked. 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_focal_loss Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/model/segmenter.py
code served (permissive licence) · get_code("e71d9c7dd14f39b8")
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.functional as F

torch.manual_seed(0)

# Create small tensors for inputs and targets
# inputs: predictions (logits) - shape (2, 4)
inputs = torch.randn(2, 4, dtype=torch.float32)

# targets: binary labels matching inputs shape - shape (2, 4)
targets = torch.randint(0, 2, (2, 4), dtype=torch.float32)

# alpha: weighting factor for positive/negative balance
alpha = 0.25

# gamma: exponent for modulating factor
gamma = 2.0

ARGS = {
    "inputs": inputs,
    "targets": targets,
    "alpha": alpha,
    "gamma": gamma,
}
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
top_k_top_p_filtering Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
toneyaya/cgformer/bert/generation_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from upper9527/gerea, is pointer only (licence: NONE) · get_code("0dc219ab6716a127")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from upper9527/gerea, and GitHub detected no licence in that repository when it was checked. 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.

url_to_filename Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/bert/file_utils.py
code served (permissive licence) · get_code("e827d94caab33f59")
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 str. 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.

from hashlib import sha256

ARGS = {
    "url": "https://example.com/model.weights",
    "etag": "abc123def456"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
window_reverse Ran
ran; our contract draft was wrong, not the code
toneyaya/cgformer/model/backbone.py
code served (permissive licence) · get_code("61bf152e6a42a184")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 12, 3) 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)

# Parameters for window_reverse
# windows: (num_windows*B, window_size, window_size, C)
# The function expects windows to be partitioned from an image of size (B, H, W, C)
# where the image is divided into non-overlapping windows of size window_size x window_size

B = 2  # batch size
H = 8  # image height
W = 12  # image width
window_size = 4  # window size
C = 3  # number of channels

# Calculate number of windows
num_windows_h = H // window_size  # 2
num_windows_w = W // window_size  # 3
num_windows = num_windows_h * num_windows_w  # 6

# windows shape: (num_windows*B, window_size, window_size, C)
# = (6*2, 4, 4, 3) = (12, 4, 4, 3)
windows = torch.randn(num_windows * B, window_size, window_size, C)

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "W": W,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 8, 12, 3) — shape (2, 8, 12, 3) 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
load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
toneyaya/cgformer/bert/modeling_bert.py
pointer only (licence: MIT); the stored copy get_code serves, from lsan2401/rmsin, is pointer only (licence: NONE) · get_code("fb9398de2966d6de")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lsan2401/rmsin, and GitHub detected no licence in that repository when it was checked. 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. No invocation recorded.

Also present in other papers' code

Of 23 samples lifted from this paper's linked repositories, 23 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 20 are also present in other papers whose code we hold (19 with at least one paper dated earlier, 6 the same month, 19 later) and 3 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
window_reverse 227 other papers
112 dated earlier, 3 the same month, 103 later, 9 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
window_partition 223 other papers
108 dated earlier, 4 the same month, 102 later, 9 same year, order not determinable · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 220 more not named here
swish 206 other papers
154 dated earlier, 4 the same month, 48 later · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
whitespace_tokenize 43 other papers
32 dated earlier, 11 later
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
and 40 more not named here
load_vocab 29 other papers
19 dated earlier, 10 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
and 26 more not named here
prune_linear_layer 29 other papers
25 dated earlier, 4 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.08230 (2019-06)
Evaluating Protein Transfer Learning with TAPE
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
and 26 more not named here
gelu_new 24 other papers
14 dated earlier, 1 the same month, 9 later
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2104.08066 (2021-04)
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
and 21 more not named here
gelu_fast 22 other papers
12 dated earlier, 1 the same month, 9 later
2010.03957 (2020-10)
Transformers for Modeling Physical Systems
2104.08066 (2021-04)
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
and 19 more not named here
mish 19 other papers
15 dated earlier, 4 later
2006.04884 (2020-06)
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
2007.12223 (2020-07)
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
2012.07463 (2020-12)
Parameter-Efficient Transfer Learning with Diff Pruning
and 16 more not named here
load_tf_weights_in_bert 16 other papers
13 dated earlier, 3 later
2006.04884 (2020-06)
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
2007.12223 (2020-07)
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
2012.07463 (2020-12)
Parameter-Efficient Transfer Learning with Diff Pruning
and 13 more not named here
prune_conv1d_layer 16 other papers
13 dated earlier, 3 later
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1909.05311 (2019-09)
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
and 13 more not named here
is_remote_url 14 other papers
10 dated earlier, 4 later
1905.00641 (2019-05)
RetinaFace: Single-stage Dense Face Localisation in the Wild
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
and 11 more not named here
url_to_filename 12 other papers
10 dated earlier, 2 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
2005.00796 (2020-05)
A Simple Language Model for Task-Oriented Dialogue
and 9 more not named here
conv_layer 9 other papers
4 dated earlier, 5 later
2111.15174 (2021-11)
CRIS: CLIP-Driven Referring Image Segmentation
2210.10276 (2022-10)
CLIP-Driven Fine-grained Text-Image Person Re-identification
2306.09244 (2023-06)
Text Promptable Surgical Instrument Segmentation with Vision-Language Models
and 6 more not named here
calc_banned_ngram_tokens 8 other papers
4 dated earlier, 4 later
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2106.01317 (2021-06)
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
2109.04096 (2021-09)
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
and 5 more not named here
top_k_top_p_filtering 5 other papers
2 dated earlier, 3 later
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2109.04096 (2021-09)
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
2402.02503 (2024-02)
GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering
and 2 more not named here
calc_banned_bad_words_ids 3 other papers
3 later
2312.06149 (2023-12)
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
2402.02503 (2024-02)
GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering
2601.09141 (2026-01)
Identity-Robust Language Model Generation via Content Integrity Preservation
find_pruneable_heads_and_indices 3 other papers
1 dated earlier, 2 later
2308.13853 (2023-08)
Beyond One-to-One: Rethinking the Referring Image Segmentation
2312.12198 (2023-12)
Mask Grounding for Referring Image Segmentation
2312.12470 (2023-12)
Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation
hard_softmax 3 other papers
1 dated earlier, 1 the same month, 1 later
2303.17056 (2023-03)
Audio-Visual Grouping Network for Sound Localization from Mixtures
2309.05281 (2023-09)
Class-Incremental Grouping Network for Continual Audio-Visual Learning
2310.19001 (2023-10)
Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
hf_bucket_url 2 other papers
2 dated earlier
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2109.08133 (2021-09)
Phrase Retrieval Learns Passage Retrieval, Too

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

Referring image segmentation aims to segment the target referent in an image conditioning on a natural language expression. Existing one-stage methods employ per-pixel classification frameworks, which attempt straightforwardly to align vision and language at the pixel level, thus failing to capture critical object-level information. In this paper, we propose a mask classification framework, Contrastive Grouping with Transformer network (CGFormer), which explicitly captures object-level information via token-based querying and grouping strategy. Specifically, CGFormer first introduces learnable query tokens to represent objects and then alternately queries linguistic features and groups visual features into the query tokens for object-aware crossmodal reasoning. In addition, CGFormer achieves crosslevel interaction by jointly updating the query tokens and decoding masks in every two consecutive layers. Finally, CGFormer cooperates contrastive learning to the grouping strategy to identify the token and its mask corresponding to the referent. Experimental results demonstrate that CG-Former outperforms state-of-the-art methods in both segmentation and generalization settings consistently and significantly. Code is available at https://github.com/ Toneyaya/CGFormer.

For agents

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

get_harvested_code_for_paper("2309.01017")
get_code_for_paper("2309.01017")
have("2309.01017")

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

curl https://syntology.ai/api/ran/2309.01017.json

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

[![Syntology run record](https://syntology.ai/api/ran/2309.01017.svg)](https://syntology.ai/paper/2309.01017)

Connect an agent — have() is free.