SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.11384 · NeurIPS · 2024

Understanding Multi-Granularity for Open-Vocabulary Part Segmentation

Jiho Choi, Seonho Lee, Seungho Lee, Minhyun Lee, Hyunjung Shim

arXiv · PDF · Open in the Atlas

Code that ran

13 of 15 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, 0 violated it and 0 have no contract verdict; 13 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2406.11384.json · badge: /api/ran/2406.11384.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
kaist-cvml-lab/part-clipseg canonical (classifier label)
classifier basis: census
13 ran · 2 no recorded run
FunctionStatusWhere it lives
clipseg_loss Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/models/clipseg/modeling_clipseg.py
code served (permissive licence) · get_code("41b007e677e02ece")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function clipseg_loss takes a similarity tensor
# It calls contrastive_loss on it and on its transpose
# contrastive_loss expects a 2D tensor (logits) where it can compute cross_entropy
# with targets of torch.arange(len(logits))
# So similarity should be a 2D tensor of shape (batch_size, batch_size)
# representing similarity scores between captions and images

similarity = torch.randn(2, 2)

ARGS = {
    "similarity": similarity
}
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
contrastive_loss Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/models/clipseg/modeling_clipseg.py
pointer only (licence: MIT); the stored copy get_code serves, from microsoft/xpretrain, is pointer only (licence: NOASSERTION) · get_code("4675779aec92d6c0")
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 microsoft/xpretrain, 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.

convert_pytorch_state_dict_to_flax Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/modeling_flax_pytorch_utils.py
code served (permissive licence) · get_code("5168a172bbb363a5")
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 dict. 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 jax.numpy as jnp
import numpy as np
from flax.traverse_util import flatten_dict, unflatten_dict

torch.manual_seed(0)

# Create a minimal PyTorch state dict
pt_state_dict = {
    'layer.0.weight': torch.randn(4, 3),
    'layer.0.bias': torch.randn(4),
    'layer.1.weight': torch.randn(5, 4),
    'layer.1.bias': torch.randn(5),
}

# Create a minimal Flax model class
class MinimalFlaxModel:
    def __init__(self):
        self.base_model_prefix = 'layer'
        
        # Build minimal params structure
        params_dict = {
            ('layer', '0', 'kernel'): jnp.ones((3, 4)),
            ('layer', '0', 'bias'): jnp.ones((4,)),
            ('layer', '1', 'kernel'): jnp.ones((4, 5)),
            ('layer', '1', 'bias'): jnp.ones((5,)),
        }
        
        # Unflatten to get nested structure
        unflat = unflatten_dict(params_dict)
        self.params = {'params': unflat}

flax_model = MinimalFlaxModel()

ARGS = {
    'pt_state_dict': pt_state_dict,
    'flax_model': flax_model,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
flax, jax, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
convert_state_dict Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py
code served (permissive licence) · get_code("7f278ee4020690d8")
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 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 torch
import numpy as np
from collections import OrderedDict

torch.manual_seed(0)

# Create a minimal config class that provides the required attributes
class MinimalConfig:
    def __init__(self):
        self.vision_config = type('obj', (object,), {'hidden_size': 4})()
        self.text_config = type('obj', (object,), {'hidden_size': 5})()
        self.reduce_dim = 6

# Create orig_state_dict with various key patterns that the function processes
orig_state_dict = OrderedDict()

# Keys for clip_model with attn.in_proj (visual)
orig_state_dict['clip_model.visual.transformer.resblocks.0.attn.in_proj_weight'] = torch.randn(12, 8)  # 4*3 for QKV
orig_state_dict['clip_model.visual.transformer.resblocks.0.attn.in_proj_bias'] = torch.randn(12)

# Keys for clip_model with attn.in_proj (text)
orig_state_dict['clip_model.transformer.resblocks.1.attn.in_proj_weight'] = torch.randn(15, 10)  # 5*3 for QKV
orig_state_dict['clip_model.transformer.resblocks.1.attn.in_proj_bias'] = torch.randn(15)

# Keys for decoder self_attn
orig_state_dict['blocks.2.self_attn.in_proj_weight'] = torch.randn(18, 7)  # 6*3 for QKV
orig_state_dict['blocks.2.self_attn.in_proj_bias'] = torch.randn(18)

# Keys that go through rename_key
orig_state_dict['clip_model.transformer.ln_final.weight'] = torch.randn(5)
orig_state_dict['clip_model.visual.ln_post.weight'] = torch.randn(4)
orig_state_dict['visual.proj.weight'] = torch.randn(3, 2)
orig_state_dict['text_projection.weight'] = torch.randn(2, 3)
orig_state_dict['clip_model.visual.conv1.weight'] = torch.randn(4, 3, 2, 2)
orig_state_dict['clip_model.visual.class_embedding'] = torch.randn(4)
orig_state_dict['clip_model.visual.positional_embedding'] = torch.randn(5, 4)
orig_state_dict['clip_model.positional_embedding'] = torch.randn(10, 5)
orig_state_dict['clip_model.token_embedding.weight'] = torch.randn(8, 4)
orig_state_dict['clip_model.transformer.resblocks.0.ln_1.weight'] = torch.randn(5)
orig_state_dict['clip_model.transformer.resblocks.0.ln_2.weight'] = torch.randn(5)
orig_state_dict['clip_model.transformer.resblocks.0.c_fc.weight'] = torch.randn(6, 5)
orig_state_dict['clip_model.transformer.resblocks.0.c_proj.weight'] = torch.randn(5, 6)
orig_state_dict['clip_model.visual.ln_pre.weight'] = torch.randn(4)
orig_state_dict['film_mul.0.weight'] = torch.randn(3, 3)
orig_state_dict['film_add.1.weight'] = torch.randn(2, 2)
orig_state_dict['reduce.weight'] = torch.randn(4, 5)
orig_state_dict['trans_conv.0.weight'] = torch.randn(3, 4, 2, 2)
orig_state_dict['blocks.0.linear1.weight'] = torch.randn(7, 6)
orig_state_dict['blocks.0.linear2.weight'] = torch.randn(6, 7)
orig_state_dict['blocks.1.norm1.weight'] = torch.randn(5)
orig_state_dict['blocks.1.norm2.weight'] = torch.randn(5)

config = MinimalConfig()

ARGS = {
    'orig_state_dict': orig_state_dict,
    'config': config
}
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 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
get_clipseg_config Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kaist-cvml-lab/part-clipseg/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py
code served (permissive licence) · get_code("3677a1331007ac04")
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 CLIPSegConfig. 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
from transformers import CLIPSegConfig, CLIPSegTextConfig, CLIPSegVisionConfig

torch.manual_seed(0)

ARGS = {
    "model_name": "clipseg_refined_rd16"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CLIPSegConfig — a CLIPSegConfig output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CLIPSegConfig 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
get_relative_import_files Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/dynamic_module_utils.py
code served (permissive licence) · get_code("00cc853a73f3aeb6")
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 list, 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 re
from pathlib import Path
import tempfile
import os

# Create a temporary directory and files for testing
temp_dir = tempfile.mkdtemp()

# Create a simple module file with relative imports
module_file = os.path.join(temp_dir, "main_module.py")
with open(module_file, 'w') as f:
    f.write("""
from .helper import some_function
import .utils
from .submodule import ClassA
""")

# Create helper module
helper_file = os.path.join(temp_dir, "helper.py")
with open(helper_file, 'w') as f:
    f.write("""
def some_function():
    pass
""")

# Create utils module
utils_file = os.path.join(temp_dir, "utils.py")
with open(utils_file, 'w') as f:
    f.write("""
# utility functions
""")

# Create submodule
submodule_file = os.path.join(temp_dir, "submodule.py")
with open(submodule_file, 'w') as f:
    f.write("""
class ClassA:
    pass
""")

ARGS = {
    "module_file": module_file
}
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 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
get_relative_imports Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/dynamic_module_utils.py
code served (permissive licence) · get_code("450aeffe7f80f917")
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 list, 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 tempfile
import os

# Create a temporary Python file with relative imports
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_module.py")

content = """
import .submodule
import .utils
from .helpers import some_function
from .core import another_function
import os
from typing import List
"""

with open(temp_file, 'w', encoding='utf-8') as f:
    f.write(content)

ARGS = {
    'module_file': temp_file
}
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 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
infer_metric_tags_from_eval_results Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/modelcard.py
pointer only (licence: MIT); the stored copy get_code serves, from shen8424/CORE, is pointer only (licence: NONE) · get_code("dd8f7751ef859581")
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 shen8424/CORE, 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.

load_imagenet_labels Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/datasets/partimagenet_preprocess.py
code served (permissive licence) · get_code("26175e73e7041e86")
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 dict. 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 tempfile
import os

# Create a temporary imagenet labels file
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_filename = temp_file.name

# Write sample imagenet labels in the expected format
# Format: imagenet_id name1,name2,name3
labels_content = """n02084442 cat,feline,kitty
n02085374 dog,canine,puppy
n02085782 Japanese spaniel,Japanese dog,chin
n02085936 Maltese dog,Maltese terrier,Maltese
n02086094 Afghan hound,Afghan
"""

temp_file.write(labels_content)
temp_file.close()

ARGS = {
    'imagenet_labels_filename': temp_filename
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
parse_keras_history Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/modelcard.py
code served (permissive licence) · get_code("a4491b45d19b7a39")
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 torch
import torch.nn as nn
from unittest.mock import Mock

torch.manual_seed(0)

# Create a mock tf.keras.History object
mock_history = Mock()
mock_history.history = {
    'loss': [0.5, 0.4, 0.3],
    'accuracy': [0.7, 0.8, 0.85],
    'val_loss': [0.6, 0.5, 0.4],
    'val_accuracy': [0.65, 0.75, 0.82]
}
mock_history.epoch = [0, 1, 2]

ARGS = {
    'logs': mock_history
}
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
preprocess_partimagenet Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/datasets/partimagenet_preprocess.py
code served (permissive licence) · get_code("ee588a4e50fa1acd")
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 os
import shutil
import tempfile

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()

# Create the required directory structure
images_train_dir = os.path.join(temp_dir, 'images', 'train')
images_val_dir = os.path.join(temp_dir, 'images', 'val')
anno_train_dir = os.path.join(temp_dir, 'annotations', 'train')
anno_val_dir = os.path.join(temp_dir, 'annotations', 'val')

os.makedirs(images_train_dir, exist_ok=True)
os.makedirs(images_val_dir, exist_ok=True)
os.makedirs(anno_train_dir, exist_ok=True)
os.makedirs(anno_val_dir, exist_ok=True)

# Create sample image files with valid class IDs
valid_image_files = [
    'n02128757_tiger_001.jpg',
    'n02110063_malamute_001.jpg',
    'n01704323_triceratops_001.jpg',
]
for img_file in valid_image_files:
    open(os.path.join(images_train_dir, img_file), 'w').close()
    open(os.path.join(images_val_dir, img_file), 'w').close()

# Create sample annotation files
anno_files = [
    'n02128757_tiger_001.xml',
    'n02110063_malamute_001.xml',
    'n01704323_triceratops_001.xml',
]
for anno_file in anno_files:
    open(os.path.join(anno_train_dir, anno_file), 'w').close()
    open(os.path.join(anno_val_dir, anno_file), 'w').close()

# Create train.json and val.json in annotations directories
open(os.path.join(anno_train_dir, 'train.json'), 'w').close()
open(os.path.join(anno_val_dir, 'val.json'), 'w').close()

# Create ImageNet labels file
labels_file = os.path.join(temp_dir, 'imagenet_labels.txt')
with open(labels_file, 'w') as f:
    f.write('n02128757 tiger, tigers\n')
    f.write('n02110063 malamute, malamutes\n')
    f.write('n01704323 triceratops, triceratops\n')
    f.write('n02128925 golden retriever, golden retrievers\n')
    f.write('n02129604 ice bear, polar bear\n')
    f.write('n02128385 leopard, leopards\n')
    f.write('n01601155 Indian cobra, cobra\n')
    f.write('n01728920 green lizard, lizard\n')
    f.write('n02110185 Siberian husky, husky\n')

ARGS = {
    'data_dir': temp_dir,
    'imagenet_labels_filename': labels_file,
}
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 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
rename_key Ran
ran; our contract draft was wrong, not the code
kaist-cvml-lab/part-clipseg/transformers/models/clipseg/convert_clipseg_original_pytorch_to_hf.py
code served (permissive licence) · get_code("f58ed61ea5ae630b")
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.

import torch

# The function rename_key takes a single parameter: a string 'name'
# It performs various string replacements on this name and returns the modified string
# No complex objects needed - just a string input

ARGS = {
    'name': 'clip_model.visual.transformer.resblocks.0.attn.in_proj_weight'
}
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 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
rename_key_and_reshape_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kaist-cvml-lab/part-clipseg/transformers/modeling_flax_pytorch_utils.py
code served (permissive licence) · get_code("61779b0406a59cfc")
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 jax.numpy as jnp
import numpy as np

# Create a small random Flax state dict with various key patterns
random_flax_state_dict = {
    ('layer', 'scale'): jnp.array([1.0, 2.0, 3.0, 4.0]),
    ('layer', 'mean'): jnp.array([0.1, 0.2, 0.3, 0.4]),
    ('layer', 'var'): jnp.array([0.01, 0.02, 0.03, 0.04]),
    ('layer', 'embedding'): jnp.ones((4, 5)),
    ('layer', 'kernel'): jnp.ones((2, 3, 4, 5)),
    ('prefix', 'layer', 'scale'): jnp.array([1.0, 2.0]),
}

# Create a PyTorch tensor to be renamed and potentially reshaped
# Using a 4D tensor for testing the 4D reshape case
pt_tensor = np.random.randn(3, 4, 5, 6).astype(np.float32)

# Create a tuple key representing a PyTorch weight name
pt_tuple_key = ('layer', 'weight')

# Model prefix used for checking prefixed keys
model_prefix = 'prefix'

ARGS = {
    'pt_tuple_key': pt_tuple_key,
    'pt_tensor': pt_tensor,
    'random_flax_state_dict': random_flax_state_dict,
    'model_prefix': model_prefix,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax, numpy — 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
check_imports Not yet run
unverified (harvested, no recorded run)
kaist-cvml-lab/part-clipseg/transformers/dynamic_module_utils.py
code served (permissive licence) · get_code("f4075cdecbb730c5")
How it ran

no invocation recorded.

is_hf_dataset Not yet run
unverified (harvested, no recorded run)
kaist-cvml-lab/part-clipseg/transformers/modelcard.py
pointer only (licence: MIT); the stored copy get_code serves, from shen8424/CORE, is pointer only (licence: NONE) · get_code("ec7b1528a936234d")
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 shen8424/CORE, 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 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 11 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 5 the same month, 9 later) and 4 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
contrastive_loss 27 other papers
13 dated earlier, 13 later, 1 same year, order not determinable · 3 only as an assembly brick
2206.00621 (2022-06)
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training
2209.06430 (2022-09)
CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment
2210.00312 (2022-10)
Multimodal Analogical Reasoning over Knowledge Graphs
and 24 more not named here
infer_metric_tags_from_eval_results 19 other papers
11 dated earlier, 1 the same month, 7 later
2022.findings-emnlp.427 (2022 (year only))
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
and 16 more not named here
get_relative_import_files 18 other papers
13 dated earlier, 2 the same month, 3 later
2211.11694 (2022-11)
Exploring Discrete Diffusion Models for Image Captioning
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
and 15 more not named here
get_relative_imports 18 other papers
13 dated earlier, 2 the same month, 3 later
2211.11694 (2022-11)
Exploring Discrete Diffusion Models for Image Captioning
2304.05568 (2023-04)
Improving Diffusion Models for Scene Text Editing with Dual Encoders
2305.15756 (2023-05)
UniTRec: A Unified Text-to-Text Transformer and Joint Contrastive Learning Framework for Text-based Recommendation
and 15 more not named here
is_hf_dataset 16 other papers
8 dated earlier, 1 the same month, 7 later
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
2312.09979 (2023-12)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
and 13 more not named here
parse_keras_history 16 other papers
8 dated earlier, 1 the same month, 7 later
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
2312.09979 (2023-12)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
and 13 more not named here
convert_pytorch_state_dict_to_flax 6 other papers
6 dated earlier
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
2312.09979 (2023-12)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
and 3 more not named here
rename_key_and_reshape_tensor 6 other papers
6 dated earlier
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2310.09832 (2023-10)
Merging Experts into One: Improving Computational Efficiency of Mixture of Experts
2312.09979 (2023-12)
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
and 3 more not named here
check_imports 3 other papers
2 dated earlier, 1 later
2310.05107 (2023-10)
OV-PARTS: Towards Open-Vocabulary Part Segmentation
2402.05827 (2024-02)
On the Robustness of Editing Large Language Models
2501.09688 (2025-01)
Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
load_imagenet_labels 1 other paper
1 later
2501.09688 (2025-01)
Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
preprocess_partimagenet 1 other paper
1 later
2501.09688 (2025-01)
Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation

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

Ground-truth (b) Object-level Pred. (c) Generalized Parts Pred. (d) Final Pred. (e) "head" (f) "torso" (g) "ear" (h) "nose" (i) "paw" Figure 1: Prediction results of our PartCLIPSeg for unseen categories in the Pascal-Part-116 [7, 46] validation set. A "dog" is unseen during training. The final prediction of PartCLIPSeg utilizes (b) object-level context and (c) generalized parts, incorporating disjoint activation among (e)-(i) parts, and enhancing activation for smaller parts (e.g., (h) "nose").

For agents

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

get_harvested_code_for_paper("2406.11384")
get_code_for_paper("2406.11384")
have("2406.11384")

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

curl https://syntology.ai/api/ran/2406.11384.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.11384.svg)](https://syntology.ai/paper/2406.11384)

Connect an agent — have() is free.