SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.00515 · 2020

Linguistic Structure Guided Context Modeling for Referring Image Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

16 of 17 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 15 have no contract verdict; 1 failure of our instrument; 1 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/2010.00515.json · badge: /api/ran/2010.00515.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
spyflying/LSCM-Refseg canonical (classifier label)
classifier basis: census
16 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_accuracy Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/processing_tools.py
code served (permissive licence) · get_code("194457507e72807b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create sample scores and labels
# scores: array of floats that will be compared to 0
# labels: array where non-zero means positive, zero means negative
np.random.seed(0)

scores = np.array([0.5, -0.3, 0.1, -0.8, 0.2, -0.1], dtype=np.float32)
labels = np.array([1, 0, 1, 0, 1, 1], dtype=np.int32)

ARGS = {
    "scores": scores,
    "labels": labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_bbox_iou Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/eval_tools.py
code served (permissive licence) · get_code("f450953318e6ee92")
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 ndarray, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create sample bounding boxes in format [x1, y1, x2, y2]
# Two bounding boxes
bboxes = np.array([
    [10, 20, 50, 80],
    [15, 25, 60, 90]
])

# Target bounding box
target = np.array([
    [20, 30, 70, 100]
])

ARGS = {
    "bboxes": bboxes,
    "target": target
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
compute_mask_IU Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/eval_tools.py
code served (permissive licence) · get_code("09efe975daf592dc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create small binary masks for testing
# The function expects arrays where the last two dimensions match
masks = np.random.randint(0, 2, size=(2, 4, 3)).astype(bool)
target = np.random.randint(0, 2, size=(2, 4, 3)).astype(bool)

ARGS = {
    "masks": masks,
    "target": target,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
crop_bboxes_subtract_mean Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/im_processing.py
code served (permissive licence) · get_code("d2e8a2e2ab967bb5")
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 ndarray, ndim 4, dtype family float, shape (2, 8, 8, 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 numpy as np
import skimage.transform

# Create a small test image (4 height x 3 width x 3 channels)
im = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

# Create bounding boxes as list of [xmin, ymin, xmax, ymax]
# Using coordinates that fit within the image dimensions
bboxes = [
    [0, 0, 2, 3],  # bbox 1
    [1, 1, 2, 2]   # bbox 2
]

# Crop size for output patches
crop_size = 8

# Image mean to subtract (3 channels)
image_mean = np.array([103.939, 116.779, 123.68], dtype=np.float32)

ARGS = {
    'im': im,
    'bboxes': bboxes,
    'crop_size': crop_size,
    'image_mean': image_mean
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (2, 8, 8, 3) — shape (2, 8, 8, 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
generate_bilinear_filter Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/processing_tools.py
code served (permissive licence) · get_code("f7989872fc271fc0")
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 ndarray, ndim 4, dtype family float, shape (8, 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 numpy as np

def generate_bilinear_filter(stride):
    f = np.concatenate((np.arange(0, stride), np.arange(stride, 0, -1))) / stride
    return np.outer(f, f).astype(np.float32)[:, :, np.newaxis, np.newaxis]

ARGS = {
    "stride": 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (8, 8, 1, 1) — shape (8, 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
generate_spatial_batch Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/processing_tools.py
code served (permissive licence) · get_code("59f5606fd0309cbf")
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 ndarray, ndim 4, dtype family float, shape (2, 3, 4, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function takes three integer parameters: N (batch size), featmap_H (height), and featmap_W (width)
# It generates a spatial batch array of shape (N, featmap_H, featmap_W, 8)
# The function uses these parameters only in:
# - np.zeros((N, featmap_H, featmap_W, 8), ...) - creates array with these dimensions
# - range loops over featmap_H and featmap_W
# - arithmetic operations with N, featmap_H, featmap_W

# Set up small but distinct dimensions
N = 2  # batch size
featmap_H = 3  # height
featmap_W = 4  # width

ARGS = {
    "N": N,
    "featmap_H": featmap_H,
    "featmap_W": featmap_W,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (2, 3, 4, 8) — shape (2, 3, 4, 8) 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
l2_regularization_loss Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/loss.py
code served (permissive licence) · get_code("64e03b60c7102569")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create small TensorFlow variables with distinct shapes
var1 = tf.Variable(np.random.randn(2, 3).astype(np.float32))
var2 = tf.Variable(np.random.randn(4, 5).astype(np.float32))
var3 = tf.Variable(np.random.randn(2).astype(np.float32))

variables = [var1, var2, var3]
weight_decay = 0.01

ARGS = {
    "variables": variables,
    "weight_decay": weight_decay
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
load_json Ran
ran; our contract draft was wrong, not the code
spyflying/LSCM-Refseg/util/io.py
code served (permissive licence) · get_code("2d946250dd2f5a4f")
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 json
import tempfile
import os

# Create a temporary JSON file to load
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test.json")

# Write a valid JSON file
test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(temp_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "filename": 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 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
load_referit_gt_mask Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/io.py
code served (permissive licence) · get_code("530fed7535d13582")
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 ndarray, ndim 2, dtype family float, shape (3, 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 scipy.io as sio
import numpy as np
import tempfile
import os

# Create a temporary .mat file with the required structure
temp_dir = tempfile.mkdtemp()
mask_path = os.path.join(temp_dir, "test_mask.mat")

# Create a sample segmentation image (2D array with integer values)
# The function checks where segimg_t == 0
segimg_t = np.array([
    [0, 1, 2, 0],
    [1, 0, 1, 2],
    [0, 1, 0, 1]
], dtype=np.int32)

# Save to .mat file
sio.savemat(mask_path, {'segimg_t': segimg_t})

ARGS = {
    'mask_path': mask_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 4) — shape (3, 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_str_list Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/io.py
code served (permissive licence) · get_code("0b90dfa6d16c4a7a")
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 file with some test strings
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("line one\n")
temp_file.write("line two\n")
temp_file.write("line three\n")
temp_file.close()

ARGS = {
    "filename": temp_file.name
}
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
load_vocab_dict_from_file Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/text_processing.py
code served (permissive licence) · get_code("f63e65fc417999ae")
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 vocabulary file
with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt') as f:
    vocab_file = f.name
    f.write("apple\n")
    f.write("banana\n")
    f.write("cherry\n")
    f.write("date\n")
    f.write("elderberry\n")

ARGS = {
    "dict_file": vocab_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 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
preprocess_sentence Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/text_processing.py
code served (permissive licence) · get_code("5d0a6645f212e560")
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 int; 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

# Define the constants and functions from the target code
UNK_IDENTIFIER = '<unk>'
PAD_IDENTIFIER = '<pad>'
SENTENCE_SPLIT_REGEX = re.compile('(\\W+)')

def sentence2vocab_indices(sentence, vocab_dict):
    words = SENTENCE_SPLIT_REGEX.split(sentence.strip())
    words = [w.lower() for w in words if len(w.strip()) > 0]
    if words[-1] == '.':
        words = words[:-1]
    vocab_indices = [vocab_dict[w] if w in vocab_dict else vocab_dict[UNK_IDENTIFIER] for w in words]
    return vocab_indices

def preprocess_sentence(sentence, vocab_dict, T):
    vocab_indices = sentence2vocab_indices(sentence, vocab_dict)
    if len(vocab_indices) > T:
        vocab_indices = vocab_indices[:T]
    if len(vocab_indices) < T:
        vocab_indices = [vocab_dict[PAD_IDENTIFIER]] * (T - len(vocab_indices)) + vocab_indices
    return vocab_indices

# Create test arguments
sentence = "hello world test."
vocab_dict = {
    'hello': 1,
    'world': 2,
    'test': 3,
    UNK_IDENTIFIER: 0,
    PAD_IDENTIFIER: 4,
}
T = 5

ARGS = {
    'sentence': sentence,
    'vocab_dict': vocab_dict,
    'T': T,
}
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 int — 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
resize_and_crop Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/im_processing.py
code served (permissive licence) · get_code("25b3bc3dcf28fdbc")
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 ndarray, ndim 3, dtype family float, shape (4, 5, 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 numpy as np
import skimage.transform

# Create a simple test image with shape (height, width, channels)
# Using distinct dimensions: 6 height, 8 width, 3 channels (RGB)
im = np.random.rand(6, 8, 3).astype(np.float64)

# Define input dimensions for resizing/cropping
input_h = 4
input_w = 5

ARGS = {
    "im": im,
    "input_h": input_h,
    "input_w": input_w,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (4, 5, 3) — shape (4, 5, 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
resize_and_pad Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/im_processing.py
code served (permissive licence) · get_code("abcefd336b9b2406")
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 ndarray, ndim 3, dtype family float, shape (10, 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 numpy as np
import skimage.transform

# Create a small test image with 3 channels (RGB)
# Using shape (6, 8, 3) for height=6, width=8, 3 color channels
im = np.random.rand(6, 8, 3).astype(np.float32)

# Define input dimensions for resizing and padding
input_h = 10
input_w = 12

ARGS = {
    "im": im,
    "input_h": input_h,
    "input_w": input_w,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (10, 12, 3) — shape (10, 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
sentence2vocab_indices Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/text_processing.py
code served (permissive licence) · get_code("c01f6b0c8f72794c")
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 int; 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

UNK_IDENTIFIER = '<unk>'
SENTENCE_SPLIT_REGEX = re.compile('(\\W+)')

# Create a small vocab_dict with common words and the UNK token
vocab_dict = {
    '<unk>': 0,
    'hello': 1,
    'world': 2,
    'this': 3,
    'is': 4,
    'a': 5,
    'test': 6,
    'sentence': 7,
}

# Create a test sentence with some known and unknown words
sentence = "hello world this is unknown"

ARGS = {
    'sentence': sentence,
    'vocab_dict': vocab_dict,
}
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 int — 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
weighed_logistic_loss Ran
ran on a synthesized input
spyflying/LSCM-Refseg/util/loss.py
code served (permissive licence) · get_code("9c14d97dc852ea26")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)

# Create small test tensors
batch_size = 2
height = 4
width = 3
channels = 2

# scores: logits tensor, shape should be compatible with sigmoid_cross_entropy_with_logits
# The function reduces over dims [1, 2, 3], so we need at least 4 dimensions
scores = tf.constant(np.random.randn(batch_size, height, width, channels).astype(np.float32))

# labels: binary labels, same shape as scores
labels = tf.constant(np.random.randint(0, 2, size=(batch_size, height, width, channels)).astype(np.float32))

# pos_loss_mult: positive class loss multiplier
pos_loss_mult = 1.0

# neg_loss_mult: negative class loss multiplier
neg_loss_mult = 1.0

ARGS = {
    "scores": scores,
    "labels": labels,
    "pos_loss_mult": pos_loss_mult,
    "neg_loss_mult": neg_loss_mult,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
logistic_loss_cond Not yet run
unverified (harvested, no recorded run)
spyflying/LSCM-Refseg/util/loss.py
code served (permissive licence) · get_code("40605e728317c5b0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 6 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 5 the same month, 4 later) and 11 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
load_json 6 other papers
1 dated earlier, 5 later
2001.09099 (2020-01)
TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval
2107.06383 (2021-07)
How Much Can CLIP Benefit Vision-and-Language Tasks?
2212.03191 (2022-12)
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
and 3 more not named here
l2_regularization_loss 2 other papers
1 the same month, 1 later
2010.00514 (2020-10)
Referring Image Segmentation via Cross-Modal Progressive Comprehension
2202.12076 (2022-02)
Phrase-Based Affordance Detection via Cyclic Bilateral Interaction
logistic_loss_cond 2 other papers
1 the same month, 1 later
2010.00514 (2020-10)
Referring Image Segmentation via Cross-Modal Progressive Comprehension
2202.12076 (2022-02)
Phrase-Based Affordance Detection via Cyclic Bilateral Interaction
weighed_logistic_loss 2 other papers
1 the same month, 1 later
2010.00514 (2020-10)
Referring Image Segmentation via Cross-Modal Progressive Comprehension
2202.12076 (2022-02)
Phrase-Based Affordance Detection via Cyclic Bilateral Interaction
compute_bbox_iou 1 other paper
1 the same month
2010.00514 (2020-10)
Referring Image Segmentation via Cross-Modal Progressive Comprehension
compute_mask_IU 1 other paper
1 the same month
2010.00514 (2020-10)
Referring Image Segmentation via Cross-Modal Progressive Comprehension

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 predict the foreground mask of the object referred by a natural language sentence. Multimodal context of the sentence is crucial to distinguish the referent from the background. Existing methods either insufficiently or redundantly model the multimodal context. To tackle this problem, we propose a "gather-propagate-distribute" scheme to model multimodal context by cross-modal interaction and implement this scheme as a novel Linguistic Structure guided Context Modeling (LSCM) module. Our LSCM module builds a Dependency Parsing Tree suppressed Word Graph (DPT-WG) which guides all the words to include valid multimodal context of the sentence while excluding disturbing ones through three steps over the multimodal feature, i.e., gathering, constrained propagation and distributing. Extensive experiments on four benchmarks demonstrate that our method outperforms all the previous state-of-the-arts.

For agents

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

get_harvested_code_for_paper("2010.00515")
get_code_for_paper("2010.00515")
have("2010.00515")

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

curl https://syntology.ai/api/ran/2010.00515.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.00515.svg)](https://syntology.ai/paper/2010.00515)

Connect an agent — have() is free.