SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.01635 · 2023

SPTS v2: Single-Point Scene Text Spotting

arXiv · PDF · Open in the Atlas

Code that ran

15 of 16 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 8 have no contract verdict; 6 failures 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/2301.01635.json · badge: /api/ran/2301.01635.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
bytedance/sptsv2 canonical (classifier label)
classifier basis not recorded on the link
15 ran · 1 no recorded run
FunctionStatusWhere it lives
all_gather Ran
ran; our contract draft was wrong, not the code
bytedance/sptsv2/util/misc_sptsv2.py
code served (permissive licence) · get_code("ebbfd2397d6c7321")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import pickle

torch.manual_seed(0)

# The all_gather function accepts a single parameter: data
# which must be any picklable object. The function pickles it,
# converts to tensor, and gathers across ranks.
# Since we're not in a distributed setting, it will return [data]

# Create a simple picklable data object - a dict with various types
data = {
    "tensor": torch.randn(2, 4),
    "list": [1, 2, 3],
    "string": "test_data",
    "number": 42,
    "nested": {"a": 1, "b": [4, 5, 6]}
}

ARGS = {
    "data": data
}
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 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
bezier_to_polygon Ran
ran on a synthesized input
bytedance/sptsv2/datasets/ocr_dataset.py
code served (permissive licence) · get_code("5d3dcc613a7cfc85")
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 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function expects a bezier parameter that will be:
# 1. Converted to np.array
# 2. Reshaped to (2, 4, 2)
# 3. Further manipulated
# So we need to provide something array-like with 16 elements (2*4*2)

# Create a simple bezier curve control points array
# 16 elements total: 2 curves, 4 control points each, 2D coordinates
bezier_input = [
    # First curve: 4 control points in 2D
    0.0, 0.0,  # point 1
    0.5, 1.0,  # point 2
    1.0, 1.0,  # point 3
    1.5, 0.0,  # point 4
    # Second curve: 4 control points in 2D
    1.5, 0.0,  # point 1
    2.0, -1.0, # point 2
    2.5, -1.0, # point 3
    3.0, 0.0,  # point 4
]

ARGS = {
    "bezier": bezier_input
}
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 list, ndim 2, 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
crop Ran
ran on a synthesized input
bytedance/sptsv2/datasets/sptsv2_transforms.py
code served (permissive licence) · get_code("8eac9e88e2b866d8")
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 torchvision.transforms.functional as F
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a small PIL image (height=100, width=80)
image = Image.new('RGB', (80, 100), color=(73, 109, 137))

# Create target dict with required fields
target = {
    'boxes': torch.tensor([
        [10.0, 15.0, 40.0, 50.0],  # box 1
        [45.0, 55.0, 75.0, 90.0],  # box 2
    ], dtype=torch.float32),
    'size': torch.tensor([100, 80], dtype=torch.int64),
    'labels': torch.tensor([1, 2], dtype=torch.int64),
    'area': torch.tensor([900.0, 1050.0], dtype=torch.float32),
    'iscrowd': torch.tensor([0, 0], dtype=torch.int64),
    'rec': torch.tensor([0, 1], dtype=torch.int64),
    'masks': torch.randint(0, 2, (2, 100, 80), dtype=torch.uint8),
    'bezier_pts': torch.tensor([
        [10.0, 15.0, 12.0, 16.0, 14.0, 17.0, 16.0, 18.0, 18.0, 19.0, 20.0, 20.0, 22.0, 21.0, 24.0, 22.0],
        [45.0, 55.0, 47.0, 56.0, 49.0, 57.0, 51.0, 58.0, 53.0, 59.0, 55.0, 60.0, 57.0, 61.0, 59.0, 62.0],
    ], dtype=torch.float32),
    'center_pts': torch.tensor([
        [25.0, 32.0],
        [60.0, 72.0],
    ], dtype=torch.float32),
}

# Define region: (ymin, xmin, height, width)
region = (5, 5, 60, 50)

ARGS = {
    'image': image,
    'target': target,
    'region': region,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — 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
crop_ Ran
ran on a synthesized input
bytedance/sptsv2/datasets/sptsv2_transforms.py
code served (permissive licence) · get_code("94654eada185e63b")
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 torchvision.transforms.functional as F

torch.manual_seed(0)

# Create a small image tensor (3 channels, height 10, width 12)
image = torch.randint(0, 256, (3, 10, 12), dtype=torch.uint8)

# Create a target dict with boxes and masks
target = {
    'labels': torch.tensor([0, 1]),
    'area': torch.tensor([20.0, 30.0]),
    'iscrowd': torch.tensor([0, 0]),
    'boxes': torch.tensor([[1.0, 1.0, 5.0, 4.0], [3.0, 2.0, 8.0, 7.0]]),
    'masks': torch.randint(0, 2, (2, 10, 12), dtype=torch.uint8),
    'size': torch.tensor([10, 12])
}

# Define region as (top, left, height, width)
region = (1, 2, 6, 8)

ARGS = {
    'image': image,
    'target': target,
    'region': region
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — 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
draw_short_line Ran
ran on a synthesized input
bytedance/sptsv2/util/visualize.py
code served (permissive licence) · get_code("a4a397c75fc42094")
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 int, shape (100, 100, 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 cv2
import numpy as np

# Create a small image (BGR format for OpenCV)
image = np.zeros((100, 100, 3), dtype=np.uint8)

# Create bezier_pts array with shape (8, 2) since the function accesses indices 0, 3, 4, 7
# Each row is [x, y] coordinate
bezier_pts = np.array([
    [10, 10],   # index 0
    [20, 15],   # index 1
    [30, 20],   # index 2
    [40, 25],   # index 3
    [50, 30],   # index 4
    [60, 35],   # index 5
    [70, 40],   # index 6
    [80, 45]    # index 7
], dtype=np.int32)

ARGS = {
    "image": image,
    "bezier_pts": bezier_pts
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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 int, shape (100, 100, 3) — shape (100, 100, 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
dynamic_point Ran
ran on a synthesized input
bytedance/sptsv2/datasets/ocr_dataset.py
code served (permissive licence) · get_code("dd6bcdc703fcdaed")
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 math
import random

random.seed(0)

# pts is used with indexing: pts[0] and pts[1]
# So it needs to be a sequence with at least 2 elements
pts = (1.5, 2.5)

# radius is used in arithmetic (multiplication with math.cos and math.sin results)
# It should be a numeric value
radius = 0.5

ARGS = {
    "pts": pts,
    "radius": radius,
}
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, 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
extract_result_from_output_seqs Ran
ran on a synthesized input
bytedance/sptsv2/util/visualize.py
code served (permissive licence) · get_code("5c400bdf7fa3204b")
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

torch.manual_seed(0)

# Analyze the function to determine parameter requirements:
# - seqs: tensor of indices, used with indexing and comparison
# - rec_score: tensor with shape allowing [:, category_start_index:category_start_index + len(chars)]
# - key_pts: string key for dictionary
# - key_label: string key for dictionary
# - return_index: boolean
# - bins: integer
# - padding_bins: integer
# - pad_rec: boolean
# - text_length: integer
# - chars: list

bins = 1000
padding_bins = 10
text_length = 25
chars = ['a', 'b', 'c', 'd', 'e']  # 5 characters

# Calculate dimensions needed
category_start_index = bins + 2 * padding_bins
end_index = bins + len(chars) + 1

# Create seqs tensor: needs indices up to end_index
# Structure: [pt1, pt2, char_indices..., end_index] repeated
# Making a small sequence with 2 points, 25 characters, then end marker
seqs_list = [100, 200]  # 2 point coordinates
seqs_list.extend([category_start_index + i % len(chars) for i in range(text_length)])  # 25 character indices
seqs_list.append(end_index)  # end marker
seqs = torch.tensor(seqs_list, dtype=torch.long)

# Create rec_score tensor: shape [batch_size, num_features]
# It gets sliced as rec_score[:, category_start_index:category_start_index + len(chars)]
# So we need at least category_start_index + len(chars) columns
# We need enough rows for the number of sequences (1 sequence needs 1 row with text_length entries processed)
batch_size = 2
num_features = category_start_index + len(chars) + 10  # extra buffer
rec_score = torch.randn(batch_size, num_features)

ARGS = {
    'seqs': seqs,
    'rec_score': rec_score,
    'key_pts': 'center_pts',
    'key_label': 'rec',
    'return_index': False,
    'bins': bins,
    'padding_bins': padding_bins,
    'pad_rec': True,
    'text_length': text_length,
    'chars': chars,
}
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 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
generate_square_subsequent_mask Ran
ran, violated the contract we drafted
bytedance/sptsv2/models/encoder_decoder.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from chend-vl/instructocr, is pointer only (licence: NONE) · get_code("894b253f35765276")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from chend-vl/instructocr, 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.

hflip Ran
ran; our contract draft was wrong, not the code
bytedance/sptsv2/datasets/sptsv2_transforms.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kellyiss/situformer, is pointer only (licence: NONE) · get_code("9be9e658b5bd688a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kellyiss/situformer, 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.

nested_tensor_from_tensor_list Ran
ran; our contract draft was wrong, not the code
bytedance/sptsv2/util/misc_sptsv2.py
code served (permissive licence) · get_code("5adadb63e05f89b9")
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 NestedTensor. 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 typing import List

torch.manual_seed(0)

# Create a list of 3D tensors with different sizes
# Each tensor has shape (C, H, W)
tensor1 = torch.randn(3, 4, 5)  # 3 channels, 4 height, 5 width
tensor2 = torch.randn(3, 6, 7)  # 3 channels, 6 height, 7 width

tensor_list = [tensor1, tensor2]

ARGS = {
    "tensor_list": tensor_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type NestedTensor — a NestedTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a NestedTensor 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
process_args Ran
ran on a synthesized input
bytedance/sptsv2/util/data.py
code served (permissive licence) · get_code("3176f181873cc5f4")
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 Args. 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

class Args:
    def __init__(self):
        self.bins = 10
        self.padding_bins = 2
        self.chars = ['a', 'b', 'c', 'd', 'e']
        self.pad_rec = False

ARGS = {
    "args": Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Args — a Args output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Args 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
read_lexicon Ran
ran on a synthesized input
bytedance/sptsv2/eval_ic15.py
code served (permissive licence) · get_code("667724bf107c52b8")
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 os
import tempfile

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

# Test case 1: .txt file path
txt_file = os.path.join(temp_dir, 'lexicon.txt')
with open(txt_file, 'w') as f:
    f.write("word1\n")
    f.write("  word2  \n")
    f.write("word3\n")

ARGS = {
    'lexicon_path': txt_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
reduce_dict Ran
ran; our contract draft was wrong, not the code
bytedance/sptsv2/util/misc_sptsv2.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from kellyiss/situformer, is pointer only (licence: NONE) · get_code("05992505df9ef0cd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from kellyiss/situformer, 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.

window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bytedance/sptsv2/models/encoder_decoder.py
code served (permissive licence) · get_code("f9fd6241d935f07b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (12, 4, 4, 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 tensor with shape (B, H, W, C)
# B = 2 (batch size)
# H = 8 (height, must be divisible by window_size)
# W = 12 (width, must be divisible by window_size)
# C = 4 (channels)
# window_size = 4

B = 2
H = 8
W = 12
C = 4
window_size = 4

x = torch.randn(B, H, W, C)

ARGS = {
    'x': x,
    'window_size': window_size
}
Setup block drafted by
a language model, Claude Sonnet 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 (12, 4, 4, 4) — shape (12, 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
window_reverse Ran
ran; our contract draft was wrong, not the code
bytedance/sptsv2/models/encoder_decoder.py
code served (permissive licence) · get_code("fb32094c6dbece71")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 8, 12, 6) 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)

# Define parameters
# We need windows of shape (num_windows*B, window_size, window_size, C)
# where num_windows = (H // window_size) * (W // window_size)

B = 2
H = 8
W = 12
window_size = 4
C = 6

# Calculate num_windows
num_windows_h = H // window_size  # 8 // 4 = 2
num_windows_w = W // window_size  # 12 // 4 = 3
num_windows = num_windows_h * num_windows_w  # 2 * 3 = 6

# Total number of windows across batch
total_windows = num_windows * B  # 6 * 2 = 12

# Create windows tensor
windows = torch.randn(total_windows, window_size, window_size, C)

ARGS = {
    'windows': windows,
    'window_size': window_size,
    'H': H,
    'W': W
}
Setup block drafted by
a language model, Claude Sonnet 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, 6) — shape (2, 8, 12, 6) 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
weighted_edit_distance Not yet run
unverified (harvested, no recorded run)
bytedance/sptsv2/eval_ic15.py
code served (permissive licence) · get_code("16e0e017ff8eb9d7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 7 later) and 9 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
74 dated earlier, 144 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
69 dated earlier, 145 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
nested_tensor_from_tensor_list 55 other papers
20 dated earlier, 34 later, 1 same year, order not determinable · 17 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2101.01909 (2021-01)
Line Segment Detection Using Transformers without Edges
and 52 more not named here
reduce_dict 33 other papers
14 dated earlier, 19 later
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
1811.10200 (2018-11)
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments
2007.02419 (2020-07)
Attention-based Joint Detection of Object and Semantic Part
and 30 more not named here
all_gather 30 other papers
12 dated earlier, 18 later
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
1811.10200 (2018-11)
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments
2007.02419 (2020-07)
Attention-based Joint Detection of Object and Semantic Part
and 27 more not named here
hflip 10 other papers
4 dated earlier, 5 later, 1 same year, order not determinable
2106.00666 (2021-06)
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
2112.05375 (2021-12)
Rethinking the Two-Stage Framework for Grounded Situation Recognition
2112.08647 (2021-12)
QAHOI: Query-Based Anchors for Human-Object Interaction Detection
and 7 more not named here
generate_square_subsequent_mask 8 other papers
6 dated earlier, 2 later · 1 only as an assembly brick
2004.09144 (2020-04)
Transformer Reasoning Network for Image-Text Matching and Retrieval
2008.05231 (2020-08)
Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders
2107.03377 (2021-07)
Long Short-Term Transformer for Online Action Detection
and 5 more not named here

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

End-to-end scene text spotting has made significant progress due to its intrinsic synergy between text detection and recognition. Previous methods commonly regard manual annotations such as horizontal rectangles, rotated rectangles, quadrangles, and polygons as a prerequisite, which are much more expensive than using single-point. Our new framework, SPTS v2, allows us to train high-performing text-spotting models using a single-point annotation. SPTS v2 reserves the advantage of the auto-regressive Transformer with an Instance Assignment Decoder (IAD) through sequentially predicting the center points of all text instances inside the same predicting sequence, while with a Parallel Recognition Decoder (PRD) for text recognition in parallel, which significantly reduces the requirement of the length of the sequence. These two decoders share the same parameters and are interactively connected with a simple but effective information transmission process to pass the gradient and information. Comprehensive experiments on various existing benchmark datasets demonstrate the SPTS v2 can outperform previous state-of-the-art single-point text spotters with fewer parameters while achieving 19$\times$ faster inference speed. Within the context of our SPTS v2 framework, our experiments suggest a potential preference for single-point representation in scene text spotting when compared to other representations. Such an attempt provides a significant opportunity for scene text spotting applications beyond the realms of existing paradigms. Code is available at: https://github.com/Yuliang-Liu/SPTSv2.

For agents

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

get_harvested_code_for_paper("2301.01635")
get_code_for_paper("2301.01635")
have("2301.01635")

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

curl https://syntology.ai/api/ran/2301.01635.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.01635.svg)](https://syntology.ai/paper/2301.01635)

Connect an agent — have() is free.