SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.14616 · 2021

ICDAR 2021 Competition on Scientific Literature Parsing

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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 5 have no contract verdict; 3 failures of our instrument; 0 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/2106.14616.json · badge: /api/ran/2106.14616.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
wenwenyu/MASTER-pytorch canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
clones Ran
ran on a synthesized input
wenwenyu/MASTER-pytorch/model/transformer.py
code served (permissive licence) · get_code("919b57fa5b33755b")
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 ModuleList. 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 copy
from torch import nn

torch.manual_seed(0)

# Create a simple module to clone
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Instantiate the module to clone
to_clone_module = SimpleModule()

# Define ARGS for all parameters of clones function
ARGS = {
    "_to_clone_module": to_clone_module,
    "_clone_times": 3,
    "_is_deep": True
}
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 ModuleList — a ModuleList output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ModuleList output the recorded ndim 1 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
wenwenyu/MASTER-pytorch/model/backbone.py
code served (permissive licence) · get_code("158bf4c3a5f11f04")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Conv2d. 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 torch import nn

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
wenwenyu/MASTER-pytorch/model/backbone.py
pointer only (licence: MIT); the stored copy get_code serves, from liyi01827/noisy-contrastive, is pointer only (licence: NONE) · get_code("ec20f22a185cd708")
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 liyi01827/noisy-contrastive, 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.

convert_PubLayNet_blob_to_target_blob Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from ibm-aur-nlp/PubLayNet
pointer only; the stored copy get_code serves, from ibm-aur-nlp/PubLayNet, is pointer only (licence: NOASSERTION) · get_code("ef1e85717438b077")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_image_with_specific_base Ran
ran on a synthesized input
wenwenyu/MASTER-pytorch/utils/GeometryUtils.py
code served (permissive licence) · get_code("040902e0434e025a")
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 (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

# Create a small test image (4x3 with 3 channels - RGB)
# Using distinct dimensions to make shapes unambiguous
_image = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

# Define margins - these represent pixel positions where the image should be placed
_left_margin = 5
_top_margin = 2

# Define base sizes for height and width padding
_height_base = 8
_width_base = 8

# Define the padding value (0 for black padding)
_pad_value = 0

# Whether to output the padding ratio
_output_pad_ratio = False

ARGS = {
    "_image": _image,
    "_left_margin": _left_margin,
    "_top_margin": _top_margin,
    "_height_base": _height_base,
    "_width_base": _width_base,
    "_pad_value": _pad_value,
    "_output_pad_ratio": _output_pad_ratio,
}
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 3, dtype family int, shape (8, 8, 3) — shape (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
predict Ran
ran on a synthesized input
wenwenyu/MASTER-pytorch/model/master.py
code served (permissive licence) · get_code("353e3f0c62275e10")
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

torch.manual_seed(0)

# Build a minimal decode_stage model
class DecodeStage(nn.Module):
    def __init__(self, vocab_size, hidden_dim):
        super().__init__()
        self.linear = nn.Linear(hidden_dim, vocab_size)
    
    def forward(self, labels, memory):
        # labels shape: (batch_size, seq_len)
        # memory shape: (batch_size, memory_dim)
        # output shape: (batch_size, seq_len, vocab_size)
        batch_size, seq_len = labels.shape
        memory_dim = memory.shape[1]
        
        # Simple decoder: project memory to vocab logits for each position
        output = self.linear(memory)  # (batch_size, vocab_size)
        output = output.unsqueeze(1).expand(batch_size, seq_len, -1)  # (batch_size, seq_len, vocab_size)
        return output

# Parameters
batch_size = 2
source_dim = 5
memory_dim = 4
vocab_size = 10
max_length = 3

# Create tensors
source = torch.randn(batch_size, source_dim)
memory = torch.randn(batch_size, memory_dim)

# Create decode stage model
decode_stage = DecodeStage(vocab_size=vocab_size, hidden_dim=memory_dim)

# Symbol indices
sos_symbol = 1
eos_symbol = 2
padding_symbol = 0

ARGS = {
    "_memory": memory,
    "_source": source,
    "_decode_stage": decode_stage,
    "_max_length": max_length,
    "_sos_symbol": sos_symbol,
    "_eos_symbol": eos_symbol,
    "_padding_symbol": padding_symbol,
}
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
resize_with_height Ran
ran on a synthesized input
wenwenyu/MASTER-pytorch/utils/GeometryUtils.py
code served (permissive licence) · get_code("570d335fcbf53e29")
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 (50, 75, 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 test image with distinct dimensions (100 height, 150 width, 3 channels)
# Using BGR format as typical for cv2
test_image = np.random.randint(0, 256, (100, 150, 3), dtype=np.uint8)

# Target height for resizing
target_height = 50

ARGS = {
    "_image": test_image,
    "_target_height": target_height
}
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 (50, 75, 3) — shape (50, 75, 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
subsequent_mask Ran
ran on a synthesized input
wenwenyu/MASTER-pytorch/model/transformer.py
code served (permissive licence) · get_code("834af6288569bec9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 1, 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)

# The function expects _target to be a tensor with .size() method
# It accesses _target.size(0) for batch_size and _target.size(1) for sequence_length
# So we need a 2D tensor with at least 2 dimensions
_target = torch.randint(0, 10, (2, 4))

ARGS = {
    "_target": _target
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 1, 4, 4) — shape (2, 1, 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

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 2 later) and 5 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
conv3x3 686 other papers
312 dated earlier, 12 the same month, 356 later, 6 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
conv1x1 431 other papers
132 dated earlier, 5 the same month, 288 later, 5 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
convert_PubLayNet_blob_to_target_blob 1 other paper
1 dated earlier
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis

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

Scientific literature contain important information related to cutting-edge innovations in diverse domains. Advances in natural language processing have been driving the fast development in automated information extraction from scientific literature. However, scientific literature is often available in unstructured PDF format. While PDF is great for preserving basic visual elements, such as characters, lines, shapes, etc., on a canvas for presentation to humans, automatic processing of the PDF format by machines presents many challenges. With over 2.5 trillion PDF documents in existence, these issues are prevalent in many other important application domains as well. Our ICDAR 2021 Scientific Literature Parsing Competition (ICDAR2021-SLP) aims to drive the advances specifically in document understanding. ICDAR2021-SLP leverages the PubLayNet and PubTabNet datasets, which provide hundreds of thousands of training and evaluation examples. In Task A, Document Layout Recognition, submissions with the highest performance combine object detection and specialised solutions for the different categories. In Task B, Table Recognition, top submissions rely on methods to identify table components and post-processing methods to generate the table structure and content. Results from both tasks show an impressive performance and opens the possibility for high performance practical applications.

For agents

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

get_harvested_code_for_paper("2106.14616")
get_code_for_paper("2106.14616")
have("2106.14616")

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

curl https://syntology.ai/api/ran/2106.14616.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.14616.svg)](https://syntology.ai/paper/2106.14616)

Connect an agent — have() is free.