SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.10831 · 2020

CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 6 have no contract verdict; 0 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/2008.10831.json · badge: /api/ran/2008.10831.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
mdv3101/CDeCNet canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
Overlap_percentage Ran
ran on a synthesized input
mdv3101/CDeCNet/postprocessing/2.multiscale_post_map_bbox.py
code served (permissive licence) · get_code("07f02a498db9c6a2")
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 torch
import numpy as np

torch.manual_seed(0)

# The function Overlap_percentage takes 4 parameters:
# l1, r1, l2, r2 - these represent bounding box coordinates
# Each is expected to be indexable with [0] and [1] for x and y coordinates
# l1, r1 define first bounding box (left, top) and (right, bottom)
# l2, r2 define second bounding box (left, top) and (right, bottom)

# Create sample bounding box coordinates
# Format: (x, y) tuples or lists
l1 = [10, 20]      # top-left of box 1
r1 = [50, 80]      # bottom-right of box 1

l2 = [30, 40]      # top-left of box 2
r2 = [70, 100]     # bottom-right of box 2

ARGS = {
    "l1": l1,
    "r1": r1,
    "l2": l2,
    "r2": r2,
}
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 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
Overlap_percentage Ran
ran on a synthesized input
mdv3101/CDeCNet/postprocessing/3.multiscale_post_nms.py
code served (permissive licence) · get_code("ceb224f9eda472d7")
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 torch
import numpy as np

# The function takes 4 parameters: l1, r1, l2, r2
# Each represents a bounding box coordinate pair (x, y)
# l1, r1 define the first bounding box (left and right corners)
# l2, r2 define the second bounding box (left and right corners)

# Create two simple bounding boxes
# Box 1: top-left at (10, 20), bottom-right at (50, 60)
l1 = (10, 20)
r1 = (50, 60)

# Box 2: top-left at (30, 40), bottom-right at (70, 80)
l2 = (30, 40)
r2 = (70, 80)

ARGS = {
    "l1": l1,
    "r1": r1,
    "l2": l2,
    "r2": r2
}
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 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
check_overlap Ran
ran on a synthesized input
mdv3101/CDeCNet/postprocessing/2.multiscale_post_map_bbox.py
code served (permissive licence) · get_code("520baafc22e3305e")
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 torch
import numpy as np

torch.manual_seed(0)

# Construct bounding box dictionaries
# Each bbox is represented as (left_top, right_bottom) where:
# left_top = (x_left, y_top)
# right_bottom = (x_right, y_bottom)

bbox_1 = {
    0: ((10, 20), (50, 60)),
    1: ((100, 100), (200, 200)),
}

bbox_2 = {
    0: ((15, 25), (55, 65)),
    1: ((300, 300), (400, 400)),
}

# Also test the case where bbox_1 is empty
bbox_1_empty = {}

ARGS = {
    "bbox_1": bbox_1,
    "bbox_2": bbox_2,
}
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 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
check_overlap Ran
ran on a synthesized input
mdv3101/CDeCNet/postprocessing/3.multiscale_post_nms.py
code served (permissive licence) · get_code("dcd0fce51b149910")
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

# Analyze the function check_overlap
# Parameters:
# - bbox_1: a bounding box with [0] = left-top point (l1), [1] = right-bottom point (r1)
# - bbox_2: a bounding box with [0] = left-top point (l2), [1] = right-bottom point (r2)
# Each point is accessed as [0] for x-coordinate and [1] for y-coordinate

# Create sample bounding boxes
# Format: [[left, top], [right, bottom]]
# bbox_1: box from (10, 20) to (100, 150)
bbox_1 = [[10, 20], [100, 150]]

# bbox_2: box from (15, 25) to (95, 145) - mostly overlapping with bbox_1
bbox_2 = [[15, 25], [95, 145]]

ARGS = {
    "bbox_1": bbox_1,
    "bbox_2": bbox_2,
}
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
read_file_return_bbox_dict Ran
ran on a synthesized input
mdv3101/CDeCNet/postprocessing/2.multiscale_post_map_bbox.py
code served (permissive licence) · get_code("f3b3ca6fbd1ffba1")
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 file with sample detection data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("table 0.7 10 20 100 150\n")
temp_file.write("person 0.8 5 5 50 100\n")
temp_file.write("table 0.9 200 200 300 350\n")
temp_file.write("table 0.3 400 400 450 500\n")
temp_file.write("table 0.6 600 600 700 750\n")
temp_file.close()

ARGS = {
    "read_text_path": 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 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
read_file_return_bbox_dict Ran
ran on a synthesized input
mdv3101/CDeCNet/postprocessing/3.multiscale_post_nms.py
code served (permissive licence) · get_code("d0a70d88b2e0ea37")
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 file with test data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file_path = temp_file.name

# Write test data to the file
# Format: caption confidence x1 y1 x2 y2
test_data = [
    "cat 0.9 10 20 100 200",
    "dog 0.3 15 25 105 205",  # Below threshold 0.5
    "bird 0.7 30 40 110 210",
    "fish 0.4 5 10 95 190",    # Below threshold 0.5
    "person 0.85 50 60 150 250",
]

for line in test_data:
    temp_file.write(line + '\n')

temp_file.close()

ARGS = {
    'read_text_path': temp_file_path
}
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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Localizing page elements/objects such as tables, figures, equations, etc. is the primary step in extracting information from document images. We propose a novel end-to-end trainable deep network, (CDeC-Net) for detecting tables present in the documents. The proposed network consists of a multistage extension of Mask R-CNN with a dual backbone having deformable convolution for detecting tables varying in scale with high detection accuracy at higher IoU threshold. We empirically evaluate CDeC-Net on all the publicly available benchmark datasets - ICDAR-2013, ICDAR-2017, ICDAR-2019,UNLV, Marmot, PubLayNet, and TableBank - with extensive experiments. Our solution has three important properties: (i) a single trained model CDeC-Net‡ performs well across all the popular benchmark datasets; (ii) we report excellent performances across multiple, including higher, thresholds of IoU; (iii) by following the same protocol of the recent papers for each of the benchmarks, we consistently demonstrate the superior quantitative performance. Our code and models will be publicly released for enabling the reproducibility of the results.

For agents

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

get_harvested_code_for_paper("2008.10831")
get_code_for_paper("2008.10831")
have("2008.10831")

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

curl https://syntology.ai/api/ran/2008.10831.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.10831.svg)](https://syntology.ai/paper/2008.10831)

Connect an agent — have() is free.