SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.09193 · 2020

VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; 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/2001.09193.json · badge: /api/ran/2001.09193.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
anjany/verse canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_dice Ran
ran, honoured the contract we drafted
anjany/verse/utils/eval_utilities.py
code served (permissive licence) · get_code("f046341b1b772210")
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 float64, 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 numpy as np

# Construct valid arguments for compute_dice
# The function takes two array-like boolean inputs and an optional empty_score parameter

# Create two small boolean arrays of identical shape
im1 = np.array([
    [True, False, True, False],
    [False, True, False, True]
], dtype=bool)

im2 = np.array([
    [True, True, False, False],
    [False, True, True, False]
], dtype=bool)

# Define the arguments dictionary
ARGS = {
    'im1': im1,
    'im2': im2,
    'empty_score': 1.0
}
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 float64, 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
get_hits Ran
ran; our contract draft was wrong, not the code
anjany/verse/utils/eval_utilities.py
code served (permissive licence) · get_code("25fd56cb846ea3fc")
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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create sample data for vertebrae centroids
# max_vert_idx represents the maximum number of vertebrae we're dealing with
max_vert_idx = 5

# Create ground truth centroids: shape (max_vert_idx, 3)
# Each row is a 3D coordinate (x, y, z)
# Some vertebrae may be absent (marked with NaN)
cent_list_gt = np.array([
    [10.0, 20.0, 30.0],   # vertebra 1
    [11.0, 21.0, 31.0],   # vertebra 2
    [np.nan, np.nan, np.nan],  # vertebra 3 absent
    [13.0, 23.0, 33.0],   # vertebra 4
    [14.0, 24.0, 34.0],   # vertebra 5
], dtype=np.float32)

# Create predicted centroids: shape (max_vert_idx, 3)
# Some predictions may also be absent (marked with NaN)
# Some predictions are close to ground truth (< 20mm), some are far
cent_list_pred = np.array([
    [10.5, 20.5, 30.5],   # vertebra 1, close to GT (distance ~0.87mm)
    [15.0, 25.0, 35.0],   # vertebra 2, far from GT (distance ~14.14mm)
    [np.nan, np.nan, np.nan],  # vertebra 3 absent
    [13.2, 23.2, 33.2],   # vertebra 4, close to GT (distance ~0.35mm)
    [np.nan, np.nan, np.nan],  # vertebra 5 absent in prediction
], dtype=np.float32)

ARGS = {
    "cent_list_gt": cent_list_gt,
    "cent_list_pred": cent_list_pred,
    "max_vert_idx": max_vert_idx,
}
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 — 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
construct_distance_matrix Not yet run
unverified (harvested, no recorded run)
anjany/verse/utils/eval_utilities.py
code served (permissive licence) · get_code("8a077b466e0d0898")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
compute_dice 1 other paper
1 later
2103.06360 (2021-03)
A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Data
construct_distance_matrix 1 other paper
1 later
2103.06360 (2021-03)
A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Data
get_hits 1 other paper
1 later
2103.06360 (2021-03)
A Computed Tomography Vertebral Segmentation Dataset with Anatomical Variations and Multi-Vendor Scanner Data

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision-support systems for diagnosis, surgery planning, and population-based analysis on spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms towards labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel-level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at different fields-of-view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The content and code concerning VerSe can be accessed at: https://github.com/anjany/verse.

For agents

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

get_harvested_code_for_paper("2001.09193")
get_code_for_paper("2001.09193")
have("2001.09193")

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

curl https://syntology.ai/api/ran/2001.09193.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.09193.svg)](https://syntology.ai/paper/2001.09193)

Connect an agent — have() is free.