SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.00163 · 2026

Deep Learning Pose Estimation for Multi-Label Phenotyping of Co-Occurring Hyperkinetic Movement Disorders

Ur Rehman, Xavier Vasques, Laura Cif, Diane Demailly, Gabriella Horvàth, Juan Dario, Ortigoza Escobar, Nathalie Dorison, Mayté Castro Jiménez, Cécile Hubsch, Thomas Wirth, Gun-Marie Hariz, and 8 more

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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 0 have no contract verdict; 6 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2602.00163.json · badge: /api/ran/2602.00163.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
xaviervasques/CODY canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
extract_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xaviervasques/CODY/combined/combined_hmd.py
code served (permissive licence) · get_code("ebc4c249b3ca97c0")
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 numpy as np
import pandas as pd
import scipy.stats as stats
from scipy.fft import fft

# Create a small sample DataFrame with a group structure
np.random.seed(42)
signal_data = np.random.randn(20)
group_df = pd.DataFrame({
    'signal_col_1': signal_data,
    'signal_col_2': signal_data + np.random.randn(20) * 0.1,
    'signal_col_3': signal_data * 2 + np.random.randn(20) * 0.2,
})

ARGS = {
    'group': group_df,
    'cols': ['signal_col_1', 'signal_col_2'],
    'fps': 30.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, scipy — 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
extract_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xaviervasques/CODY/patients/patient.py
code served (permissive licence) · get_code("ca0ddaa851a9ba96")
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 numpy as np
import pandas as pd
import scipy.stats as stats
from scipy.fft import fft

# Create a small DataFrame with numeric columns
np.random.seed(0)
signal_data = np.random.randn(20)
df = pd.DataFrame({
    'x': signal_data,
    'y': signal_data + np.random.randn(20) * 0.1,
    'z': signal_data * 2
})

# Create a group (simulating a pandas GroupBy object)
# We'll just use the full dataframe as a simple stand-in
group = df

# Define columns to process
cols = ['x', 'y']

ARGS = {
    'group': group,
    'cols': cols
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, scipy — 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
extract_features Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xaviervasques/CODY/tasks/task.py
code served (permissive licence) · get_code("416001470e98cbb9")
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 numpy as np
import pandas as pd
import scipy.stats as stats
from scipy.fft import fft

# Create a small DataFrame with numeric data
np.random.seed(42)
n_rows = 20
group = pd.DataFrame({
    'signal_x': np.random.randn(n_rows),
    'signal_y': np.random.randn(n_rows),
    'signal_z': np.random.randn(n_rows)
})

cols = ['signal_x', 'signal_y']

ARGS = {
    'group': group,
    'cols': cols
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, scipy — 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
higuchi_fd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xaviervasques/CODY/combined/combined_hmd.py
code served (permissive licence) · get_code("af17e6b5204fe3b0")
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 float, 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

# The function higuchi_fd computes the Higuchi fractal dimension of a signal.
# It takes:
# - signal: a sequence (list, array, etc.) of numeric values
# - kmax: maximum k value for the algorithm (default 5)

# Construct a simple signal - a small array with enough samples
signal = np.array([1.0, 1.5, 2.1, 2.3, 2.8, 3.2, 3.5, 4.1, 4.6, 5.2], dtype=float)

# kmax should be less than len(signal) - 1 for meaningful results
kmax = 5

ARGS = {
    "signal": signal,
    "kmax": kmax,
}
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 float, 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
permutation_entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xaviervasques/CODY/combined/combined_hmd.py
code served (permissive licence) · get_code("b59ea2ff4da1a6ab")
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 float, 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

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

# Create a simple signal as a numpy array
signal = np.array([1.2, 2.3, 1.1, 3.4, 2.5, 1.8, 3.2, 2.9, 1.5, 2.1])

# Define arguments for permutation_entropy
ARGS = {
    "signal": signal,
    "order": 3,
    "delay": 1
}
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 float, 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
permutation_entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xaviervasques/CODY/patients/patient.py
code served (permissive licence) · get_code("85caf36ff4afa959")
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; 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

np.random.seed(0)

# Create a simple signal (1D array of floats)
signal = np.array([1.2, 3.5, 2.1, 4.8, 1.9, 3.2, 2.7, 4.1, 1.5, 3.8], dtype=np.float64)

ARGS = {
    'signal': signal,
    'order': 3,
    'delay': 1
}
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 — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
higuchi_fd Not yet run
unverified (harvested, no recorded run)
xaviervasques/CODY/patients/patient.py
code served (permissive licence) · get_code("7b780e51dcacc0ea")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

A single-centre, exploratory proof-of-concept study using a pose-based hybrid pipeline combining deep learning pose estimation with feature-engineered supervised classification.

For agents

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

get_harvested_code_for_paper("2602.00163")
get_code_for_paper("2602.00163")
have("2602.00163")

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

curl https://syntology.ai/api/ran/2602.00163.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.00163.svg)](https://syntology.ai/paper/2602.00163)

Connect an agent — have() is free.