SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.01440 · NeurIPS · 2020

Uncertainty-Aware Multi-Modal Ensembling for Severity Prediction of Alzheimer's Dementia

Utkarsh Sarawgi, Wazeer Zulfikar, Rishab Khincha, Pattie Maes, © Sarawgi

arXiv · PDF · Open in the Atlas

Code that ran

6 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 6 have no contract verdict; 0 failures of our instrument; 2 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/2010.01440.json · badge: /api/ran/2010.01440.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
wazeerzulfikar/alzheimers-dementia canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
clean_file Ran
ran on a synthesized input
wazeerzulfikar/alzheimers-dementia/utils.py
code served (permissive licence) · get_code("12002f68f6fc8d41")
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 str. 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 re

def clean_file(lines):
    return re.sub('[0-9]+[_][0-9]+', '', lines.replace('*INV:', '').replace('*PAR:', '')).strip().replace('\x15', '').replace('\n', '').replace('\t', ' ').replace('[+ ', '[+').replace('[* ', '[*').replace('[: ', '[:').replace(' .', '').replace("'s", '').replace(' ?', '').replace(' !', '').replace(' ]', ']').lower()

# The function takes a single parameter 'lines' which should be a string
# It performs various string operations including regex substitution and replacements
sample_lines = "Some text with *INV: and *PAR: markers, 123_456 pattern, and [+ brackets] with 's apostrophes?"

ARGS = {
    'lines': sample_lines
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
extra_clean Ran
ran on a synthesized input
wazeerzulfikar/alzheimers-dementia/utils.py
code served (permissive licence) · get_code("90e2314123cfe944")
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 str. 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 re

def clean_file(lines):
    return re.sub('[0-9]+[_][0-9]+', '', lines.replace('*INV:', '').replace('*PAR:', '')).strip().replace('\x15', '').replace('\n', '').replace('\t', ' ').replace('[+ ', '[+').replace('[* ', '[*').replace('[: ', '[:').replace(' .', '').replace("'s", '').replace(' ?', '').replace(' !', '').replace(' ]', ']').lower()

def extra_clean(lines):
    lines = clean_file(lines)
    lines = lines.replace('[+exc]', '')
    lines = lines.replace('[+gram]', '')
    lines = lines.replace('[+es]', '')
    lines = re.sub('[&][=]*[a-z]+', '', lines)
    lines = re.sub('\\[[*][a-z]:[a-z][-|a-z]*\\]', '', lines)
    lines = re.sub('[^A-Za-z0-9\\s_]+', '', lines)
    lines = re.sub('[_]', ' ', lines)
    return lines

# Construct test input for extra_clean function
test_input = (
    "*INV: hello world *PAR: test 123_456 [+exc] [+gram] [+es] "
    "&=something [*a:b-c] special! chars? [test] "
    "apostrophe's test_underscore text\x15\n\t"
)

ARGS = {
    "lines": test_input
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_individual_accuracy Ran
ran on a synthesized input
wazeerzulfikar/alzheimers-dementia/evaluator.py
code served (permissive licence) · get_code("9b08f1fb35bd4a22")
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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Build a small classification model
class SimpleClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 2)
    
    def predict(self, x):
        with torch.no_grad():
            if isinstance(x, torch.Tensor):
                x = x.numpy()
            x = torch.tensor(x, dtype=torch.float32)
            output = self.fc(x)
            return output.numpy()

# Build a small regression model
class SimpleRegressor(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 1)
    
    def forward(self, x):
        if isinstance(x, np.ndarray):
            x = torch.tensor(x, dtype=torch.float32)
        return self.fc(x)
    
    def predict(self, x):
        with torch.no_grad():
            if isinstance(x, torch.Tensor):
                x = x.numpy()
            x = torch.tensor(x, dtype=torch.float32)
            output = self.fc(x)
            return output.numpy()

# Config class for regression with uncertainty flag
class Config:
    def __init__(self, uncertainty=False):
        self.uncertainty = uncertainty

# Classification setup
classification_model = SimpleClassifier()
classification_feature = np.random.randn(2, 4).astype(np.float32)
classification_y = np.array([[1, 0], [0, 1]])  # One-hot encoded labels
classification_config = Config(uncertainty=False)

# Regression setup
regression_model = SimpleRegressor()
regression_feature = np.random.randn(2, 4).astype(np.float32)
regression_y = np.array([1.5, 2.5])  # Scalar targets
regression_config = Config(uncertainty=False)

ARGS = {
    'task': 'classification',
    'model': classification_model,
    'feature': classification_feature,
    'y': classification_y,
    'config': classification_config,
    'fold': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — 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
get_intervention_features Ran
ran on a synthesized input
wazeerzulfikar/alzheimers-dementia/dataset.py
code served (permissive licence) · get_code("963190a4d52788c7")
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 int; 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 tempfile
import os

# Create a temporary transcription file with sample content
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
transcription_content = """INV: Hello, how are you?
PAR: I'm doing well, thank you.
INV: That's great to hear.
PAR: Yes, everything is fine.
INV: Good to know.
PAR: Thank you for asking."""

temp_file.write(transcription_content)
temp_file.close()

ARGS = {
    'transcription_filename': temp_file.name,
    'max_length': 40
}
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 2, dtype family int — 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
get_spectogram_features Ran
ran on a synthesized input
wazeerzulfikar/alzheimers-dementia/dataset.py
code served (permissive licence) · get_code("518fe34f68d75fcc")
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 float, shape (4, 3, 1) 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
import tempfile
import os

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

# Create a small mel-spectrogram file
# The function expects a 2D numpy array that will be expanded to 3D
mel_data = np.random.randn(4, 3).astype(np.float32)
spectogram_filename = os.path.join(temp_dir, "test_spectrogram.npy")
np.save(spectogram_filename, mel_data)

ARGS = {
    "spectogram_filename": spectogram_filename
}
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 float, shape (4, 3, 1) — shape (4, 3, 1) 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
words_count Ran
ran on a synthesized input
wazeerzulfikar/alzheimers-dementia/utils.py
code served (permissive licence) · get_code("e8e91f94e6d93604")
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 int, ndim 0, dtype family int, 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 re

def clean_file(lines):
    return re.sub('[0-9]+[_][0-9]+', '', lines.replace('*INV:', '').replace('*PAR:', '')).strip().replace('\x15', '').replace('\n', '').replace('\t', ' ').replace('[+ ', '[+').replace('[* ', '[*').replace('[: ', '[:').replace(' .', '').replace("'s", '').replace(' ?', '').replace(' !', '').replace(' ]', ']').lower()

def extra_clean(lines):
    lines = clean_file(lines)
    lines = lines.replace('[+exc]', '')
    lines = lines.replace('[+gram]', '')
    lines = lines.replace('[+es]', '')
    lines = re.sub('[&][=]*[a-z]+', '', lines)
    lines = re.sub('\\[[*][a-z]:[a-z][-|a-z]*\\]', '', lines)
    lines = re.sub('[^A-Za-z0-9\\s_]+', '', lines)
    lines = re.sub('[_]', ' ', lines)
    return lines

def words_count(content):
    extra_cleaned = extra_clean(content).split(' ')
    return len(extra_cleaned) - extra_cleaned.count('')

# Setup test content
test_content = "Hello world *INV: test *PAR: data 123_456 with [+exc] tags and &equals stuff [*a:b-c] more text"

ARGS = {
    'content': test_content
}
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 int, ndim 0, dtype family int, 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
evaluate Not yet run
unverified (harvested, no recorded run)
wazeerzulfikar/alzheimers-dementia/evaluator.py
code served (permissive licence) · get_code("90a5493ae934738a")
How it ran

no invocation recorded.

get_ensemble_accuracy Not yet run
unverified (harvested, no recorded run)
wazeerzulfikar/alzheimers-dementia/evaluator.py
code served (permissive licence) · get_code("6b391365cbb6b35c")
How it ran

no invocation recorded.

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, 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 8 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

Reliability in Neural Networks (NNs) is crucial in safety-critical applications like healthcare, and uncertainty estimation is a widely researched method to highlight the confidence of NNs in deployment. In this work, we propose an uncertainty-aware boosting technique for multi-modal ensembling to predict Alzheimer's Dementia Severity. The propagation of uncertainty across acoustic, cognitive, and linguistic features produces an ensemble system robust to heteroscedasticity in the data. Weighing the different modalities based on the uncertainty estimates, we experiment on the benchmark ADReSS dataset, a subject-independent and balanced dataset, to show that our method outperforms the state-of-the-art methods while also reducing the overall entropy of the system. The source code is available at https://github.com /wazeerzulfikar/alzheimers-dementia

For agents

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

get_harvested_code_for_paper("2010.01440")
get_code_for_paper("2010.01440")
have("2010.01440")

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

curl https://syntology.ai/api/ran/2010.01440.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.01440.svg)](https://syntology.ai/paper/2010.01440)

Connect an agent — have() is free.