SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.19130 · 2024

Evidential Concept Embedding Models: Towards Reliable Concept Explanations for Skin Disease Diagnosis

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, 1 violated it and 0 have no contract verdict; 5 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/2406.19130.json · badge: /api/ran/2406.19130.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
obiyoag/evi-cem canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_bin_accuracy Ran
ran; our contract draft was wrong, not the code
obiyoag/evi-cem/utils.py
code served (permissive licence) · get_code("f6e2a42cc26a7564")
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 2, 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)

# Create small tensors for the function arguments
# c_pred: binary classification predictions (batch_size x num_classes)
# Shape: (2, 3) - 2 samples, 3 binary classification tasks
c_pred = torch.tensor([[0.8, 0.3, 0.6], [0.2, 0.9, 0.1]], dtype=torch.float32)

# y_pred: probability predictions (batch_size,) or similar
# Shape: (2,) - 2 samples with probability predictions
y_pred = torch.tensor([[0.7], [0.4]], dtype=torch.float32)

# c_true: true binary labels (batch_size x num_classes)
# Shape: (2, 3) - matching c_pred
c_true = torch.tensor([[1, 0, 1], [0, 1, 0]], dtype=torch.float32)

# y_true: true labels (batch_size,)
# Shape: (2,) - matching y_pred
y_true = torch.tensor([1, 0], dtype=torch.float32)

ARGS = {
    "c_pred": c_pred,
    "y_pred": y_pred,
    "c_true": c_true,
    "y_true": y_true,
}
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 tuple, ndim 2, 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
construct_callbacks Ran
ran; our contract draft was wrong, not the code
obiyoag/evi-cem/utils.py
code served (permissive licence) · get_code("ef8dfce510a10995")
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 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 tempfile
import os

# Create a temporary directory for checkpoint saving
temp_dir = tempfile.mkdtemp()

# Define the config dictionary with all required keys
config = {
    'ckpt_saving': True,
    'ckpt_save_dir': temp_dir,
    'ckpt_save_monitor': 'val_auc',
    'ckpt_save_mode': 'max',
    'save_weights_only': True,
}

# Map the function parameter to its argument value
ARGS = {
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pytorch_lightning, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — 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_cav Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
obiyoag/evi-cem/learn_cavs.py
code served (permissive licence) · get_code("287392eae1fafe8c")
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
from sklearn.svm import SVC

# Create small training data
np.random.seed(0)
X_train = np.random.randn(10, 5)  # 10 samples, 5 features
y_train = np.array([0, 1, 0, 1, 0, 1, 0, 1, 0, 1])  # binary labels

# Define the arguments dictionary
ARGS = {
    'X_train': X_train,
    'y_train': y_train,
    'C': 1.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
get_embeddings Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
obiyoag/evi-cem/learn_cavs.py
code served (permissive licence) · get_code("6cd52c2775a843cb")
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 2, dtype family float, shape (4, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Create a minimal model that takes an image and outputs embeddings
class EmbeddingModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(3, 4)
    
    def forward(self, x):
        # x shape: (batch_size, 3)
        # output shape: (batch_size, 4)
        return self.fc(x)

# Create a minimal data loader
# The function expects tuples with 5 elements: (image, _, _, _, _)
# Only image is used, the rest are ignored
loader = [
    (torch.randn(2, 3), None, None, None, None),  # batch of 2 images, 3 channels
    (torch.randn(2, 3), None, None, None, None),  # batch of 2 images, 3 channels
]

# Create the model
model = EmbeddingModel()

# Define arguments
ARGS = {
    "loader": loader,
    "model": model,
}
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 ndarray, ndim 2, dtype family float, shape (4, 4) — shape (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
init_logger Ran
ran, violated the contract we drafted
obiyoag/evi-cem/utils.py
code served (permissive licence) · get_code("ec1838ce50f98f86")
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 bool, 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 numpy as np

torch.manual_seed(0)

config = {
    'logger': 'false',
    'project_name': 'test_project',
    'exp_name': 'test_experiment'
}

ARGS = {
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pytorch_lightning, torch, wandb — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
learn_concept_bank Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
obiyoag/evi-cem/learn_cavs.py
code served (permissive licence) · get_code("6a9176a05e17c1cc")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import numpy as np

torch.manual_seed(0)

# Create a minimal backbone model that outputs embeddings
class SimpleBackbone(nn.Module):
    def __init__(self, embedding_dim=4):
        super().__init__()
        self.linear = nn.Linear(3, embedding_dim)
    
    def forward(self, x):
        # x shape: (batch_size, 3)
        # output shape: (batch_size, embedding_dim)
        return self.linear(x)

# Create minimal data loaders
# Each loader yields tuples of (image, _, _, _, _)
# The function unpacks 5 values and uses only the first (image)
def create_loader(num_samples, input_dim=3):
    """Create a simple loader that yields (image, dummy, dummy, dummy, dummy) tuples"""
    data = []
    for i in range(num_samples):
        image = torch.randn(2, input_dim)  # batch_size=2, input_dim=3
        data.append((image, None, None, None, None))
    return data

# Create positive and negative loaders
pos_loader = create_loader(num_samples=2, input_dim=3)
neg_loader = create_loader(num_samples=2, input_dim=3)

# Create backbone model
backbone = SimpleBackbone(embedding_dim=4)

# Regularization parameter
reg = 1.0

ARGS = {
    'pos_loader': pos_loader,
    'neg_loader': neg_loader,
    'backbone': backbone,
    'reg': reg,
}
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 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

Due to the high stakes in medical decision-making, there is a compelling demand for interpretable deep learning methods in medical image analysis. Concept Bottleneck Models (CBM) have emerged as an active interpretable framework incorporating human-interpretable concepts into decision-making. However, their concept predictions may lack reliability when applied to clinical diagnosis, impeding concept explanations' quality. To address this, we propose an evidential Concept Embedding Model (evi-CEM), which employs evidential learning to model the concept uncertainty. Additionally, we offer to leverage the concept uncertainty to rectify concept misalignments that arise when training CBMs using vision-language models without complete concept supervision. With the proposed methods, we can enhance concept explanations' reliability for both supervised and label-efficient settings. Furthermore, we introduce concept uncertainty for effective test-time intervention. Our evaluation demonstrates that evi-CEM achieves superior performance in terms of concept prediction, and the proposed concept rectification effectively mitigates concept misalignments for label-efficient training. Our code is available at https://github.com/obiyoag/evi-CEM.

For agents

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

get_harvested_code_for_paper("2406.19130")
get_code_for_paper("2406.19130")
have("2406.19130")

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

curl https://syntology.ai/api/ran/2406.19130.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.19130.svg)](https://syntology.ai/paper/2406.19130)

Connect an agent — have() is free.