SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.00411 · 2021

Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features

arXiv · PDF · Open in the Atlas

Code that ran

5 of 12 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 7 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/2104.00411.json · badge: /api/ran/2104.00411.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
CAMP-eXplain-AI/CheXplain-IBA canonical (classifier label)
classifier basis: census
5 ran · 7 no recorded run
FunctionStatusWhere it lives
ifnone Ran
ran, honoured the contract we drafted
CAMP-eXplain-AI/CheXplain-IBA/IBA/IBA/utils.py
code served (permissive licence) · get_code("6f4763ec77290638")
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 torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    "a": None,
    "b": 42
}
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 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
insert_into_sequential Ran
ran; our contract draft was wrong, not the code
CAMP-eXplain-AI/CheXplain-IBA/IBA/IBA/pytorch.py
code served (permissive licence) · get_code("2051b0d0f5da07d3")
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 Sequential. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple sequential model with a few layers
sequential = nn.Sequential(
    nn.Linear(4, 3),
    nn.ReLU(),
    nn.Linear(3, 2)
)

# Create a layer to insert
layer = nn.Dropout(0.5)

# Position to insert at
idx = 1

ARGS = {
    "sequential": sequential,
    "layer": layer,
    "idx": idx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
label_exists Ran
ran, honoured the contract we drafted
CAMP-eXplain-AI/CheXplain-IBA/model/csv_processing.py
code served (permissive licence) · get_code("b1733ea4fdc65085")
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 torch
import numpy as np

torch.manual_seed(0)

# The function checks if 'label' is in 'finding'
# This works with strings, lists, dicts, sets, or any container that supports 'in' operator
# We'll test with a simple case

label = "finding_1"
finding = "This is a finding_1 report"

ARGS = {
    "label": label,
    "finding": finding
}
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 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
tensor_to_np_img Ran
ran; our contract draft was wrong, not the code
CAMP-eXplain-AI/CheXplain-IBA/IBA/IBA/pytorch.py
code served (permissive licence) · get_code("62b5772d8033fdab")
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, 5, 3) 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)

# The function takes img_t as input, which should be a torch tensor of shape (c, h, w)
# where c is channels, h is height, w is width
# The function expects a tensor with 3 channels (RGB), and applies normalization transforms

img_t = torch.randn(3, 4, 5)  # (channels=3, height=4, width=5)

ARGS = {
    "img_t": img_t
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — 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, 5, 3) — shape (4, 5, 3) 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
to_unit_interval Ran
ran, honoured the contract we drafted
CAMP-eXplain-AI/CheXplain-IBA/IBA/IBA/utils.py
code served (permissive licence) · get_code("e5e556749746630d")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# The function takes a single argument x and calls:
# - x.min() 
# - x.max()
# - arithmetic operations (subtraction, division)
# This means x should be a torch tensor with numeric values

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
calc_cam Not yet run
unverified (harvested, no recorded run)
CAMP-eXplain-AI/CheXplain-IBA/model/visualize_prediction.py
code served (permissive licence) · get_code("807696ec1d5ddd58")
How it ran

no invocation recorded.

eval_localization Not yet run
unverified (harvested, no recorded run)
CAMP-eXplain-AI/CheXplain-IBA/model/merged_visualize_prediction.py
code served (permissive licence) · get_code("712a59ede55f7b3c")
How it ran

no invocation recorded.

evaluate_mae Not yet run
unverified (harvested, no recorded run)
CAMP-eXplain-AI/CheXplain-IBA/model/eval_model.py
code served (permissive licence) · get_code("96d8c8ef29da58f9")
How it ran

no invocation recorded.

load_monkeys Not yet run
unverified (harvested, no recorded run)
CAMP-eXplain-AI/CheXplain-IBA/IBA/IBA/utils.py
code served (permissive licence) · get_code("9a306d4046aceb10")
How it ran

no invocation recorded.

make_pred_multilabel Not yet run
unverified (harvested, no recorded run)
CAMP-eXplain-AI/CheXplain-IBA/model/eval_model.py
code served (permissive licence) · get_code("372442a43ddc5185")
How it ran

no invocation recorded.

pos_neg_weights_in_batch Not yet run
unverified (harvested, no recorded run)
CAMP-eXplain-AI/CheXplain-IBA/model/model.py
code served (permissive licence) · get_code("abf44b5f5898d4a7")
How it ran

no invocation recorded.

show_next Not yet run
unverified (harvested, no recorded run)
CAMP-eXplain-AI/CheXplain-IBA/model/merged_visualize_prediction.py
code served (permissive licence) · get_code("5103f9950a73e262")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 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.

FunctionAlso present inEarliest-datedOthers named
ifnone 2 other papers
2 dated earlier
1806.07421 (2018-06)
RISE: Randomized Input Sampling for Explanation of Black-box Models
2001.00396 (2020-01)
Restricting the Flow: Information Bottlenecks for Attribution
insert_into_sequential 1 other paper
1 dated earlier
1806.07421 (2018-06)
RISE: Randomized Input Sampling for Explanation of Black-box Models
load_monkeys 1 other paper
1 dated earlier
1806.07421 (2018-06)
RISE: Randomized Input Sampling for Explanation of Black-box Models
tensor_to_np_img 1 other paper
1 dated earlier
1806.07421 (2018-06)
RISE: Randomized Input Sampling for Explanation of Black-box Models
to_unit_interval 1 other paper
1 dated earlier
1806.07421 (2018-06)
RISE: Randomized Input Sampling for Explanation of Black-box Models

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

Neural networks have demonstrated remarkable performance in classification and regression tasks on chest X-rays. In order to establish trust in the clinical routine, the networks' prediction mechanism needs to be interpretable. One principal approach to interpretation is feature attribution. Feature attribution methods identify the importance of input features for the output prediction. Building on Information Bottleneck Attribution (IBA) method, for each prediction we identify the chest X-ray regions that have high mutual information with the network's output. Original IBA identifies input regions that have sufficient predictive information. We propose Inverse IBA to identify all informative regions. Thus all predictive cues for pathologies are highlighted on the X-rays, a desirable property for chest X-ray diagnosis. Moreover, we propose Regression IBA for explaining regression models. Using Regression IBA we observe that a model trained on cumulative severity score labels implicitly learns the severity of different X-ray regions. Finally, we propose Multi-layer IBA to generate higher resolution and more detailed attribution/saliency maps. We evaluate our methods using both human-centric (ground-truth-based) interpretability metrics, and human-independent feature importance metrics on NIH Chest X-ray8 and BrixIA datasets. The Code is publicly available.

For agents

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

get_harvested_code_for_paper("2104.00411")
get_code_for_paper("2104.00411")
have("2104.00411")

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

curl https://syntology.ai/api/ran/2104.00411.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.00411.svg)](https://syntology.ai/paper/2104.00411)

Connect an agent — have() is free.