SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.19308 · 2024

Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 failures of our instrument; 5 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/2407.19308.json · badge: /api/ran/2407.19308.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
zood123/comet canonical (classifier label)
classifier basis: census
7 ran · 5 no recorded run
FunctionStatusWhere it lives
CNNBlock Ran
ran; our contract draft was wrong, not the code
zood123/comet/models/ResNetWithGate.py
pointer only (licence: NONE); the stored copy get_code serves, from davidGCR/saliencyMapper, is pointer only (licence: NONE) · get_code("3c3691349aa65f73")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv3x3 Ran
ran; our contract draft was wrong, not the code
zood123/comet/models/ResNetWithGate.py
pointer only (licence: NONE); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

downsample_basic_block Ran
ran; our contract draft was wrong, not the code
zood123/comet/models/ResNetWithGate.py
pointer only (licence: NONE) · get_code("b51274b9d6c9c97a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mixup_criterion Ran
ran; our contract draft was wrong, not the code
zood123/comet/train_module.py
pointer only (licence: NONE); the stored copy get_code serves, from hhi-aml/histobenchmark, is pointer only (licence: NONE) · get_code("97f484048ac03556")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mixup_data Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zood123/comet/train_module.py
pointer only (licence: NONE); the stored copy get_code serves, from winycg/HCGNet, is pointer only (licence: NONE) · get_code("8897714b1e9b6396")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

single_attr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zood123/comet/eval_module.py
pointer only (licence: NONE) · get_code("f6f3611ff2e86ac3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

str2bool Ran
ran, violated the contract we drafted
zood123/comet/evaluation_explain.py
pointer only (licence: NONE) · get_code("f017532fc389cbfe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

bam_real_mask Not yet run
unverified (harvested, no recorded run)
zood123/comet/eval_module.py
pointer only (licence: NONE) · get_code("49373659fb963e78")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

calculate_multiple_iou Not yet run
unverified (harvested, no recorded run)
zood123/comet/evaluation_explain.py
pointer only (licence: NONE) · get_code("625f3275be8f335f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_attributor Not yet run
unverified (harvested, no recorded run)
zood123/comet/attribution_methods.py
pointer only (licence: NONE) · get_code("dc1b0d5a5b0ca8b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

read_bam_mask Not yet run
unverified (harvested, no recorded run)
zood123/comet/eval_module.py
pointer only (licence: NONE) · get_code("0607f975d7f0f087")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

resize_bbox Not yet run
unverified (harvested, no recorded run)
zood123/comet/evaluation_explain.py
pointer only (licence: NONE) · get_code("5c91b1007d1039d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zood123/comet when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. 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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 1 the same month, 3 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.

FunctionAlso present inEarliest-datedOthers named
conv3x3 686 other papers
603 dated earlier, 14 the same month, 52 later, 17 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
str2bool 82 other papers
80 dated earlier, 2 later
1510.03055 (2015-10)
A Diversity-Promoting Objective Function for Neural Conversation Models
1703.06490 (2017-03)
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
1710.10467 (2017-10)
Generalized End-to-End Loss for Speaker Verification
and 79 more not named here
mixup_criterion 14 other papers
13 dated earlier, 1 later
1706.06083 (2017-06)
Towards Deep Learning Models Resistant to Adversarial Attacks
1905.02175 (2019-05)
Adversarial Examples Are Not Bugs, They Are Features
1906.06784 (2019-06)
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
and 11 more not named here
mixup_data 12 other papers
11 dated earlier, 1 same year, order not determinable
1908.09699 (2019-08)
Gated Convolutional Networks with Hybrid Connectivity for Image Classification
2102.13280 (2021-02)
MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
2104.00466 (2021-04)
Improving Calibration for Long-Tailed Recognition
and 9 more not named here
CNNBlock 1 other paper
1 dated earlier
1705.07857 (2017-05)
Real Time Image Saliency for Black Box Classifiers
get_attributor 1 other paper
1 dated earlier
2303.11932 (2023-03)
Studying How to Efficiently and Effectively Guide Models with Explanations

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

As deep vision models' popularity rapidly increases, there is a growing emphasis on explanations for model predictions. The inherently explainable attribution method aims to enhance the understanding of model behavior by identifying the important regions in images that significantly contribute to predictions. It is achieved by cooperatively training a selector (generating an attribution map to identify important features) and a predictor (making predictions using the identified features). Despite many advancements, existing methods suffer from the incompleteness problem, where discriminative features are masked out, and the interlocking problem, where the non-optimized selector initially selects noise, causing the predictor to fit on this noise and perpetuate the cycle. To address these problems, we introduce a new objective that discourages the presence of discriminative features in the masked-out regions thus enhancing the comprehensiveness of feature selection. A pre-trained detector is introduced to detect discriminative features in the masked-out region. If the selector selects noise instead of discriminative features, the detector can observe and break the interlocking situation by penalizing the selector. Extensive experiments show that our model makes accurate predictions with higher accuracy than the regular black-box model, and produces attribution maps with high feature coverage, localization ability, fidelity and robustness. Our code will be available at \href{https://github.com/Zood123/COMET}{https://github.com/Zood123/COMET}.

For agents

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

get_harvested_code_for_paper("2407.19308")
get_code_for_paper("2407.19308")
have("2407.19308")

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

curl https://syntology.ai/api/ran/2407.19308.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.19308.svg)](https://syntology.ai/paper/2407.19308)

Connect an agent — have() is free.