SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.03391 · ICLR · 2025

Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons

Shahaf Bassan, Ron Eliav, Shlomit Gur

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 2 have no contract verdict; 1 failure 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/2502.03391.json · badge: /api/ran/2502.03391.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
IBM/SAX canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
create_word_frequency_dictionary Ran
ran on a synthesized input
IBM/SAX/AIFin/demo_pages.py
code served (permissive licence) · get_code("86ce1492cce449f9")
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 pandas as pd
from collections import Counter

# Create a small DataFrame with text data
df = pd.DataFrame({
    'text_column': [
        'apple, banana, cherry',
        'apple, date, elderberry',
        'banana, fig, grape',
        None,  # Test pd.notna() handling
        'apple, banana'
    ]
})

# Define the arguments for the function
ARGS = {
    'df': df,
    'column_name': 'text_column'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — 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
score_to_label Ran
ran on a synthesized input
IBM/SAX/AIFin/demo_pages.py
code served (permissive licence) · get_code("aba2e31d52d8419f")
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 torch
import numpy as np

# score_to_label takes a single parameter 'score' which should be a numeric value
# The function compares it against various thresholds and returns a string label

# Test with a score value that will trigger one of the conditions
score = 0.85  # This will return 'Very Positive' (>= 0.7 and < 0.9)

ARGS = {
    'score': score
}
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 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
wrapper_method Ran
ran; our contract draft was wrong, not the code
IBM/SAX/ICLR25/attack_files/attack_file.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from nilspwalter/the-uncanny-valley, is pointer only (licence: NOASSERTION) · get_code("9b45cb80d93fe980")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from nilspwalter/the-uncanny-valley, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
wrapper_method 6 other papers
5 dated earlier, 1 later
2310.18274 (2023-10)
LipSim: A Provably Robust Perceptual Similarity Metric
2401.16352 (2024-01)
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
2402.02309 (2024-02)
Jailbreaking Attack against Multimodal Large Language Model
and 3 more not named here

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

Minimal sufficient reasons represent a prevalent form of explanation -the smallest subset of input features which, when held constant at their corresponding values, ensure that the prediction remains unchanged. Previous post-hoc methods attempt to obtain such explanations but face two main limitations: (i) Obtaining these subsets poses a computational challenge, leading most scalable methods to converge towards suboptimal, less meaningful subsets; (ii) These methods heavily rely on sampling out-of-distribution input assignments, potentially resulting in counterintuitive behaviors. To tackle these limitations, we propose in this work a self-supervised training approach, which we term sufficient subset training (SST). Using SST, we train models to generate concise sufficient reasons for their predictions as an integral part of their output. Our results indicate that our framework produces succinct and faithful subsets substantially more efficiently than competing post-hoc methods, while maintaining comparable predictive performance. Code is available at: https://github.com/IBM/SAX/tree/main/ICLR25.

For agents

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

get_harvested_code_for_paper("2502.03391")
get_code_for_paper("2502.03391")
have("2502.03391")

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

curl https://syntology.ai/api/ran/2502.03391.json

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

[![Syntology run record](https://syntology.ai/api/ran/2502.03391.svg)](https://syntology.ai/paper/2502.03391)

Connect an agent — have() is free.