SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.02586 · ICML · 2023

Concept-based Explanations for Out-of-Distribution Detectors

Somesh Jha, Jiefeng Chen, Ryan Feng, Atul Prakash, Jihye Choi, Jayaram Raghuram

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 1 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/2203.02586.json · badge: /api/ran/2203.02586.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
jihyechoi77/concepts-for-ood marked official in Papers with Code
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
Weight Ran
ran on a synthesized input · constructed an object; no result was computed
jihyechoi77/concepts-for-ood/concept_model.py
code served (permissive licence) · get_code("6af13855c2f4296e")
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 an instance of its own class, Weight: the run constructed the object and did not call it, so no result was computed. 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 tensorflow as tf
from tensorflow import keras
from tensorflow.keras.layers import Layer

# Define the Weight layer (provided in the problem)
init = keras.initializers.RandomUniform(minval=-0.5, maxval=0.5, seed=None)

class Weight(Layer):
    """Simple Weight class."""

    def __init__(self, dim, normalize=False, **kwargs):
        self.dim = dim
        self.norm = normalize
        super(Weight, self).__init__(**kwargs)

    def build(self, input_shape):
        self.kernel = self.add_weight(name='proj', shape=self.dim, initializer=init, trainable=True)
        super(Weight, self).build(input_shape)

    def call(self, x):
        if self.norm:
            return tf.math.l2_normalize(self.kernel, axis=0)
        else:
            return self.kernel

    def compute_output_shape(self, input_shape):
        return self.dim


# Construct ARGS dictionary with valid arguments for Weight.__init__
ARGS = {
    'dim': (4, 3),
    'normalize': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Weight — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Weight 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
topic_model_new Not yet run
unverified (harvested, no recorded run)
jihyechoi77/concepts-for-ood/concept_model.py
code served (permissive licence) · get_code("c46ffaff16e9e0e4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

Out-of-distribution (OOD) detection plays a crucial role in ensuring the safe deployment of deep neural network (DNN) classifiers. While a myriad of methods have focused on improving the performance of OOD detectors, a critical gap remains in interpreting their decisions. We help bridge this gap by providing explanations for OOD detectors based on learned high-level concepts. We first propose two new metrics for assessing the effectiveness of a particular set of concepts for explaining OOD detectors: 1) detection completeness -which quantifies the sufficiency of concepts for explaining an OOD detector's decisions, and 2) concept separability -which captures the distributional separation between in-distribution and OOD data in the concept space. Based on these metrics, we propose an unsupervised framework for learning a set of concepts that satisfy the desired properties of high detection completeness and concept separability, and demonstrate its effectiveness in providing concept-based explanations for diverse off-the-shelf OOD detectors. We also show how to identify prominent concepts contributing to the detection results, and provide further reasoning about their decisions.

For agents

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

get_harvested_code_for_paper("2203.02586")
get_code_for_paper("2203.02586")
have("2203.02586")

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

curl https://syntology.ai/api/ran/2203.02586.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.02586.svg)](https://syntology.ai/paper/2203.02586)

Connect an agent — have() is free.