SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.02430 · NeurIPS · 2023

Automated Classification of Model Errors on ImageNet

Marc Fischer, Martin Vechev, Mark Müller, Momchil Peychev, Fine Grained

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2401.02430.json · badge: /api/ran/2401.02430.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
eth-sri/automated-error-analysis canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_mla Ran
ran, honoured the contract we drafted
eth-sri/automated-error-analysis/src/evaluation.py
code served (permissive licence) · get_code("5925897b03dfbdfc")
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) and returned float, 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 pandas as pd
from enum import Enum

class ErrorClsTypes(str, Enum):
    correct = 'correct'
    correct_but_wrong_label = 'correct (top-1=target) but target is wrong/unclear'
    empty_multi_label_correct = 'empty (problematic) multi-label, correct (top-1=target)'
    empty_multi_label_correct_collapsed_mapping = 'empty (problematic) multi-label, correct wrt collapsed mappings'
    empty_multi_label_wrong = 'empty (problematic) multi label, wrong (top-1 != target)'
    OOV_similar_to_target = 'fine-grained/OOV, same superset as target, but target not in multi-label'
    common_co_occurrences_with_target = 'common co-occurrences with target (spurious correlations), but target not in multi-label'
    correct_collapsed_mapping = 'correct (collapsed mapping)'
    correct_multi_label = 'correct wrt multi label (ambiguous/multi-object)'
    same_superclass = 'same superclass (fine-grained)'
    OOV_detected_by_clip = 'potentially OOV, detected by CLIP'
    common_co_occurrences = 'common co-occurrences (spurious correlations)'
    non_prototypical = 'non-prototypical (DoughBagel)'
    not_classified = 'error not classified'

# Create a sample DataFrame with required columns
data = {
    'target': ['class_a', 'class_b', 'class_a', 'class_c'],
    'error_types': [
        [ErrorClsTypes.correct],
        [ErrorClsTypes.same_superclass],
        [ErrorClsTypes.correct_multi_label],
        [ErrorClsTypes.non_prototypical]
    ]
}

df = pd.DataFrame(data)

ARGS = {
    'df': df,
    'method': 'no_error'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

While the ImageNet dataset has been driving computer vision research over the past decade, significant label noise and ambiguity have made top-1 accuracy an insufficient measure of further progress. To address this, new label-sets and evaluation protocols have been proposed for ImageNet showing that state-of-the-art models already achieve over 95% accuracy and shifting the focus on investigating why the remaining errors persist. Recent work in this direction employed a panel of experts to manually categorize all remaining classification errors for two selected models. However, this process is time-consuming, prone to inconsistencies, and requires trained experts, making it unsuitable for regular model evaluation thus limiting its utility. To overcome these limitations, we propose the first automated error classification framework, a valuable tool to study how modeling choices affect error distributions. We use our framework to comprehensively evaluate the error distribution of over 900 models. Perhaps surprisingly, we find that across model architectures, scales, and pre-training corpora, top-1 accuracy is a strong predictor for the portion of all error types. In particular, we observe that the portion of severe errors drops significantly with top-1 accuracy indicating that, while it underreports a model's true performance, it remains a valuable performance metric. We release all our code at https://github.com/eth-sri/automated-error-analysis.

For agents

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

get_harvested_code_for_paper("2401.02430")
get_code_for_paper("2401.02430")
have("2401.02430")

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

curl https://syntology.ai/api/ran/2401.02430.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.02430.svg)](https://syntology.ai/paper/2401.02430)

Connect an agent — have() is free.