SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.13027 · 2021

AutoMix: Unveiling the Power of Mixup for Stronger Classifiers

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 0 have no contract verdict; 4 failures of our instrument; 2 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/2103.13027.json · badge: /api/ran/2103.13027.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
Westlake-AI/AutoMix canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
zeyuanyin/tiny-imagenet community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zeyuanyin/tiny-imagenet/classification/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from talalwasim/textguidedresilience, is pointer only (licence: NONE) · get_code("0d95e28fac98427f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from talalwasim/textguidedresilience, and GitHub detected no licence in that repository 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.

find_classes Ran
ran; our contract draft was wrong, not the code
zeyuanyin/tiny-imagenet/classification/tiny_imagenet_dataset.py
code served (permissive licence) · get_code("403277d0bfbb477b")
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 tuple. 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 tempfile
import os

# Create a temporary file with class names
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("cat\n")
temp_file.write("dog\n")
temp_file.write("bird\n")
temp_file.close()

ARGS = {
    "class_file": temp_file.name
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
make_dataset Ran
ran; our contract draft was wrong, not the code
zeyuanyin/tiny-imagenet/classification/tiny_imagenet_dataset.py
code served (permissive licence) · get_code("5ded0879a886f3c4")
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 list, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import tempfile
import shutil

# Create a temporary directory structure that mimics the expected dataset layout
temp_root = tempfile.mkdtemp()
base_folder = "tiny_imagenet"
base_path = os.path.join(temp_root, base_folder)
os.makedirs(base_path)

# Create train directory structure
train_dir = os.path.join(base_path, "train")
os.makedirs(train_dir)

# Create two dummy classes with images subdirectories
for cls_name in ["class_a", "class_b"]:
    cls_dir = os.path.join(train_dir, cls_name)
    os.makedirs(cls_dir)
    imgs_dir = os.path.join(cls_dir, "images")
    os.makedirs(imgs_dir)
    # Create dummy image files
    for i in range(2):
        img_path = os.path.join(imgs_dir, f"img_{i}.jpg")
        with open(img_path, "w") as f:
            f.write("dummy")

# Create val directory structure
val_dir = os.path.join(base_path, "val")
os.makedirs(val_dir)
val_imgs_dir = os.path.join(val_dir, "images")
os.makedirs(val_imgs_dir)

# Create dummy validation images
for i in range(2):
    img_path = os.path.join(val_imgs_dir, f"val_img_{i}.jpg")
    with open(img_path, "w") as f:
        f.write("dummy")

# Create val_annotations.txt
val_annotations_path = os.path.join(val_dir, "val_annotations.txt")
with open(val_annotations_path, "w") as f:
    f.write("val_img_0.jpg\tclass_a\n")
    f.write("val_img_1.jpg\tclass_b\n")

# Define class_to_idx mapping
class_to_idx = {
    "class_a": 0,
    "class_b": 1
}

ARGS = {
    "root": temp_root,
    "base_folder": base_folder,
    "dirname": "train",
    "class_to_idx": class_to_idx
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list output has no array shape of its own; none is stated
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
store_model_weights Ran
ran; our contract draft was wrong, not the code
zeyuanyin/tiny-imagenet/classification/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from talalwasim/textguidedresilience, is pointer only (licence: NONE) · get_code("aa2ba35b3854fa14")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from talalwasim/textguidedresilience, and GitHub detected no licence in that repository 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.

average_checkpoints Not yet run
unverified (harvested, no recorded run)
zeyuanyin/tiny-imagenet/classification/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from talalwasim/textguidedresilience, is pointer only (licence: NONE) · get_code("30862aa4330bfa12")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from talalwasim/textguidedresilience, and GitHub detected no licence in that repository 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.

evaluate Not yet run
unverified (harvested, no recorded run)
Westlake-AI/AutoMix/engine.py
code served (permissive licence) · get_code("30d82c52aa52dbd7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 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.

FunctionAlso present inEarliest-datedOthers named
find_classes 7 other papers
7 later
2209.04996 (2022-09)
Switchable Online Knowledge Distillation
2310.00258 (2023-10)
NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
2401.11687 (2024-01)
TIM: An Efficient Temporal Interaction Module for Spiking Transformer
and 4 more not named here
accuracy 5 other papers
5 later
2303.11525 (2023-03)
Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency
2311.14062 (2023-11)
Hardware Resilience Properties of Text-Guided Image Classifiers
2407.04616 (2024-07)
Isomorphic Pruning for Vision Models
and 2 more not named here
make_dataset 3 other papers
3 later
2310.00258 (2023-10)
NAYER: Noisy Layer Data Generation for Efficient and Effective Data-free Knowledge Distillation
2401.11687 (2024-01)
TIM: An Efficient Temporal Interaction Module for Spiking Transformer
2408.01952 (2024-08)
CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization
average_checkpoints 2 other papers
2 later
2311.14062 (2023-11)
Hardware Resilience Properties of Text-Guided Image Classifiers
2409.19840 (2024-09)
Textual Training for the Hassle-Free Removal of Unwanted Visual Data : Case Studies on OOD and Hateful Image Detection
store_model_weights 2 other papers
2 later
2311.14062 (2023-11)
Hardware Resilience Properties of Text-Guided Image Classifiers
2409.19840 (2024-09)
Textual Training for the Hassle-Free Removal of Unwanted Visual Data : Case Studies on OOD and Hateful Image Detection

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

Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency information to match the mixed samples and labels via complex offline optimization. However, there arises a trade-off between precise mixing policies and optimization complexity. To address this challenge, we propose a novel automatic mixup (AutoMix) framework, where the mixup policy is parameterized and serves the ultimate classification goal directly. Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i.e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework. For the generation, a learnable lightweight mixup generator, Mix Block, is designed to generate mixed samples by modeling patch-wise relationships under the direct supervision of the corresponding mixed labels. To prevent the degradation and instability of bi-level optimization, we further introduce a momentum pipeline to train AutoMix in an end-to-end manner. Extensive experiments on nine image benchmarks prove the superiority of AutoMix compared with state-of-the-art in various classification scenarios and downstream tasks.

For agents

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

get_harvested_code_for_paper("2103.13027")
get_code_for_paper("2103.13027")
have("2103.13027")

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

curl https://syntology.ai/api/ran/2103.13027.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.13027.svg)](https://syntology.ai/paper/2103.13027)

Connect an agent — have() is free.