SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.04373 · NeurIPS · 2020

AutoCLINT: The Winning Method in AutoCV Challenge 2019

Woonhyuk Baek, Kakao Brain, Ildoo Kim, Sungwoong Kim, Sungbin Lim

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 0 have no contract verdict; 3 failures 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/2005.04373.json · badge: /api/ran/2005.04373.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
kakaobrain/autoclint canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
ShearX Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kakaobrain/autoclint/skeleton/data/augmentations.py
code served (permissive licence) · get_code("8930514ccb00f8c4")
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 Image. 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 random
import PIL
import PIL.Image
import PIL.ImageOps
import PIL.ImageEnhance
import PIL.ImageDraw
import numpy as np
from collections import defaultdict

# Create a small PIL Image object
# ShearX expects an image with a .transform() method and .size attribute
img = PIL.Image.new('RGB', (100, 80))

# v parameter: a float between -0.3 and 0.3
v = 0.15

ARGS = {
    'img': img,
    'v': v
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
ShearY Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kakaobrain/autoclint/skeleton/data/augmentations.py
code served (permissive licence) · get_code("508600c3fb3442f9")
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 Image. 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 random
import PIL
import PIL.Image
import PIL.ImageOps
import PIL.ImageEnhance
import PIL.ImageDraw
import numpy as np
from collections import defaultdict

# Create a small PIL Image object
# The function calls img.size and img.transform()
img = PIL.Image.new('RGB', (100, 80))

# Create valid arguments for ShearY
ARGS = {
    'img': img,
    'v': 0.15
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
TranslateX Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
kakaobrain/autoclint/skeleton/data/augmentations.py
code served (permissive licence) · get_code("723d66c34d290b95")
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 Image. 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 random
import PIL
import PIL.Image
import PIL.ImageOps
import PIL.ImageEnhance
import PIL.ImageDraw
import numpy as np
from collections import defaultdict

# Create a simple PIL Image for testing
# The function uses img.size[0] and img.transform()
img = PIL.Image.new('RGB', (100, 80), color='red')

# v must be in range [-0.45, 0.45]
v = 0.3

ARGS = {
    'img': img,
    'v': v
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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
ShearX 8 other papers
3 dated earlier, 5 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2001.06001 (2020-01)
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
and 5 more not named here
ShearY 8 other papers
3 dated earlier, 5 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2001.06001 (2020-01)
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
and 5 more not named here
TranslateX 8 other papers
3 dated earlier, 5 later · 1 only as an assembly brick
1904.12848 (2019-04)
Unsupervised Data Augmentation for Consistency Training
1905.00397 (2019-05)
Fast AutoAugment
2001.06001 (2020-01)
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
and 5 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

NeurIPS 2019 AutoDL challenge is a series of six automated machine learning competitions. Particularly, Au-toCV challenges mainly focused on classification tasks on visual domain. In this paper, we introduce the winning method in the competition, AutoCLINT (Computationally LIght Network Training). The proposed method implements an autonomous training strategy, including efficient code optimization, and applies an automated data augmentation to achieve the fast adaptation of pretrained networks. We implement a light version of Fast AutoAugment [12] to search for data augmentation policies efficiently for the arbitrarily given image domains. We also empirically analyze the components of the proposed method and provide ablation studies focusing on AutoCV datasets. Our code 1 is open to the public, who wants to apply the proposed method.

For agents

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

get_harvested_code_for_paper("2005.04373")
get_code_for_paper("2005.04373")
have("2005.04373")

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

curl https://syntology.ai/api/ran/2005.04373.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.04373.svg)](https://syntology.ai/paper/2005.04373)

Connect an agent — have() is free.