SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.04867 · 2019

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

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; 0 honoured the contract we drafted, 0 violated it and 0 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/1910.04867.json · badge: /api/ran/1910.04867.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
google-research/task_adaptation canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_data_params_from_flags Ran
ran; our contract draft was wrong, not the code
google-research/task_adaptation/task_adaptation/adapt_and_eval.py
code served (permissive licence) · get_code("731698a07fab5fc6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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.

from absl import flags
import sys

# Clear any existing flags to avoid conflicts
if hasattr(flags.FLAGS, '__dict__'):
    for flag_name in list(flags.FLAGS.__dict__['__flags'].keys()):
        delattr(flags.FLAGS, flag_name)
    flags.FLAGS.__dict__['__flags'] = {}
    flags.FLAGS.__dict__['__dict_flags'] = {}

FLAGS = flags.FLAGS

# Define all the flags that the function expects
flags.DEFINE_string('dataset', 'mnist', 'Dataset name')
flags.DEFINE_string('dataset_train_split_name', 'train', 'Train split name')
flags.DEFINE_string('dataset_eval_split_name', 'test', 'Eval split name')
flags.DEFINE_integer('shuffle_buffer_size', 1000, 'Shuffle buffer size')
flags.DEFINE_integer('prefetch', 2, 'Prefetch size')
flags.DEFINE_integer('train_examples', 5000, 'Number of training examples')
flags.DEFINE_integer('batch_size', 32, 'Batch size for training')
flags.DEFINE_integer('batch_size_eval', 64, 'Batch size for evaluation')
flags.DEFINE_string('data_dir', '/tmp/data', 'Data directory')
flags.DEFINE_list('input_range', ['0.0', '1.0'], 'Input range as list of strings')

# Parse flags with a dummy argv to initialize them
FLAGS(sys.argv[:1])

# The function takes a mode parameter
mode = 'adaptation'

ARGS = {'mode': mode}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
absl — 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

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

Representation learning promises to unlock deep learning for the long tail of vision tasks without expensive labelled datasets. Yet, the absence of a unified evaluation for general visual representations hinders progress. Popular protocols are often too constrained (linear classification), limited in diversity (ImageNet, CIFAR, Pascal-VOC), or only weakly related to representation quality (ELBO, reconstruction error). We present the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples. With VTAB, we conduct a large-scale study of many popular publicly-available representation learning algorithms. We carefully control confounders such as architecture and tuning budget. We address questions like: How effective are ImageNet representations beyond standard natural datasets? How do representations trained via generative and discriminative models compare? To what extent can self-supervision replace labels? And, how close are we to general visual representations?

For agents

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

get_harvested_code_for_paper("1910.04867")
get_code_for_paper("1910.04867")
have("1910.04867")

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

curl https://syntology.ai/api/ran/1910.04867.json

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

[![Syntology run record](https://syntology.ai/api/ran/1910.04867.svg)](https://syntology.ai/paper/1910.04867)

Connect an agent — have() is free.