SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.02843 · NeurIPS · 2023

Are Vision Transformers More Data Hungry Than Newborn Visual Systems?

Justin Wood, Lalit Pandey, Samantha Wood

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2312.02843.json · badge: /api/ran/2312.02843.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
buildingamind/vit-cot canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
buildingamind/ViT-CoT canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
create_decoder Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
buildingamind/vit-cot/models/common.py
code served (permissive licence) · get_code("8dd8c7db24c1a794")
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 Sequential. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function takes a list of channel sizes and builds a decoder
# using ConvTranspose2d layers. We need to provide a list of integers
# representing channel dimensions.

channels = [64, 32, 16, 3]

ARGS = {
    "channels": channels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
create_encoder Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
buildingamind/vit-cot/models/common.py
code served (permissive licence) · get_code("b4b12ef2736a3dae")
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 Sequential. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function takes a 'channels' parameter which is a list/sequence of integers
# representing the number of channels at each layer of the encoder.
# The function iterates through channels[1:] and creates Conv2d layers
# that transform from channels[i] to channels[i+1].

# Let's create a simple channels list:
# - Start with 3 input channels (typical for RGB images)
# - Then 16 channels
# - Then 32 channels
# This will create 2 Conv2d layers followed by a Flatten layer

channels = [3, 16, 32]

ARGS = {
    "channels": channels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
get_model_output_size Ran
ran, honoured the contract we drafted
buildingamind/ViT-CoT/scripts/evaluate.py
code served (permissive licence) · get_code("7bba2e94d7262551")
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 int, ndim 0, dtype family int, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model that takes an input and produces an output
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(5, 8)
        self.fc2 = nn.Linear(8, 3)
    
    def forward(self, x):
        x = self.fc1(x)
        x = torch.relu(x)
        x = self.fc2(x)
        return x

model = SimpleModel()

# Test with int input_size
input_size = 5

ARGS = {
    "model": model,
    "input_size": input_size
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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 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, 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 3 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

Vision transformers (ViTs) are top-performing models on many computer vision benchmarks and can accurately predict human behavior on object recognition tasks. However, researchers question the value of using ViTs as models of biological learning because ViTs are thought to be more "data hungry" than brains, with ViTs requiring more training data to reach similar levels of performance. To test this assumption, we directly compared the learning abilities of ViTs and animals, by performing parallel controlled-rearing experiments on ViTs and newborn chicks. We first raised chicks in impoverished visual environments containing a single object, then simulated the training data available in those environments by building virtual animal chambers in a video game engine. We recorded the first-person images acquired by agents moving through the virtual chambers and used those images to train self-supervised ViTs that leverage time as a teaching signal, akin to biological visual systems. When ViTs were trained "through the eyes" of newborn chicks, the ViTs solved the same view-invariant object recognition tasks as the chicks. Thus, ViTs were not more data hungry than newborn visual systems: both learned view-invariant object representations in impoverished visual environments. The flexible and generic attention-based learning mechanism in ViTs-combined with the embodied data streams available to newborn animals-appears sufficient to drive the development of animal-like object recognition.

For agents

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

get_harvested_code_for_paper("2312.02843")
get_code_for_paper("2312.02843")
have("2312.02843")

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

curl https://syntology.ai/api/ran/2312.02843.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.02843.svg)](https://syntology.ai/paper/2312.02843)

Connect an agent — have() is free.