SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.02290 · ICLR · 2021

Contrastive Syn-to-Real Generalization

Anima Anandkumar, Zhangyang Wang, Wuyang Chen, Zhiding Yu, Shalini De Mello, Sifei Liu, Jose Alvarez, Austin

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 1 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/2104.02290.json · badge: /api/ran/2104.02290.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
NVlabs/CSG marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
ryanking13/CSG community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
MoCoLoss Ran
ran on a synthesized input · constructed an object; no result was computed
ryanking13/CSG/loss/moco_loss.py
code served (permissive licence) · get_code("a9035681e2b85d9a")
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 an instance of its own class, MoCoLoss: the run constructed the object and did not call it, so no result was computed. 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
from torch import nn

torch.manual_seed(0)

# Create small encoder models
class SimpleEncoder(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.mlp = nn.Sequential(
            nn.Linear(input_dim, output_dim),
            nn.ReLU(),
            nn.Linear(output_dim, output_dim)
        )
    
    def forward(self, x):
        return self.mlp(x)

# Instantiate encoders
encoder_q = SimpleEncoder(input_dim=8, output_dim=4)
encoder_k = SimpleEncoder(input_dim=8, output_dim=4)

# Define ARGS dict with all required parameters
ARGS = {
    'embedding_dim': 4,
    'queue_size': 16,
    'momentum': 0.999,
    'temperature': 0.07,
    'scale_loss': 1.0,
    'queue_ids': ['a', 'b'],
}
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 MoCoLoss — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MoCoLoss 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
chunk_feature Ran
ran on a synthesized input
NVlabs/CSG/model/csg_builder.py
pointer only (licence: NOASSERTION) · get_code("7137f5836bf77b0d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, NVlabs/CSG (NOASSERTION). 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.

concat_all_gather Ran
ran, honoured the contract we drafted
NVlabs/CSG/model/csg_builder.py
pointer only (licence: NOASSERTION) · get_code("a2ad46fbfc2d7b20")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, NVlabs/CSG (NOASSERTION). 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.

CSG Not yet run
unverified (harvested, no recorded run)
NVlabs/CSG/model/csg_builder.py
pointer only (licence: NOASSERTION) · get_code("2e581e90912e9383")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, NVlabs/CSG (NOASSERTION). 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Training on synthetic data can be beneficial for label or data-scarce scenarios. However, synthetically trained models often suffer from poor generalization in real domains due to domain gaps. In this work, we make a key observation that the diversity of the learned feature embeddings plays an important role in the generalization performance. To this end, we propose contrastive synthetic-to-real generalization (CSG), a novel framework that leverages the pre-trained ImageNet knowledge to prevent overfitting to the synthetic domain, while promoting the diversity of feature embeddings as an inductive bias to improve generalization. In addition, we enhance the proposed CSG framework with attentional pooling (A-pool) to let the model focus on semantically important regions and further improve its generalization. We demonstrate the effectiveness of CSG on various synthetic training tasks, exhibiting state-of-the-art performance on zero-shot domain generalization.

For agents

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

get_harvested_code_for_paper("2104.02290")
get_code_for_paper("2104.02290")
have("2104.02290")

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

curl https://syntology.ai/api/ran/2104.02290.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.02290.svg)](https://syntology.ai/paper/2104.02290)

Connect an agent — have() is free.