SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2112.02650 · 2021

VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 1 has 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/2112.02650.json · badge: /api/ran/2112.02650.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
squareslab/varclr canonical (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
forward Ran
ran on a synthesized input
squareslab/varclr/varclr/utils/infer.py
code served (permissive licence) · get_code("22a97b7cb4d23098")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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)

class MockTransformerModel(nn.Module):
    """Mock model that mimics transformer output structure."""
    def __init__(self, hidden_size=4, num_hidden_layers=12):
        super().__init__()
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.embedding = nn.Embedding(100, hidden_size)
        
    def forward(self, input_ids, attention_mask, output_hidden_states=False):
        batch_size, seq_len = input_ids.shape
        
        # Generate hidden states for each layer
        hidden_states = []
        x = self.embedding(input_ids)
        hidden_states.append(x)
        
        for _ in range(self.num_hidden_layers):
            x = x + torch.randn(batch_size, seq_len, self.hidden_size) * 0.1
            hidden_states.append(x)
        
        # Create output object
        class ModelOutput:
            def __init__(self, hidden_states):
                self.hidden_states = hidden_states
        
        return ModelOutput(hidden_states=hidden_states)

# Create model
model = MockTransformerModel(hidden_size=4, num_hidden_layers=12)

# Create input tensors
batch_size = 2
seq_len = 3
input_ids = torch.randint(0, 100, (batch_size, seq_len))
attention_mask = torch.ones(batch_size, seq_len, dtype=torch.long)

ARGS = {
    "model": model,
    "input_ids": input_ids,
    "attention_mask": attention_mask,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
read_embs Not yet run
unverified (harvested, no recorded run)
squareslab/varclr/varclr/utils/infer_ft_cbow.py
code served (permissive licence) · get_code("60f222a086c1f357")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Variable names are critical for conveying intended program behavior. Machine learning-based program analysis methods use variable name representations for a wide range of tasks, such as suggesting new variable names and bug detection. Ideally, such methods could capture semantic relationships between names beyond syntactic similarity, e.g., the fact that the names average and mean are similar. Unfortunately, previous work has found that even the best of previous representation approaches primarily capture relatedness (whether two variables are linked at all), rather than similarity (whether they actually have the same meaning). We propose VarCLR, a new approach for learning semantic representations of variable names that effectively captures variable similarity in this stricter sense. We observe that this problem is an excellent fit for contrastive learning, which aims to minimize the distance between explicitly similar inputs, while maximizing the distance between dissimilar inputs. This requires labeled training data, and thus we construct a novel, weakly-supervised variable renaming dataset mined from GitHub edits. We show that VarCLR enables the effective application of sophisticated, general-purpose language models like BERT, to variable name representation and thus also to related downstream tasks like variable name similarity search or spelling correction. VarCLR produces models that significantly outperform the state-of-the-art on IdBench, an existing benchmark that explicitly captures variable similarity (as distinct from relatedness). Finally, we contribute a release of all data, code, and pre-trained models, aiming to provide a drop-in replacement for variable representations used in either existing or future program analyses that rely on variable names.

For agents

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

get_harvested_code_for_paper("2112.02650")
get_code_for_paper("2112.02650")
have("2112.02650")

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

curl https://syntology.ai/api/ran/2112.02650.json

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

[![Syntology run record](https://syntology.ai/api/ran/2112.02650.svg)](https://syntology.ai/paper/2112.02650)

Connect an agent — have() is free.