SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03850 · ACL · 2022

UniXcoder: Unified Cross-Modal Pre-training for Code Representation

Ming Zhou, Nan Duan, Jian Yin, Daya Guo, Shuai Lu, Yanlin Wang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 2 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/2203.03850.json · badge: /api/ran/2203.03850.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
microsoft/CodeBERT marked official in Papers with Code
Papers with Code archive
1 ran · 1 no recorded run
celbree/reacc community
Papers with Code archive
1 ran · 1 no recorded run
FunctionStatusWhere it lives
Beam Ran
ran on a synthesized input · constructed an object; no result was computed
microsoft/CodeBERT/UniXcoder/unixcoder.py
code served (permissive licence) · get_code("2af39b0537b177ac")
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, Beam: 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

torch.manual_seed(0)

# Beam class constructor takes: size, eos, device
ARGS = {
    "size": 4,           # beam size
    "eos": 2,            # end-of-sequence token id
    "device": torch.device("cpu")  # device to place tensors on
}
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 Beam — 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 Beam 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
RobertaLMHead Ran
ran on a synthesized input · constructed an object; no result was computed
celbree/reacc/model.py
code served (permissive licence) · get_code("c12eead558180dcb")
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, RobertaLMHead: 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
import torch.nn as nn
import torch.nn.functional as F

class RobertaLMHead(nn.Module):
    """Roberta Head for masked language modeling."""

    def __init__(self, config):
        super().__init__()
        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
        self.layer_norm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
        self.decoder = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
        self.bias = nn.Parameter(torch.zeros(config.vocab_size))
        self.decoder.bias = self.bias

    def forward(self, features, **kwargs):
        x = self.dense(features)
        x = F.gelu(x)
        x = self.layer_norm(x)
        x = self.decoder(x)
        return x


torch.manual_seed(0)


class Config:
    def __init__(self):
        self.hidden_size = 4
        self.vocab_size = 5
        self.layer_norm_eps = 1e-5


config = Config()

ARGS = {
    "config": config
}
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 RobertaLMHead — 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 RobertaLMHead 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
SimpleModel Not yet run
unverified (harvested, no recorded run)
celbree/reacc/model.py
code served (permissive licence) · get_code("0722e58fd64d7bcf")
How it ran

no invocation recorded.

UniXcoder Not yet run
unverified (harvested, no recorded run)
microsoft/CodeBERT/UniXcoder/unixcoder.py
code served (permissive licence) · get_code("01a9fd1ab720469b")
How it ran

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

Pre-trained models for programming languages have recently demonstrated great success on code intelligence. To support both code-related understanding and generation tasks, recent works attempt to pre-train unified encoder-decoder models. However, such encoder-decoder framework is sub-optimal for auto-regressive tasks, especially code completion that requires a decoder-only manner for efficient inference. In this paper, we present UniXcoder, a unified cross-modal pre-trained model for programming language. The model utilizes mask attention matrices with prefix adapters to control the behavior of the model and leverages cross-modal contents like AST and code comment to enhance code representation. To encode AST that is represented as a tree in parallel, we propose a one-to-one mapping method to transform AST in a sequence structure that retains all structural information from the tree. Furthermore, we propose to utilize multi-modal contents to learn representation of code fragment with contrastive learning, and then align representations among programming languages using a cross-modal generation task. We evaluate UniXcoder on five code-related tasks over nine datasets. To further evaluate the performance of code fragment representation, we also construct a dataset for a new task, called zero-shot code-to-code search. Results show that our model achieves state-of-the-art performance on most tasks and analysis reveals that comment and AST can both enhance UniXcoder.

For agents

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

get_harvested_code_for_paper("2203.03850")
get_code_for_paper("2203.03850")
have("2203.03850")

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

curl https://syntology.ai/api/ran/2203.03850.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.03850.svg)](https://syntology.ai/paper/2203.03850)

Connect an agent — have() is free.