SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.06645 · 2021

On Multi-Modal Learning of Editing Source Code

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 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/2108.06645.json · badge: /api/ran/2108.06645.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
modit-team/MODIT canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
Embedding Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
modit-team/MODIT/src/transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from instance-wise-ordered-transformer/iot, is pointer only (licence: NOASSERTION) · get_code("96cbb5e9ca5b6be0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from instance-wise-ordered-transformer/iot, and GitHub could not classify the licence of that repository (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.

Linear Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
modit-team/MODIT/src/transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from instance-wise-ordered-transformer/iot, is pointer only (licence: NOASSERTION) · get_code("8cd8cb0d1e9e63e4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from instance-wise-ordered-transformer/iot, and GitHub could not classify the licence of that repository (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.

collate Ran
ran on a synthesized input
modit-team/MODIT/src/denoising_dataset.py
code served (permissive licence) · get_code("a7feb3487f931b94")
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 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.

import torch

torch.manual_seed(0)

# Create sample data - each sample has 'id', 'source', and 'target' keys
# source and target are 1D tensors of token indices
samples = [
    {
        'id': 0,
        'source': torch.LongTensor([1, 2, 3, 4]),
        'target': torch.LongTensor([5, 6, 7]),
    },
    {
        'id': 1,
        'source': torch.LongTensor([1, 2]),
        'target': torch.LongTensor([5, 6, 7, 8, 9]),
    },
]

pad_idx = 0
eos_idx = 2
vocab = {
    'pad': pad_idx,
    'eos': eos_idx,
    'bos': 1,
}

ARGS = {
    'samples': samples,
    'pad_idx': pad_idx,
    'eos_idx': eos_idx,
    'vocab': vocab,
    'left_pad_source': False,
    'left_pad_target': False,
    'input_feeding': True,
    'pad_to_length': None,
}
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 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
collate_tokens Ran
ran on a synthesized input
modit-team/MODIT/src/denoising_dataset.py
code served (permissive licence) · get_code("1bc93e6eb54b046e")
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 int, shape (3, 5) 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

torch.manual_seed(0)

# Create a list of 1d tensors with varying lengths
values = [
    torch.tensor([10, 11, 12, 13]),
    torch.tensor([20, 21, 22]),
    torch.tensor([30, 31, 32, 33, 34]),
]

pad_idx = 0
eos_idx = 1
left_pad = False
move_eos_to_beginning = False
pad_to_length = None
pad_to_multiple = 1

ARGS = {
    "values": values,
    "pad_idx": pad_idx,
    "eos_idx": eos_idx,
    "left_pad": left_pad,
    "move_eos_to_beginning": move_eos_to_beginning,
    "pad_to_length": pad_to_length,
    "pad_to_multiple": pad_to_multiple,
}
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 int, shape (3, 5) — shape (3, 5) 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 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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
Linear 58 other papers
19 dated earlier, 39 later · 5 only as an assembly brick
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1706.03762 (2017-06)
Attention Is All You Need
1904.01681 (2019-04)
Augmented Neural ODEs
and 55 more not named here
Embedding 29 other papers
14 dated earlier, 15 later
1904.01681 (2019-04)
Augmented Neural ODEs
1906.12183 (2019-06)
Neural ODEs as the Deep Limit of ResNets with constant weights
2002.03184 (2020-02)
Time-aware Large Kernel Convolutions
and 26 more not named here

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

In recent years, Neural Machine Translator (NMT) has shown promise in automatically editing source code. Typical NMT based code editor only considers the code that needs to be changed as input and suggests developers with a ranked list of patched code to choose from - where the correct one may not always be at the top of the list. While NMT based code editing systems generate a broad spectrum of plausible patches, the correct one depends on the developers' requirement and often on the context where the patch is applied. Thus, if developers provide some hints, using natural language, or providing patch context, NMT models can benefit from them. As a proof of concept, in this research, we leverage three modalities of information: edit location, edit code context, commit messages (as a proxy of developers' hint in natural language) to automatically generate edits with NMT models. To that end, we build MODIT, a multi-modal NMT based code editing engine. With in-depth investigation and analysis, we show that developers' hint as an input modality can narrow the search space for patches and outperform state-of-the-art models to generate correctly patched code in top-1 position.

For agents

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

get_harvested_code_for_paper("2108.06645")
get_code_for_paper("2108.06645")
have("2108.06645")

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

curl https://syntology.ai/api/ran/2108.06645.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.06645.svg)](https://syntology.ai/paper/2108.06645)

Connect an agent — have() is free.