SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1602.03001 · 2016

A Convolutional Attention Network for Extreme Summarization of Source Code

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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 0 have no contract verdict; 1 failure 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/1602.03001.json · badge: /api/ran/1602.03001.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
bentrevett/extreme-summarization-of-source-code reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
files_to_data Ran
ran; our contract draft was wrong, not the code
bentrevett/extreme-summarization-of-source-code/preprocess.py
code served (permissive licence) · get_code("a773b5969f246944")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 json
import os
import tempfile
import shutil

# Create a temporary directory structure with a JSON file
temp_dir = tempfile.mkdtemp()

# Create sample data that matches the expected structure
sample_data = [
    {
        "filename": "example1.py",
        "name": ["method", "one"],
        "tokens": ["def", "<id>", "method_one", "</id>", "(", "%self%", ")", ":", "return", "True"]
    },
    {
        "filename": "example2.py",
        "name": ["another", "method"],
        "tokens": ["def", "<id>", "another_method", "</id>", "(", "%self%", ",", "x", ")", ":", "print", "(", "x", ")", "<id>", "some_id", "</id>"]
    }
]

# Write the JSON file
json_filename = "test_data.json"
with open(os.path.join(temp_dir, json_filename), 'w') as f:
    json.dump(sample_data, f)

ARGS = {
    "DIR": temp_dir,
    "FILE": json_filename
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Attention mechanisms in neural networks have proved useful for problems in which the input and output do not have fixed dimension. Often there exist features that are locally translation invariant and would be valuable for directing the model's attention, but previous attentional architectures are not constructed to learn such features specifically. We introduce an attentional neural network that employs convolution on the input tokens to detect local time-invariant and long-range topical attention features in a context-dependent way. We apply this architecture to the problem of extreme summarization of source code snippets into short, descriptive function name-like summaries. Using those features, the model sequentially generates a summary by marginalizing over two attention mechanisms: one that predicts the next summary token based on the attention weights of the input tokens and another that is able to copy a code token as-is directly into the summary. We demonstrate our convolutional attention neural network's performance on 10 popular Java projects showing that it achieves better performance compared to previous attentional mechanisms.

For agents

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

get_harvested_code_for_paper("1602.03001")
get_code_for_paper("1602.03001")
have("1602.03001")

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

curl https://syntology.ai/api/ran/1602.03001.json

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

[![Syntology run record](https://syntology.ai/api/ran/1602.03001.svg)](https://syntology.ai/paper/1602.03001)

Connect an agent — have() is free.