SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.07177 · EMNLP · 2021

Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup

Weiguo Gao, Xuan Li, Guang Liu, Yuzhao Mao, Hailong Huang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 1 failure 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/2109.07177.json · badge: /api/ran/2109.07177.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
songyouwei/ABSA-PyTorch canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
build_embedding_matrix Ran
ran on a synthesized input
songyouwei/ABSA-PyTorch/data_utils.py
code served (permissive licence) · get_code("dbd3d55c5e5a0fc7")
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 ndarray, ndim 2, dtype family float, shape (7, 300) 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 os
import pickle
import numpy as np
import tempfile

# Create a temporary directory for the test
temp_dir = tempfile.mkdtemp()

# Create a small mock word2idx dictionary
word2idx = {
    'the': 1,
    'cat': 2,
    'sat': 3,
    'on': 4,
    'mat': 5,
}

# Embedding dimension
embed_dim = 300

# Path for the pickle cache file
dat_fname = os.path.join(temp_dir, 'embedding_matrix.pkl')

# Pre-create the embedding matrix pickle to avoid file I/O issues
# This simulates a cached embedding matrix
embedding_matrix = np.random.randn(len(word2idx) + 2, embed_dim).astype('float32')
pickle.dump(embedding_matrix, open(dat_fname, 'wb'))

ARGS = {
    'word2idx': word2idx,
    'embed_dim': embed_dim,
    'dat_fname': dat_fname,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (7, 300) — shape (7, 300) 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
pad_and_truncate Ran
ran; our contract draft was wrong, not the code
songyouwei/ABSA-PyTorch/data_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from JZCS2018/SMAT, is pointer only (licence: NONE) · get_code("bf68f09b3239ce10")
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 JZCS2018/SMAT, and GitHub detected no licence in that repository when it was checked. 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.

build_tokenizer Not yet run
unverified (harvested, no recorded run)
songyouwei/ABSA-PyTorch/data_utils.py
code served (permissive licence) · get_code("b97da16eaf330fad")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
pad_and_truncate 2 other papers
1 later, 1 same year, order not determinable
2021.naacl-main.231 (2021 (year only))
Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble
2410.24105 (2024-10)
Matchmaker: Self-Improving Large Language Model Programs for Schema Matching

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

Mixup is a recent regularizer for current deep classification networks. Through training a neural network on convex combinations of pairs of examples and their labels, it imposes locally linear constraints on the model's input space. However, such strict linear constraints often lead to under-fitting which degrades the effects of regularization. Noticeably, this issue is getting more serious when the resource is extremely limited. To address these issues, we propose the Adversarial Mixing Policy (AMP), organized in a "min-max-rand" formulation, to relax the Locally Linear Constraints in Mixup. Specifically, AMP adds a small adversarial perturbation to the mixing coefficients rather than the examples. Thus, slight non-linearity is injected in-between the synthetic examples and synthetic labels. By training on these data, the deep networks are further regularized, and thus achieve a lower predictive error rate. Experiments on five text classification benchmarks and five backbone models have empirically shown that our methods reduce the error rate over Mixup variants in a significant margin (up to 31.3%), especially in low-resource conditions (up to 17.5%).

For agents

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

get_harvested_code_for_paper("2109.07177")
get_code_for_paper("2109.07177")
have("2109.07177")

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

curl https://syntology.ai/api/ran/2109.07177.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.07177.svg)](https://syntology.ai/paper/2109.07177)

Connect an agent — have() is free.