SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.09400 · 2026

D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancement

Bin Liu, Grigorios Tsoumakas, Haoyu Peng, Zhijia Wei, Jiajing Zhang

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2605.09400.json · badge: /api/ran/2605.09400.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
iunanyou/D2ACE canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
ImR Ran
ran, honoured the contract we drafted
iunanyou/D2ACE/function.py
pointer only (licence: NONE) · get_code("c11cda3f16621f7e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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.

Imbalance Ran
ran; our contract draft was wrong, not the code
iunanyou/D2ACE/function.py
pointer only (licence: NONE) · get_code("77a50b28169631bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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.

Labeltype Ran
ran; our contract draft was wrong, not the code
iunanyou/D2ACE/function.py
pointer only (licence: NONE) · get_code("2b1452fe41bb1498")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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.

compute_A_matrix Ran
ran, honoured the contract we drafted
iunanyou/D2ACE/util.py
pointer only (licence: NONE) · get_code("af2654fc51ad503c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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.

get_activation Ran
ran; our contract draft was wrong, not the code
iunanyou/D2ACE/layers.py
pointer only (licence: NONE) · get_code("4c83ea5f9d060bcf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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.

get_filter_X Ran
ran; our contract draft was wrong, not the code
iunanyou/D2ACE/util.py
pointer only (licence: NONE) · get_code("8dbe4518b391740b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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.

reparameterize Ran
ran; our contract draft was wrong, not the code
iunanyou/D2ACE/model.py
pointer only (licence: NONE); the stored copy get_code serves, from junwenbai/c-gmvae, is pointer only (licence: NONE) · get_code("3cd91116c815d020")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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.

get_double_decoder_loss Not yet run
unverified (harvested, no recorded run)
iunanyou/D2ACE/util.py
pointer only (licence: NONE) · get_code("a3d6297f402e100a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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. No invocation recorded.

normal_cdf Not yet run
unverified (harvested, no recorded run)
iunanyou/D2ACE/model.py
pointer only (licence: NONE) · get_code("21c116eb9b5b16c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, iunanyou/D2ACE 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. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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
reparameterize 5 other papers
5 dated earlier · 2 only as an assembly brick
2112.00976 (2021-12)
Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
2306.08330 (2023-06)
Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction
2309.09294 (2023-09)
LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation
and 2 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

Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch selection methods typically rely on a single metric to assess instance importance and use static label weights to distinguish label significance, neglecting the dynamic evolution of metric utility and label significance during training. In addition, the method that explicitly exploits label correlations is largely affected by abundant irrelevant labels and insensitive to local label distributions. To address these issues, we propose D2ACE, a novel multi-label batch selection method guided by Dual Dynamics and Adaptive Correlation Enhancement. D2ACE explicitly captures metric and label-level training dynamics by combining stagewise Bernoulli mixture sampling, which balances uncertainty and noise-resistant hardness, with dynamic label weighting to recalibrate label priorities at each epoch based on current metric statistics. Furthermore, D2ACE introduces a local contextaware correlation enhancement to focus on relevant labels with instance-adaptive dependencies. Extensive experiments on tabular and image benchmarks demonstrate that D2ACE outperforms existing batch selection approaches across various deep MLC models, achieving stronger predictive performance and more efficient correlation modeling. * Corresponding author. (a) Hard-Imb (epoch 20) (b) ML-Unc (epoch 80)

For agents

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

get_harvested_code_for_paper("2605.09400")
get_code_for_paper("2605.09400")
have("2605.09400")

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

curl https://syntology.ai/api/ran/2605.09400.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.09400.svg)](https://syntology.ai/paper/2605.09400)

Connect an agent — have() is free.