SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_20309 · AAAI · 2022

DANETs: Deep Abstract Networks for Tabular Data Classification and Regression

Jintai Chen, Jian Wu, Yao Wan, Danny Chen, Kuanlun Liao

Open in the Atlas

Code that ran

5 of 7 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 5 have no contract verdict; 0 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/aaai_20309.json · badge: /api/ran/aaai_20309.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
WhatAShot/DANet canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
create_dataloaders Ran
ran on a synthesized input
WhatAShot/DANet/lib/utils.py
code served (permissive licence) · get_code("e3c907c95401d5b5")
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 tuple. 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 numpy as np

torch.manual_seed(0)

# Create small training data
X_train = np.random.randn(8, 4).astype(np.float32)
y_train = np.random.randint(0, 2, 8).astype(np.int64)

# Create eval sets (validation and test)
X_val = np.random.randn(6, 4).astype(np.float32)
y_val = np.random.randint(0, 2, 6).astype(np.int64)

X_test = np.random.randn(4, 4).astype(np.float32)
y_test = np.random.randint(0, 2, 4).astype(np.int64)

eval_set = [(X_val, y_val), (X_test, y_test)]

ARGS = {
    "X_train": X_train,
    "y_train": y_train,
    "eval_set": eval_set,
    "batch_size": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
define_device Ran
ran on a synthesized input
WhatAShot/DANet/lib/utils.py
code served (permissive licence) · get_code("a41fc8d29f369a06")
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 str. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# The function takes a single parameter: device_name (str)
# It accepts "auto", "cpu", or "cuda" and returns either "cpu" or "cuda"
# No complex objects needed - just string arguments

ARGS = {
    'device_name': 'auto'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
is_multilabel Ran
ran on a synthesized input
WhatAShot/DANet/lib/multiclass_utils.py
code served (permissive licence) · get_code("c6f9a241825feb6a")
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 bool, ndim 0, dtype family float, shape () 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 numpy as np
from scipy.sparse import dok_matrix, lil_matrix, csr_matrix

# Test case 1: 2D numpy array with multilabel format (binary indicators)
# This should return True - has shape (3, 2) with values 0 and 1
multilabel_array = np.array([[1, 0], [0, 1], [1, 1]], dtype=np.int32)

ARGS = {
    "y": multilabel_array
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () 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
type_of_target Ran
ran on a synthesized input
WhatAShot/DANet/lib/multiclass_utils.py
code served (permissive licence) · get_code("48b6a6878bbe2a46")
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 str. 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 numpy as np
from collections.abc import Sequence

# Test case 1: 1D continuous array
y_continuous = np.array([0.1, 0.6, 0.3])

# Test case 2: 1D binary array
y_binary = np.array([1, -1, -1, 1])

# Test case 3: 1D multiclass array
y_multiclass = np.array([1, 0, 2, 1, 2])

# Test case 4: 2D multiclass-multioutput array
y_multiclass_multioutput = np.array([[1, 2], [3, 1], [2, 3]])

# Test case 5: 2D continuous-multioutput array
y_continuous_multioutput = np.array([[1.5, 2.0], [3.0, 1.6], [2.5, 3.1]])

# Test case 6: Binary with strings
y_binary_strings = np.array(['a', 'b', 'a'])

# Test case 7: Multiclass with strings
y_multiclass_strings = np.array(['a', 'b', 'c', 'a', 'b'])

# Test case 8: Simple list (sequence)
y_list = [0.1, 0.6, 0.3]

# Test case 9: Binary float array (should be detected as binary, not continuous)
y_binary_float = np.array([1.0, 2.0])

# Use the simplest case for ARGS
ARGS = {
    'y': np.array([1, 0, 2, 1, 2])
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
validate_eval_set Ran
ran on a synthesized input
WhatAShot/DANet/lib/utils.py
code served (permissive licence) · get_code("3265120aa9cc779d")
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 tuple. 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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create training data
X_train = np.random.randn(10, 5).astype(np.float32)  # 10 samples, 5 features
y_train = np.random.randint(0, 2, 10).astype(np.int32)  # 10 samples, binary labels

# Create evaluation set with compatible shapes
X_eval = np.random.randn(6, 5).astype(np.float32)  # 6 samples, 5 features (same as X_train)
y_eval = np.random.randint(0, 2, 6).astype(np.int32)  # 6 samples (same number of features as y_train)

eval_set = [(X_eval, y_eval)]
eval_name = ['validation']

ARGS = {
    'eval_set': eval_set,
    'eval_name': eval_name,
    'X_train': X_train,
    'y_train': y_train
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
check_metrics Not yet run
unverified (harvested, no recorded run)
WhatAShot/DANet/lib/metrics.py
code served (permissive licence) · get_code("148ea925a59f9fde")
How it ran

no invocation recorded.

infer_output_dim Not yet run
unverified (harvested, no recorded run)
WhatAShot/DANet/lib/multiclass_utils.py
code served (permissive licence) · get_code("c01a55237b9878e3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 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.

FunctionAlso present inEarliest-datedOthers named
check_metrics 1 other paper
1 dated earlier
1908.07442 (2019-08)
TabNet: Attentive Interpretable Tabular Learning
infer_output_dim 1 other paper
1 dated earlier
1908.07442 (2019-08)
TabNet: Attentive Interpretable Tabular Learning
is_multilabel 1 other paper
1 dated earlier
1908.07442 (2019-08)
TabNet: Attentive Interpretable Tabular Learning

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

Tabular data are ubiquitous in real world applications. Although many commonly-used neural components (e.g., convolution) and extensible neural networks (e.g., ResNet) have been developed by the machine learning community, few of them were effective for tabular data and few designs were adequately tailored for tabular data structures. In this paper, we propose a novel and flexible neural component for tabular data, called Abstract Layer (ABSTLAY), which learns to explicitly group correlative input features and generate higherlevel features for semantics abstraction. Also, we design a structure re-parameterization method to compress the trained ABSTLAY, thus reducing the computational complexity by a clear margin in the reference phase. A special basic block is built using ABSTLAYs, and we construct a family of Deep Abstract Networks (DANETs) for tabular data classification and regression by stacking such blocks. In DANETs, a special shortcut path is introduced to fetch information from raw tabular features, assisting feature interactions across different levels. Comprehensive experiments on seven real-world tabular datasets show that our ABSTLAY and DANETs are effective for tabular data classification and regression, and the computational complexity is superior to competitive methods. Besides, we evaluate the performance gains of DANET as it goes deep, verifying the extendibility of our method. Our code is available at https://github.com/WhatAShot/DANet.

For agents

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

get_harvested_code_for_paper("aaai_20309")
get_code_for_paper("aaai_20309")
have("aaai_20309")

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

curl https://syntology.ai/api/ran/aaai_20309.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_20309.svg)](https://syntology.ai/paper/aaai_20309)

Connect an agent — have() is free.