SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.09790 · 2024

Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs

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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 2 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/2407.09790.json · badge: /api/ran/2407.09790.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
jyansir/tmlp canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
attenuated_kaiming_uniform_ Ran
ran; our contract draft was wrong, not the code
jyansir/tmlp/models/excel_former.py
pointer only (licence: MIT); the stored copy get_code serves, from whatashot/excelformer, is pointer only (licence: NONE) · get_code("52bdf478c0acf98f")
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 whatashot/excelformer, 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.

default_dnn_fit Ran
ran; our contract draft was wrong, not the code
jyansir/tmlp/models/abstract.py
code served (permissive licence) · get_code("b94fc69a33d84d97")
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 torch.nn as nn

torch.manual_seed(0)

class SimpleDNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.num_layer = nn.Linear(4, 8)
        self.cat_layer = nn.Linear(3, 8)
        self.output_layer = nn.Linear(16, 2)
    
    def forward(self, x_num, x_cat):
        num_out = self.num_layer(x_num)
        cat_out = self.cat_layer(x_cat)
        combined = torch.cat([num_out, cat_out], dim=1)
        logits = self.output_layer(combined)
        return logits

model = SimpleDNN()
x_num = torch.randn(2, 4)
x_cat = torch.randn(2, 3)
y = torch.randint(0, 2, (2,))

ARGS = {
    "model": model,
    "x_num": x_num,
    "x_cat": x_cat,
    "y": y
}
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 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
default_dnn_predict Ran
ran; our contract draft was wrong, not the code
jyansir/tmlp/models/abstract.py
code served (permissive licence) · get_code("028e90d079e7d017")
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 torch.nn as nn

torch.manual_seed(0)

class SimpleDNN(nn.Module):
    def __init__(self, num_features, cat_features, output_dim):
        super().__init__()
        input_dim = num_features + cat_features
        self.fc1 = nn.Linear(input_dim, 8)
        self.fc2 = nn.Linear(8, output_dim)
    
    def forward(self, x_num, x_cat):
        x = torch.cat([x_num, x_cat], dim=1)
        x = torch.relu(self.fc1(x))
        logits = self.fc2(x)
        return logits

model = SimpleDNN(num_features=4, cat_features=3, output_dim=2)
x_num = torch.randn(2, 4)
x_cat = torch.randn(2, 3)

ARGS = {
    'model': model,
    'x_num': x_num,
    'x_cat': x_cat
}
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 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
extract_config Ran
ran; our contract draft was wrong, not the code
jyansir/tmlp/utils/model_utils.py
code served (permissive licence) · get_code("108cc824c1a9cf8c")
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
import numpy as np

torch.manual_seed(0)

# Construct a valid model_config dictionary
model_config = {
    'model': {
        'layer1': {
            'lr': 0.001,
            'weight_decay': 1e-5
        },
        'layer2': {
            'lr': 0.0005,
            'lr2': 0.001,
            'type2': True,
            'weight_decay': 1e-4,
            'weight_decay2': 1e-5
        }
    },
    'training': {
        'optimizer': {
            'name': 'adam',
            'beta1': 0.9
        },
        'scheduler': {
            'name': 'cosine',
            'name2': 'linear',
            'type2': True,
            'T_max': 100,
            'T_max2': 50
        }
    },
    'meta': {
        'version': '1.0',
        'author': 'test'
    }
}

ARGS = {
    'model_config': model_config,
    'is_large_data': False
}
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 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
load_config_from_file Ran
ran; our contract draft was wrong, not the code
jyansir/tmlp/utils/model_utils.py
code served (permissive licence) · get_code("250a725ca84b5379")
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 json
import yaml
import tempfile
import os

# Create temporary YAML file
yaml_content = {
    'model': 'test_model',
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 10
}

yaml_fd, yaml_path = tempfile.mkstemp(suffix='.yaml')
os.close(yaml_fd)
with open(yaml_path, 'w') as f:
    yaml.dump(yaml_content, f)

ARGS = {
    'file': yaml_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
make_optimizer Ran
ran; our contract draft was wrong, not the code
jyansir/tmlp/models/abstract.py
code served (permissive licence) · get_code("5d82780c042d2e41")
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 Adam. 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 torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Create a simple model with parameters to optimize
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Create parameter groups - the function expects an iterable of parameter groups
# Each parameter group is a dict with 'params' key
parameter_groups = [
    {'params': model.linear1.parameters(), 'lr': 0.01},
    {'params': model.linear2.parameters(), 'lr': 0.001}
]

ARGS = {
    'optimizer': 'adam',
    'parameter_groups': parameter_groups,
    'lr': 0.001,
    'weight_decay': 1e-4
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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
to_one_hot Ran
ran; our contract draft was wrong, not the code
jyansir/tmlp/models/node/nn_utils.py
code served (permissive licence) · get_code("c169a4c49b79cc3e")
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 3, dtype family float, shape (2, 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 small integer tensor with shape (2, 3)
y = torch.randint(0, 4, (2, 3), dtype=torch.int64)

# depth can be None (will be inferred) or an explicit integer
depth = 5

ARGS = {
    "y": y,
    "depth": depth,
}
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 3, dtype family float, shape (2, 3, 5) — shape (2, 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
get_eps Not yet run
unverified (harvested, no recorded run)
jyansir/tmlp/models/sparser.py
code served (permissive licence) · get_code("df474c95bb18a92e")
How it ran

no invocation recorded.

quantile_concrete Not yet run
unverified (harvested, no recorded run)
jyansir/tmlp/models/sparser.py
code served (permissive licence) · get_code("5ceace1bad572a5f")
How it ran

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 7 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
to_one_hot 3 other papers
3 dated earlier
1909.06312 (2019-09)
Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data
2004.00345 (2020-04)
Editable Neural Networks
2207.08548 (2022-07)
GANDALF: Gated Adaptive Network for Deep Automated Learning of Features
attenuated_kaiming_uniform_ 1 other paper
1 dated earlier
2301.02819 (2023-01)
ExcelFormer: A neural network surpassing GBDTs on tabular data

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 datasets play a crucial role in various applications. Thus, developing efficient, effective, and widely compatible prediction algorithms for tabular data is important. Currently, two prominent model types, Gradient Boosted Decision Trees (GBDTs) and Deep Neural Networks (DNNs), have demonstrated performance advantages on distinct tabular prediction tasks. However, selecting an effective model for a specific tabular dataset is challenging, often demanding time-consuming hyperparameter tuning. To address this model selection dilemma, this paper proposes a new framework that amalgamates the advantages of both GBDTs and DNNs, resulting in a DNN algorithm that is as efficient as GBDTs and is competitively effective regardless of dataset preferences for GBDTs or DNNs. Our idea is rooted in an observation that deep learning (DL) offers a larger parameter space that can represent a well-performing GBDT model, yet the current back-propagation optimizer struggles to efficiently discover such optimal functionality. On the other hand, during GBDT development, hard tree pruning, entropy-driven feature gate, and model ensemble have proved to be more adaptable to tabular data. By combining these key components, we present a Tree-hybrid simple MLP (T-MLP). In our framework, a tensorized, rapidly trained GBDT feature gate, a DNN architecture pruning approach, as well as a vanilla back-propagation optimizer collaboratively train a randomly initialized MLP model. Comprehensive experiments show that T-MLP is competitive with extensively tuned DNNs and GBDTs in their dominating tabular benchmarks (88 datasets) respectively, all achieved with compact model storage and significantly reduced training duration.

For agents

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

get_harvested_code_for_paper("2407.09790")
get_code_for_paper("2407.09790")
have("2407.09790")

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

curl https://syntology.ai/api/ran/2407.09790.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.09790.svg)](https://syntology.ai/paper/2407.09790)

Connect an agent — have() is free.