SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1702.08835 · 2017

Deep Forest

arXiv · PDF · Open in the Atlas

Code that ran

7 of 16 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 6 have no contract verdict; 1 failure of our instrument; 9 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/1702.08835.json · badge: /api/ran/1702.08835.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
PasaLab/forestlayer community (classifier label)
classifier basis not recorded on the link
5 ran · 6 no recorded run
leopiney/deep-forest community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
LAMDA-NJU/Deep-Forest reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
add_fit_time Ran
ran on a synthesized input
PasaLab/forestlayer/forestlayer/backend/common.py
code served (permissive licence) · get_code("257dbf8a0903b72c")
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 float, 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 torch

torch.manual_seed(0)

# The function add_fit_time takes a single parameter 'tim' which should be a numeric value
# The function adds it to a global FIT_TIME variable, so it should be a number (int or float)

tim_value = 1.5

ARGS = {
    "tim": tim_value
}
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 float, 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
add_kfold_time Ran
ran on a synthesized input
PasaLab/forestlayer/forestlayer/backend/common.py
code served (permissive licence) · get_code("cae5ed195d7bc040")
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 float, 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 torch
import numpy as np

# The function add_kfold_time takes a single parameter 'tim' which is added to a global variable
# The parameter appears to be a numeric value (int or float) based on the += operation

torch.manual_seed(0)

# Create a simple numeric value for the 'tim' parameter
tim_value = 0.5

ARGS = {
    "tim": tim_value
}
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 float, 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
create_logger Ran
ran on a synthesized input
leopiney/deep-forest/utils.py
code served (permissive licence) · get_code("52c95b981a1a3d21")
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 Logger. 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 logging
import uuid

ARGS = {
    'instance': 'test_logger_instance',
    'verbose': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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_CIFAR_batch Ran
ran; our contract draft was wrong, not the code
leopiney/deep-forest/data_utils.py
code served (permissive licence) · get_code("99aff553585ed743")
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 _pickle as pickle
import numpy as np
import tempfile
import os

# Create a temporary CIFAR batch file
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "cifar_batch.pkl")

# Create valid CIFAR batch data
cifar_data = {
    b'data': np.random.randint(0, 256, (10000, 3072), dtype=np.uint8),
    b'labels': np.random.randint(0, 10, 10000).tolist()
}

# Pickle the data to file
with open(temp_file, 'wb') as f:
    pickle.dump(cifar_data, f)

ARGS = {
    'filename': temp_file
}
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 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
load_mat Ran
ran on a synthesized input
PasaLab/forestlayer/forestlayer/datasets/uci_sEMG.py
code served (permissive licence) · get_code("dcff3f26f6a2c27b")
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, 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 numpy as np
import scipy.io as sio
import tempfile
import os

# Create a temporary .mat file with test data
temp_dir = tempfile.mkdtemp()
mat_path = os.path.join(temp_dir, "test_data.mat")

# Setup the move2label global dictionary
move2label = {
    'move_a': 0,
    'move_b': 1,
    'move_c': 2
}

# Create test data arrays
move_a_data = np.random.rand(3, 4).astype(np.float64)
move_b_data = np.random.rand(2, 4).astype(np.float64)
move_c_data = np.random.rand(4, 4).astype(np.float64)

# Save to .mat file
mat_dict = {
    'move_a': move_a_data,
    'move_b': move_b_data,
    'move_c': move_c_data
}
sio.savemat(mat_path, mat_dict)

# Define arguments for load_mat function
ARGS = {
    'mat_path': mat_path
}
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 tuple, ndim 1, dtype family float — a tuple 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
load_util Ran
ran on a synthesized input
PasaLab/forestlayer/forestlayer/datasets/uci_adult.py
code served (permissive licence) · get_code("5eb5e6e72cb6e10c")
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
import tempfile
import os

class FeatureParser:
    """Stand-in feature parser for UCI Adult dataset features."""
    
    def __init__(self, feature_dim, is_categorical=True):
        self.feature_dim = feature_dim
        self.is_categorical = is_categorical
        self.categories = {
            'cat_val_0': np.array([1, 0, 0], dtype=np.float32),
            'cat_val_1': np.array([0, 1, 0], dtype=np.float32),
            'cat_val_2': np.array([0, 0, 1], dtype=np.float32),
        }
    
    def get_featuredim(self):
        """Return the feature dimension for this parser."""
        return self.feature_dim
    
    def get_data(self, value):
        """Return one-hot encoded data for categorical feature."""
        if value in self.categories:
            return self.categories[value]
        return np.zeros(self.feature_dim, dtype=np.float32)
    
    def get_continuous(self, value):
        """Return continuous value."""
        try:
            return float(value)
        except:
            return 0.0


# Create temporary data file with 14 features per row + label
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.csv')
temp_path = temp_file.name

# Write sample data: 2 rows, 14 features + 1 label
temp_file.write("cat_val_0,25,cat_val_1,35,cat_val_2,45,cat_val_0,55,cat_val_1,65,cat_val_2,75,cat_val_0,85,<=50K\n")
temp_file.write("cat_val_1,30,cat_val_2,40,cat_val_0,50,cat_val_1,60,cat_val_2,70,cat_val_0,80,cat_val_1,90,>50K\n")
temp_file.close()

# Create 14 feature parsers (matching the function's expectation of exactly 14 features)
feature_parsers = [
    FeatureParser(feature_dim=3, is_categorical=True),   # Feature 0
    FeatureParser(feature_dim=1, is_categorical=False),  # Feature 1
    FeatureParser(feature_dim=3, is_categorical=True),   # Feature 2
    FeatureParser(feature_dim=1, is_categorical=False),  # Feature 3
    FeatureParser(feature_dim=3, is_categorical=True),   # Feature 4
    FeatureParser(feature_dim=1, is_categorical=False),  # Feature 5
    FeatureParser(feature_dim=3, is_categorical=True),   # Feature 6
    FeatureParser(feature_dim=1, is_categorical=False),  # Feature 7
    FeatureParser(feature_dim=3, is_categorical=True),   # Feature 8
    FeatureParser(feature_dim=1, is_categorical=False),  # Feature 9
    FeatureParser(feature_dim=3, is_categorical=True),   # Feature 10
    FeatureParser(feature_dim=1, is_categorical=False),  # Feature 11
    FeatureParser(feature_dim=3, is_categorical=True),   # Feature 12
    FeatureParser(feature_dim=1, is_categorical=False),  # Feature 13
]

ARGS = {
    'data_path': temp_path,
    'feature_parsers': feature_parsers,
    'one_hot': True,
}
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 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
transform_phase Ran
ran on a synthesized input
PasaLab/forestlayer/forestlayer/datasets/smallnorb.py
code served (permissive licence) · get_code("f5f72dc507e83016")
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

class MockNorbItem:
    def __init__(self, idx):
        self.image_lt = np.random.randint(0, 256, (96, 96), dtype=np.uint8)
        self.image_rt = np.random.randint(0, 256, (96, 96), dtype=np.uint8)
        self.category = np.uint8(idx % 10)
        self.lighting = idx % 8
        self.elevation = np.int16(idx % 10)
        self.azimuth = np.int16(idx % 20)

x_norb = [MockNorbItem(i) for i in range(24300)]

ARGS = {
    'x_norb': x_norb
}
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 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
add_comb_time Not yet run
unverified (harvested, no recorded run)
PasaLab/forestlayer/forestlayer/backend/common.py
code served (permissive licence) · get_code("552b7373509cac10")
How it ran

no invocation recorded.

deepforest_model_doc Not yet run
unverified (harvested, no recorded run)
LAMDA-NJU/Deep-Forest/deepforest/cascade.py
pointer only (licence: NOASSERTION) · get_code("53a12c0f59958db8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, LAMDA-NJU/Deep-Forest (NOASSERTION). 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.

get_CIFAR10_data Not yet run
unverified (harvested, no recorded run)
leopiney/deep-forest/data_utils.py
code served (permissive licence) · get_code("635e2c1e82a6b0b4")
How it ran

no invocation recorded.

get_num_nodes Not yet run
unverified (harvested, no recorded run)
PasaLab/forestlayer/forestlayer/backend/backend.py
code served (permissive licence) · get_code("c62dafdca8af26b5")
How it ran

no invocation recorded.

load_CIFAR10 Not yet run
unverified (harvested, no recorded run)
leopiney/deep-forest/data_utils.py
code served (permissive licence) · get_code("c8f533a07fd78a1d")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
PasaLab/forestlayer/forestlayer/datasets/imdb.py
code served (permissive licence) · get_code("6964a1a70c08d009")
How it ran

no invocation recorded.

load_data Not yet run
unverified (harvested, no recorded run)
PasaLab/forestlayer/forestlayer/datasets/smallnorb.py
code served (permissive licence) · get_code("7ccf228fa7971aeb")
How it ran

no invocation recorded.

pb2pred Not yet run
unverified (harvested, no recorded run)
PasaLab/forestlayer/forestlayer/backend/backend.py
code served (permissive licence) · get_code("17589faf9d473cf4")
How it ran

no invocation recorded.

stat_nodes Not yet run
unverified (harvested, no recorded run)
PasaLab/forestlayer/forestlayer/backend/backend.py
code served (permissive licence) · get_code("a783c2470abb60eb")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 13 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
deepforest_model_doc 1 other paper
1 later
2604.09106 (2026-04)
Detecting Diffusion-generated Images via Dynamic Assembly Forests
load_CIFAR10 1 other paper
1 later
2002.05712 (2020-02)
Cross-Iteration Batch Normalization
load_CIFAR_batch 1 other paper
1 dated earlier
1404.3606 (2014-04)
PCANet: A Simple Deep Learning Baseline for Image Classification?

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

Current deep learning models are mostly build upon neural networks, i.e., multiple layers of parameterized differentiable nonlinear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules. We conjecture that the mystery behind the success of deep neural networks owes much to three characteristics, i.e., layer-by-layer processing, in-model feature transformation and sufficient model complexity. We propose the gcForest approach, which generates \textit{deep forest} holding these characteristics. This is a decision tree ensemble approach, with much less hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to get excellent performance by using the same default setting. This study opens the door of deep learning based on non-differentiable modules, and exhibits the possibility of constructing deep models without using backpropagation.

For agents

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

get_harvested_code_for_paper("1702.08835")
get_code_for_paper("1702.08835")
have("1702.08835")

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

curl https://syntology.ai/api/ran/1702.08835.json

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

[![Syntology run record](https://syntology.ai/api/ran/1702.08835.svg)](https://syntology.ai/paper/1702.08835)

Connect an agent — have() is free.