SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1901.06033 · 2019

Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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; 0 failures of our instrument; 4 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/1901.06033.json · badge: /api/ran/1901.06033.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
emilemathieu/pvae canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
omiethescientist/HyperbolicDeepLearning community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
diff Ran
ran on a synthesized input
emilemathieu/pvae/pvae/distributions/ars.py
code served (permissive licence) · get_code("69c2938d5fbaa66e")
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 2, dtype family float, shape (2, 3) 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)

x = torch.randn(2, 4)

ARGS = {
    'x': x
}
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 2, dtype family float, shape (2, 3) — shape (2, 3) 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
extra_hidden_layer Ran
ran on a synthesized input
emilemathieu/pvae/pvae/models/architectures.py
code served (permissive licence) · get_code("a1d08d5e2c1fa566")
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 Sequential. 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)

# Analyze the function:
# - hidden_dim: an integer representing dimension
# - non_lin: a non-linearity module (nn.Module) that takes input of shape (..., hidden_dim)

# The function creates a Sequential with:
# 1. nn.Linear(hidden_dim, hidden_dim)
# 2. non_lin (the provided non-linearity)

# So non_lin must be a callable nn.Module that can accept tensors of shape (*, hidden_dim)

hidden_dim = 8
non_lin = nn.ReLU()

ARGS = {
    "hidden_dim": hidden_dim,
    "non_lin": non_lin
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
get_dataloaders Ran
ran on a synthesized input
omiethescientist/HyperbolicDeepLearning/HVAE/Data.py
code served (permissive licence) · get_code("82ae9a25c955fb4c")
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 torch
import pandas as pd
import tempfile
import os

torch.manual_seed(0)

# Create a temporary CSV file with sample data
temp_dir = tempfile.mkdtemp()
csv_path = os.path.join(temp_dir, "test_data.csv")

# Create sample data with 10 rows and 5 columns (4 features + 1 label)
sample_data = pd.DataFrame({
    'feature_1': [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0],
    'feature_2': [1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5, 9.5, 10.5],
    'feature_3': [2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0],
    'feature_4': [0.5, 1.5, 2.5, 3.5, 4.5, 5.5, 6.5, 7.5, 8.5, 9.5],
    'label': [0, 1, 0, 1, 0, 1, 0, 1, 0, 1]
})

sample_data.to_csv(csv_path, sep=',', index=False)

ARGS = {
    'workers': 0,
    'batch_size': 2,
    'csv_path': csv_path,
    'labels': True,
    'test_split': 0.3,
    'double': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas, sklearn, torch — 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_csv Ran
ran on a synthesized input
emilemathieu/pvae/pvae/datasets/datasets.py
code served (permissive licence) · get_code("a8eb4a941274e36a")
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 list, ndim 2, 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 tempfile
import os

# Create a temporary CSV file for testing
temp_dir = tempfile.mkdtemp()
csv_filename = os.path.join(temp_dir, "test.csv")

# Write some sample CSV data
csv_content = """name,age,city
Alice,30,New York
Bob,25,Los Angeles
Charlie,35,Chicago"""

with open(csv_filename, 'w') as f:
    f.write(csv_content)

ARGS = {
    'filename': csv_filename
}
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 list, ndim 2, dtype family float — a list 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
logsinh Ran
ran on a synthesized input
emilemathieu/pvae/pvae/utils.py
code served (permissive licence) · get_code("a2b20be607716473")
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 2, dtype family float, shape (2, 4) 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 math
import torch

class Constants(object):
    eta = 1e-05
    log2 = math.log(2)
    logpi = math.log(math.pi)
    log2pi = math.log(2 * math.pi)
    logceilc = 88
    logfloorc = -104
    invsqrt2pi = 1.0 / math.sqrt(2 * math.pi)
    sqrthalfpi = math.sqrt(math.pi / 2)

def logsinh(x):
    return x + torch.log(1 - torch.exp(-2 * x)) - Constants.log2

torch.manual_seed(0)

# Create a small tensor with values in a range where the function is numerically stable
# We need x to be positive and reasonably sized so that exp(-2*x) doesn't underflow
x = torch.tensor([[1.0, 2.0, 0.5, 1.5], [0.8, 1.2, 2.5, 0.3]], dtype=torch.float32)

ARGS = {
    "x": x
}
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 2, dtype family float, shape (2, 4) — shape (2, 4) 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
mse_loss Ran
ran on a synthesized input
omiethescientist/HyperbolicDeepLearning/HVAE/Loss.py
code served (permissive licence) · get_code("09149c204a657b8c")
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 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)

# Create small distinct-sized tensors for inputs and targets
inputs = torch.randn(2, 4)  # batch_size=2, dim=4
targets = torch.randn(2, 4)  # same shape as inputs

ARGS = {
    "inputs": inputs,
    "targets": targets,
}
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 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
hyp_loss Not yet run
unverified (harvested, no recorded run)
omiethescientist/HyperbolicDeepLearning/HVAE/Loss.py
code served (permissive licence) · get_code("569cfa67c995963d")
How it ran

no invocation recorded.

iwae_vec Not yet run
unverified (harvested, no recorded run)
omiethescientist/HyperbolicDeepLearning/HVAE/Loss.py
code served (permissive licence) · get_code("8eaa02fa0501a78f")
How it ran

no invocation recorded.

lexpand Not yet run
unverified (harvested, no recorded run)
emilemathieu/pvae/pvae/utils.py
code served (permissive licence) · get_code("8788efeef0d86cb7")
How it ran

no invocation recorded.

rexpand Not yet run
unverified (harvested, no recorded run)
emilemathieu/pvae/pvae/utils.py
code served (permissive licence) · get_code("2e053d97c4bd1bf1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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
lexpand 1 other paper
1 later
2402.07160 (2024-02)
PASOA-PArticle baSed Bayesian Optimal Adaptive design
rexpand 1 other paper
1 later
2402.07160 (2024-02)
PASOA-PArticle baSed Bayesian Optimal Adaptive design

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

The variational auto-encoder (VAE) is a popular method for learning a generative model and embeddings of the data. Many real datasets are hierarchically structured. However, traditional VAEs map data in a Euclidean latent space which cannot efficiently embed tree-like structures. Hyperbolic spaces with negative curvature can. We therefore endow VAEs with a Poincaré ball model of hyperbolic geometry as a latent space and rigorously derive the necessary methods to work with two main Gaussian generalisations on that space. We empirically show better generalisation to unseen data than the Euclidean counterpart, and can qualitatively and quantitatively better recover hierarchical structures.

For agents

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

get_harvested_code_for_paper("1901.06033")
get_code_for_paper("1901.06033")
have("1901.06033")

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

curl https://syntology.ai/api/ran/1901.06033.json

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

[![Syntology run record](https://syntology.ai/api/ran/1901.06033.svg)](https://syntology.ai/paper/1901.06033)

Connect an agent — have() is free.