SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.09257 · 2019

Normalizing Flows: An Introduction and Review of Current Methods

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/1908.09257.json · badge: /api/ran/1908.09257.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
kaanguney/beta-vae-normalizing-flows community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
avgmaxdist Ran
ran on a synthesized input
kaanguney/beta-vae-normalizing-flows/src/normalizing_flows/metrics.py
code served (permissive licence) · get_code("ad3a7437903d272d")
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 numpy as np

# Analyze the function:
# avgmaxdist(x1, y1, x2, y2) calls:
# - maxdist(x1, y1, x2, y2) which calls:
#   - _paired_samples(x1, y1) and _paired_samples(x2, y2)
#   - quadct(x, y, x1, y1) and quadct(x, y, x2, y2)
# 
# _paired_samples expects:
#   - x, y as Any that can be converted to 1D float arrays
#   - must have equal length
#   - must not be empty
#
# quadct expects:
#   - x, y as floats
#   - xx, yy as Any that can be converted to 1D float arrays
#
# So x1, y1, x2, y2 should all be array-like with same length

# Create small 1D arrays of distinct sizes to verify behavior
x1 = [1.0, 2.0, 3.0, 4.0]
y1 = [2.0, 3.0, 4.0, 5.0]
x2 = [1.5, 2.5, 3.5, 4.5]
y2 = [2.5, 3.5, 4.5, 5.5]

ARGS = {
    'x1': x1,
    'y1': y1,
    'x2': x2,
    'y2': y2,
}
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 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
ks2d2s Ran
ran on a synthesized input
kaanguney/beta-vae-normalizing-flows/src/normalizing_flows/metrics.py
code served (permissive licence) · get_code("6edc59c32f0a703e")
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 numpy as np

# Set random seed for reproducibility
np.random.seed(42)

# Create sample data for the two-dimensional two-sample KS test
# x1, y1: first sample (5 points)
x1 = np.array([0.1, 0.2, 0.3, 0.4, 0.5], dtype=float)
y1 = np.array([0.15, 0.25, 0.35, 0.45, 0.55], dtype=float)

# x2, y2: second sample (7 points)
x2 = np.array([0.12, 0.22, 0.32, 0.42, 0.52, 0.62, 0.72], dtype=float)
y2 = np.array([0.18, 0.28, 0.38, 0.48, 0.58, 0.68, 0.78], dtype=float)

# nboot: number of bootstrap samples (None for analytical p-value, or positive int)
nboot = None

# extra: whether to return both p-value and statistic
extra = False

ARGS = {
    "x1": x1,
    "y1": y1,
    "x2": x2,
    "y2": y2,
    "nboot": nboot,
    "extra": extra,
}
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 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
maxdist Ran
ran on a synthesized input
kaanguney/beta-vae-normalizing-flows/src/normalizing_flows/metrics.py
code served (permissive licence) · get_code("86b831217a7f2695")
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 numpy as np

# Analyze the function signature and body:
# maxdist(x1, y1, x2, y2) takes 4 parameters
# Each is passed to _paired_samples which converts to 1D numpy arrays
# The function expects x1, y1 to be paired samples (equal length, non-empty, 1D)
# The function expects x2, y2 to be paired samples (equal length, non-empty, 1D)

# Create small sample data
np.random.seed(0)

# First sample pair - 5 points
x1_data = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
y1_data = np.array([1.5, 2.5, 3.5, 4.5, 5.5])

# Second sample pair - 5 points (same length as first pair)
x2_data = np.array([1.2, 2.1, 2.9, 4.1, 4.9])
y2_data = np.array([1.3, 2.4, 3.6, 4.4, 5.6])

ARGS = {
    'x1': x1_data,
    'y1': y1_data,
    'x2': x2_data,
    'y2': y2_data,
}
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 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions.

For agents

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

get_harvested_code_for_paper("1908.09257")
get_code_for_paper("1908.09257")
have("1908.09257")

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

curl https://syntology.ai/api/ran/1908.09257.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.09257.svg)](https://syntology.ai/paper/1908.09257)

Connect an agent — have() is free.