SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.13064 · NeurIPS · 2020

Further Analysis of Outlier Detection with Deep Generative Models

Jun Zhu, Ziyu Wang, Bin Dai, David Wipf

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 failures of our instrument; 1 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/2010.13064.json · badge: /api/ran/2010.13064.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
thu-ml/ood-dgm canonical (classifier label)
classifier basis: classifier_2025
10 ran · 1 no recorded run
FunctionStatusWhere it lives
autocorr5 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thu-ml/ood-dgm/pixelcnn/linear_tests.py
pointer only (licence: NONE) · get_code("12c1f7d5258cde7c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

autocorr5 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thu-ml/ood-dgm/vae/src/oodutils.py
pointer only (licence: NONE) · get_code("95a1692d7acda49d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

autocorr_plot Ran
ran; our contract draft was wrong, not the code
thu-ml/ood-dgm/vae/src/oodutils.py
pointer only (licence: NONE) · get_code("d75580f0fb3f136b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

extract_single_chan Ran
ran, honoured the contract we drafted
thu-ml/ood-dgm/vae/src/ood_test.py
pointer only (licence: NONE) · get_code("0395293ce694df37")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

get_autocorr Ran
ran; our contract draft was wrong, not the code
thu-ml/ood-dgm/vae/src/oodutils.py
pointer only (licence: NONE) · get_code("671610baf7ebf3e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

get_autocorr_ Ran
ran; our contract draft was wrong, not the code
thu-ml/ood-dgm/pixelcnn/linear_tests.py
pointer only (licence: NONE) · get_code("ab103aa5251e1c82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

get_roc Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thu-ml/ood-dgm/vae/src/oodutils.py
pointer only (licence: NONE) · get_code("06b3d18ad8bb25f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

get_wn_stats Ran
ran; our contract draft was wrong, not the code
thu-ml/ood-dgm/pixelcnn/linear_tests.py
pointer only (licence: NONE) · get_code("41e4839301425a6c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

normalize_feature Ran
ran; our contract draft was wrong, not the code
thu-ml/ood-dgm/vae/src/oodutils.py
pointer only (licence: NONE) · get_code("69bb6ba7cbf5782d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

time_series_test Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
thu-ml/ood-dgm/vae/src/oodutils.py
pointer only (licence: NONE) · get_code("681ca4475dc8bcdf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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.

plot_autocorrelations Not yet run
unverified (harvested, no recorded run)
thu-ml/ood-dgm/vae/src/oodutils.py
pointer only (licence: NONE) · get_code("52b01ef0414c2f17")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, thu-ml/ood-dgm 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. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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 2026-11-22.

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 recent, counter-intuitive discovery that deep generative models (DGMs) can frequently assign a higher likelihood to outliers has implications for both outlier detection applications as well as our overall understanding of generative modeling. In this work, we present a possible explanation for this phenomenon, starting from the observation that a model's typical set and high-density region may not coincide. From this vantage point we propose a novel outlier test, the empirical success of which suggests that the failure of existing likelihood-based outlier tests does not necessarily imply that the corresponding generative model is uncalibrated. We also conduct additional experiments to help disentangle the impact of low-level texture versus high-level semantics in differentiating outliers. In aggregate, these results suggest that modifications to the standard evaluation practices and benchmarks commonly applied in the literature are needed.

For agents

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

get_harvested_code_for_paper("2010.13064")
get_code_for_paper("2010.13064")
have("2010.13064")

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

curl https://syntology.ai/api/ran/2010.13064.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.13064.svg)](https://syntology.ai/paper/2010.13064)

Connect an agent — have() is free.