Papers › Density estimation using Real NVP

Density estimation using Real NVP

27 May 2016arXiv:1605.08803archive 2025-07-28

Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio

Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space. We demonstrate its ability to model natural images on four datasets through sampling, log-likelihood evaluation and latent variable manipulations.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 70 code samples: 69 from 16 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 70: 48 ran (of which 26 constructed an object rather than computing a result; 38 with no instrument failure: 2 honoured, 0 violated, 36 with no contract checked; 10 where Syntology's instrument failed) · 22 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 69 samples from 16 repositories, 47 ran (38 with no instrument failure; 9 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

35 repositories listed; official and paper-mentioned ones first.

ANLGBOY/RealNVP-with-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
CompPhysVienna/paper_NF_for_rare_events mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MStypulkowski/mlinpl-generative-workshop mentioned on GitHubSyntology: not harvested report
P4ppenheimer/NormalizingFlows mentioned on GitHubpytorchSyntology: not harvested report
P4ppenheimer/NormalizingFlows_rnvp mentioned on GitHubpytorchSyntology: not harvested report
SamArgt/AudioSourceSep mentioned on GitHubtfSyntology: not harvested report
SrinjaySarkar/REAL-NVP mentioned on GitHubpytorchSyntology: not harvested report
ars-ashuha/real-nvp-pytorch mentioned on GitHubpytorchSyntology: not harvested report
chrischute/real-nvp mentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
claCase/NormalizingFlow mentioned on GitHubtfSyntology: not harvested report
desreslab/invaert4cardio mentioned on GitHubpytorchSyntology: not harvested report
e-hulten/real-nvp-2d mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
e-hulten/real_nvp_2d mentioned on GitHubpytorchSyntology: not harvested report
flavioschneider/ml_papers_presentations mentioned on GitHubMITSyntology: not harvested report
fmu2/realNVP mentioned on GitHubpytorchSyntology: 11 samples, 4 ran (0 instrument-failed) · 7 unverified report
gtegner/real_nvp mentioned on GitHubpytorchSyntology: not harvested report
hse-cs/probaforms mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (1 instrument-failed) · 2 unverified report
ikostrikov/pytorch-flows mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ispamm/realnvp-demo-pytorch mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
jenyliu/DLA_interview mentioned on GitHubpytorchSyntology: not harvested report
jfcrenshaw/pzflow mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to NICE: Non-linear Independent Components Estimation (arXiv:1410.8516; that paper's own run record: 24 ran (of which 16 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
li012589/NeuralRG mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
mahkons/flows mentioned on GitHubpytorchSyntology: 11 samples, 9 ran (5 instrument-failed) · 2 unverified report
rhychen/Glow mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
senya-ashukha/real-nvp-pytorch mentioned on GitHubpytorchSyntology: not harvested report
simonwestberg/DD2412-Glow mentioned on GitHubtfSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
simonwestberg/Glow mentioned on GitHubtfSyntology: not harvested report
sshish/NF mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
ssumin6/real_nvp mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
taesung89/real-nvp mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
wjy5446/pytorch-Real-NVP mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
xlwan/KRnet mentioned on GitHubtfSyntology: 12 samples, 7 ran (2 instrument-failed) · 5 unverified report
xqding/RealNVP mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Variational Inference with Normalizing Flows (arXiv:1505.05770; that paper's own run record: 21 ran (of which 13 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 1 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. report
gitlab.com/h2t/SALaT mentioned on GitHubtfSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

70 samples harvested: 48 ran (of which 26 constructed an object rather than computing a result; 38 with no instrument failure: 2 honoured, 0 violated, 36 with no contract checked; 10 where Syntology's instrument failed) · 22 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
7ran · our draft was wrong
3ran; the contract check could not run
36ran
22unverified

Licence: 33 of the 70 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 16 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 10 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

CompPhysVienna/paper_NF_for_rare_events community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
affine_coupling_layer conditional_bg/network/coupling_layers.py ran MIT (permissive) · 94f135340bbbc29f · report fixture: returned affine_coupling_layer · level recorded 2026-09-22
chrischute/real-nvp community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
bits_per_dim util/optim_util.py ran MIT (permissive) · 54dc276d7472ea04 · report fixture: signature x:Tensor/3/float, nll:Tensor/0/float · returned Tensor · level recorded 2026-09-24
checkerboard_mask util/array_util.py ran MIT (permissive) · 45a2481cb9317453 · report fixture: signature height:int/0/int, width:int/0/int, reverse:bool/0/bool, dtype:dtype/0/?, device:NoneType/0/?, requires_grad:bool/0/bool · returned Tensor · level recorded 2026-09-26
get_norm_layer in 111 papers util/norm_util.py ran MIT (permissive) · 94af3072059ccb7c · report fixture: signature norm_type:str/0/str · returned partial · level recorded 2026-09-26
get_param_groups in 12 papers util/norm_util.py ran MIT (permissive) · e478f33fab38d758 · report fixture: signature net:callable/0/?, weight_decay:float/0/float, norm_suffix:str/0/str, verbose:bool/0/bool · returned list · level recorded 2026-09-26
squeeze_2x2 util/array_util.py ran MIT (permissive) · 4c2fbb62a7ee51a7 · report fixture: signature x:Tensor/4/float, reverse:bool/0/bool, alt_order:bool/0/bool · returned Tensor · level recorded 2026-09-26
e-hulten/real-nvp-2d community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
CouplingLayer in 11 papers rnvp.py ran fingerprinted no licence file found · pointer only · 0eaa0501f292c8c6 · report fixture: returned CouplingLayer · level recorded 2026-09-22
RealNVP in 5 papers rnvp.py ran fingerprinted no licence file found · pointer only · 22e52a581dc49567 · report fixture: returned RealNVP · level recorded 2026-09-22
ScaleTranslate rnvp.py ran no licence file found · pointer only · d40249b744f13e2f · report fixture: returned ScaleTranslate · level recorded 2026-09-22
fmu2/realNVP community (archive-listed) 11 samples, 4 ran (0 instrument-failed) · 7 unverified
AbstractCoupling realnvp.py ran MIT (permissive) · f972e7e0b4588d1e · report fixture: returned AbstractCoupling · level recorded 2026-09-22
ResidualBlock in 100 papers realnvp.py ran MIT (permissive) · 02d7de503f8f151c · report fixture: returned ResidualBlock · level recorded 2026-09-22
ResidualModule realnvp.py ran MIT (permissive) · fbccf5ed84113182 · report fixture: returned ResidualModule · level recorded 2026-09-22
WeightNormConv2d realnvp.py ran MIT (permissive) · 355dc98275bca37b · report fixture: returned WeightNormConv2d · level recorded 2026-09-22
ChannelwiseAdditiveCoupling realnvp.py unverified MIT (permissive) · 2905171d5a4f77df · report
ChannelwiseAffineCoupling realnvp.py unverified MIT (permissive) · 81950ec1ad22027a · report
ChannelwiseCoupling realnvp.py unverified MIT (permissive) · 349f39c743f5c526 · report
CheckerboardAdditiveCoupling realnvp.py unverified MIT (permissive) · 00838e83ac1117ce · report
CheckerboardAffineCoupling realnvp.py unverified MIT (permissive) · d77fd2f51f8dae00 · report
CheckerboardCoupling realnvp.py unverified MIT (permissive) · f5044d42673aa07f · report
RealNVP in 5 papers realnvp.py unverified MIT (permissive) · db719b918ff418df · report
hse-cs/probaforms community (archive-listed) 5 samples, 3 ran (1 instrument-failed) · 2 unverified
InvertibleLayer probaforms/models/realnvp.py ran · metamorphic tier: deterministic MIT (permissive) · be475a4fed7464c2 · report fixture: returned InvertibleLayer · level recorded 2026-09-22
NormalizingFlow probaforms/models/realnvp.py ran · metamorphic tier: deterministic MIT (permissive) · 53e531a482ac4dee · report fixture: returned NormalizingFlow · level recorded 2026-09-22
gen_network probaforms/models/realnvp.py ran · our draft was wrong MIT (permissive) · 8f1ce335784ce477 · report fixture: signature n_inputs:int/0/int, n_outputs:int/0/int, hidden:tuple/1/int, activation:str/0/str · returned Sequential · level recorded 2026-09-22
RealNVP in 5 papers probaforms/models/realnvp.py unverified MIT (permissive) · 6c4e0011ebb20eb2 · report
RealNVPLayer probaforms/models/realnvp.py unverified MIT (permissive) · 1605aa4af4cccc4c · report
ikostrikov/pytorch-flows community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
CouplingLayer in 11 papers flows.py ran MIT (permissive) · 34ffed75d4fb4931 · report fixture: returned CouplingLayer · level recorded 2026-09-22
ispamm/realnvp-demo-pytorch community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
LinearBatchNorm rnvp.py ran fingerprinted no licence file found · pointer only · e65c09e2e972e3c6 · report fixture: returned LinearBatchNorm · level recorded 2026-09-22
LinearCouplingLayer rnvp.py ran no licence file found · pointer only · ee4d33b5da8d23fa · report fixture: returned LinearCouplingLayer · level recorded 2026-09-22
Permutation in 5 papers rnvp.py ran fingerprinted no licence file found · pointer only · a0db7e5e5ab30955 · report fixture: returned Permutation · level recorded 2026-09-22
LinearRNVP rnvp.py unverified no licence file found · pointer only · a64f97c02b4fcc6a · report
SequentialFlow rnvp.py unverified no licence file found · pointer only · 2ef261497864740a · report
li012589/NeuralRG community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
Flow in 10 papers flow/rnvp.py ran Apache-2.0 (permissive) · 5f7fa08b89de722c · report fixture: returned Flow · level recorded 2026-09-22
RNVP flow/rnvp.py ran Apache-2.0 (permissive) · 30e1477bc4b57f7d · report fixture: returned RNVP · level recorded 2026-09-22
checkNan flow/rnvp.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 299ba404a9f96d42 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
mahkons/flows community (archive-listed) 11 samples, 9 ran (5 instrument-failed) · 2 unverified
ActNormImage RealNVP/RealNVP.py ran · metamorphic tier: deterministic MIT (permissive) · d5af26f1bb10937d · report fixture: returned ActNormImage · level recorded 2026-09-22
ConditionalFlow RealNVP/RealNVP.py ran · metamorphic tier: deterministic MIT (permissive) · b896483dfb367a1d · report fixture: returned ConditionalFlow · level recorded 2026-09-22
Squeeze in 5 papers RealNVP/RealNVP.py ran · metamorphic tier: deterministic MIT (permissive) · a3d33c4dfab6325f · report fixture: returned Squeeze · level recorded 2026-09-22
Unsqueeze RealNVP/RealNVP.py ran · metamorphic tier: deterministic MIT (permissive) · 681e06d7532d0edf · report fixture: returned Unsqueeze · level recorded 2026-09-22
__get_channelwise_mask RealNVP/RealNVP.py ran · our draft was wrong MIT (permissive) · 3f4a65a29736ed2e · report fixture: signature shape:tuple/1/int, device:device/0/?, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22
__get_checkerboard_mask RealNVP/RealNVP.py ran · our draft was wrong MIT (permissive) · 60ea456ee4a19edf · report fixture: signature shape:tuple/1/int, device:str/0/str, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22
get_mask in 119 papers
census: 9 implementations from 10 papers, 9 distinct outputs across 7 buckets, one shared input per bucket
RealNVP/RealNVP.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · a9af99f9dc6f88d5 · report fixture: signature shape:tuple/1/int, pattern:str/0/str, device:str/0/str, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22
squeeze__ RealNVP/RealNVP.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 314875cfe97c786f · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-22
unsqueeze__ RealNVP/RealNVP.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · e24beea03138f40b · report fixture: signature image:Tensor/4/float · returned Tensor · level recorded 2026-09-22
RealNVP in 5 papers RealNVP/RealNVP.py unverified MIT (permissive) · e42de3a818fcf93d · report
SequentialFlow RealNVP/RealNVP.py unverified MIT (permissive) · 8f014633ebc49717 · report
rhychen/Glow community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
AffineCoupling in 5 papers models/glow.py ran · metamorphic tier: deterministic no licence file found · pointer only · fcdf1094082b5983 · report fixture: returned AffineCoupling · level recorded 2026-09-22
Conv2dZeroInit models/glow.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 666bcaaa2d8effd9 · report fixture: returned Conv2dZeroInit · level recorded 2026-09-22
simonwestberg/DD2412-Glow community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
AffineCoupling in 5 papers model.py ran no licence file found · pointer only · b774329417d3cb53 · report fixture: signature inputs:list/1/EagerTensor, forward:bool/0/bool · returned tuple · level recorded 2026-09-24
Conv2D_zeros model.py ran no licence file found · pointer only · 2e844d999d1172c3 · report fixture: returned Conv2D_zeros · level recorded 2026-09-22
sshish/NF community (archive-listed) 2 samples, 0 ran · 2 unverified
Basic NF.py unverified no licence file found · pointer only · ccc805cf7aa6b406 · report
CouplingLayer in 11 papers NF.py unverified no licence file found · pointer only · de669ff9f15b36d1 · report
ssumin6/real_nvp community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
AffineCouplingLayer layers.py ran · metamorphic tier: deterministic no licence file found · pointer only · a68f3013f9d0faa8 · report fixture: signature input:Tensor/2/float, reverse:bool/0/bool · returned tuple · level recorded 2026-09-22
taesung89/real-nvp community (archive-listed) 2 samples, 0 ran · 2 unverified
CouplingLayer in 11 papers real_nvp/nn.py unverified no licence file found · pointer only · f62eb0295869e616 · report
Layer in 20 papers real_nvp/nn.py unverified no licence file found · pointer only · 0e7224db7dc1693f · report
wjy5446/pytorch-Real-NVP community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
CouplingLayer in 11 papers network.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3d011f7cef5a2e7b · report fixture: returned CouplingLayer · level recorded 2026-09-22
Function_s_t network.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · b6542dbfd17b1777 · report fixture: returned Function_s_t · level recorded 2026-09-22
RealNVP in 5 papers network.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9a35cdb9141d51ec · report fixture: returned RealNVP · level recorded 2026-09-22
xlwan/KRnet community (archive-listed) 12 samples, 7 ran (2 instrument-failed) · 5 unverified
NN2 BR_lib/BR_model.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · 72ed3d4628c2fd6f · report fixture: signature inputs:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
actnorm BR_lib/BR_model.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · c793226ebfc2c109 · report fixture: signature inputs:EagerTensor/2/float, logdet:EagerTensor/0/float, reverse:bool/0/bool · returned tuple · level recorded 2026-09-22
affine_coupling BR_lib/BR_model.py ran GPL-3.0 (copyleft) · pointer only · cd3b1c121c287a2d · report fixture: signature inputs:EagerTensor/2/float, logdet:NoneType/0/?, reverse:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
default_initializer BR_lib/BR_model.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · a256d12412fc4a42 · report fixture: signature std:float/0/float · returned RandomNormal · level recorded 2026-09-22
entry_stop_gradients BR_lib/BR_model.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · 137d28e6764f74e4 · report fixture: signature target:EagerTensor/2/float, mask:EagerTensor/2/bool · returned EagerTensor · level recorded 2026-09-22
flatten_sum BR_lib/BR_model.py ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only · 42a8363a66214fb0 · report fixture: signature logps:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
log_standard_Gaussian BR_lib/BR_model.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · 678f84c2e99d3379 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
CDF_quadratic BR_lib/BR_model.py unverified GPL-3.0 (copyleft) · pointer only · 32da9e5b5ad57d81 · report
IM_rNVP BR_lib/BR_model.py unverified GPL-3.0 (copyleft) · pointer only · 3c41f44f3a1ddce7 · report
Linear in 127 papers BR_lib/BR_model.py unverified GPL-3.0 (copyleft) · pointer only · 3c1a067e298ec380 · report
W_LU BR_lib/BR_model.py unverified GPL-3.0 (copyleft) · pointer only · be23ec472b640e48 · report
flow_mapping BR_lib/BR_model.py unverified GPL-3.0 (copyleft) · pointer only · 40ddb492b2e78ade · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
int_shape in 6 papers repository not located ran · our draft was wrong licence of this copy not recorded · 3ba6aec873833b39 · report fixture: signature x:EagerTensor/2/float · returned list · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

15 assemblies on this paper: 15 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

15 sibling assemblies for real NVP (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 15 sibling assemblies; the other 3 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for real NVP (graph method: real NVP). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 15 siblings

  1. RealNVP entry · level 1 · ran · 9a35cdb9141d51ec
  2. CouplingLayer model · level 1 · ran · 3d011f7cef5a2e7b
  3. Function_s_t model · level 1 · ran · b6542dbfd17b1777

harvested Assembly for real NVP (graph method: real NVP). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. AffineCoupling entry · level 1 · ran · b774329417d3cb53
  2. Conv2D_zeros model · level 1 · ran · 2e844d999d1172c3

harvested Assembly for real NVP (graph method: real NVP). 14 bricks; individually on a fixture: 12 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. RealNVP entry · level 0 · unverified · e42de3a818fcf93d
  2. ActNormImage helper · level 1 · ran · d5af26f1bb10937d
  3. CouplingLayer model · level 1 · ran · 7e3c8937d2cbfe61
  4. SequentialFlow helper · level 0 · unverified · 8f014633ebc49717
  5. Squeeze model · level 1 · ran · a3d33c4dfab6325f
  6. Unsqueeze model · level 1 · ran · 681e06d7532d0edf
  7. get_mask helper · level 1 · ran; the contract check could not run (RAISES) · a9af99f9dc6f88d5
  8. ConditionalFlow helper · level 1 · ran · b896483dfb367a1d
  9. Flow helper · level 1 · ran · 21fa24b8b336cbae
  10. ResnetBlock helper · level 1 · ran · f4519d2bed1c4804
  11. squeeze__ helper · level 1 · ran; the contract check could not run (RAISES) · 314875cfe97c786f
  12. unsqueeze__ helper · level 1 · ran; the contract check could not run (RAISES) · e24beea03138f40b
  13. __get_channelwise_mask helper · level 1 · ran · our draft was wrong · 3f4a65a29736ed2e
  14. __get_checkerboard_mask helper · level 1 · ran · our draft was wrong · 60ea456ee4a19edf

harvested Assembly for real NVP (graph method: real NVP). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 15 siblings

  1. AffineCoupling entry · level 1 · ran · fcdf1094082b5983
  2. Conv2dZeroInit helper · level 1 · ran · 666bcaaa2d8effd9

harvested Assembly for real NVP (graph method: real NVP). 6 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. RealNVP entry · level 0 · unverified · 6c4e0011ebb20eb2
  2. GenModel helper · level 1 · ran · f7108f540de6b0bf
  3. NormalizingFlow model · level 1 · ran · 53e531a482ac4dee
  4. RealNVPLayer model · level 0 · unverified · 1605aa4af4cccc4c
  5. InvertibleLayer model · level 1 · ran · be475a4fed7464c2
  6. gen_network helper · level 1 · ran · our draft was wrong · 8f1ce335784ce477

harvested Assembly for real NVP (graph method: real NVP). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 15 siblings

  1. affine_coupling_layer entry · level 1 · ran · 94f135340bbbc29f

harvested Assembly for real NVP (graph method: real NVP). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. RNVP entry · level 1 · ran · 30e1477bc4b57f7d
  2. Flow model · level 1 · ran · 5f7fa08b89de722c
  3. checkNan helper · level 1 · ran · our draft was wrong · 299ba404a9f96d42

harvested Assembly for real NVP (graph method: real NVP). 11 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 15 siblings

  1. RealNVP entry · level 0 · unverified · db719b918ff418df
  2. ChannelwiseCoupling model · level 0 · unverified · 349f39c743f5c526
  3. CheckerboardCoupling model · level 0 · unverified · f5044d42673aa07f
  4. ChannelwiseAdditiveCoupling model · level 0 · unverified · 2905171d5a4f77df
  5. ChannelwiseAffineCoupling model · level 0 · unverified · 81950ec1ad22027a
  6. CheckerboardAdditiveCoupling model · level 0 · unverified · 00838e83ac1117ce
  7. CheckerboardAffineCoupling model · level 0 · unverified · d77fd2f51f8dae00
  8. AbstractCoupling helper · level 1 · ran · f972e7e0b4588d1e
  9. ResidualModule helper · level 1 · ran · fbccf5ed84113182
  10. ResidualBlock helper · level 1 · ran · 02d7de503f8f151c
  11. WeightNormConv2d helper · level 1 · ran · 355dc98275bca37b

harvested Assembly for real NVP (graph method: real NVP). 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 15 siblings

  1. RealNVP entry · level 1 · ran · 22e52a581dc49567
  2. BatchNorm helper · level 1 · ran · f3945dba0b2f2a01
  3. CouplingLayer model · level 1 · ran · 0eaa0501f292c8c6
  4. ScaleTranslate helper · level 1 · ran · d40249b744f13e2f

harvested Assembly for real NVP (graph method: real NVP). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 15 siblings

  1. CouplingLayer entry · level 1 · ran · 34ffed75d4fb4931

harvested Assembly for real NVP (graph method: real NVP). 5 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 15 siblings

  1. LinearRNVP entry · level 0 · unverified · a64f97c02b4fcc6a
  2. LinearBatchNorm helper · level 1 · ran · e65c09e2e972e3c6
  3. LinearCouplingLayer model · level 1 · ran · ee4d33b5da8d23fa
  4. Permutation model · level 1 · ran · a0db7e5e5ab30955
  5. SequentialFlow model · level 0 · unverified · 2ef261497864740a

harvested Assembly for real NVP (graph method: real NVP). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 15 siblings

  1. AffineCouplingLayer entry · level 1 · ran · a68f3013f9d0faa8
  1. IM_rNVP · ce23139d4c9d4e13 · 12 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. CouplingLayer · d1e67320c809970a · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. CouplingLayer · d377cf30eda00783 · 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1605.08803") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

BIG-bench Machine LearningDensity EstimationImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 32x32 Real NVP (Dinh et al., 2017) bpd 4.28 #35 of 35 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: RealNVP

AdamAffine CouplingBatch NormalizationConvolutionNormalizing FlowsReLURealNVPResidual BlockResidual ConnectionWeight DecayWeight Normalization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections