Papers › Denoising Diffusion Probabilistic Models
Denoising Diffusion Probabilistic Models
Jonathan Ho, Ajay Jain, Pieter Abbeel
We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN. Our implementation is available at https://github.com/hojonathanho/diffusion
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):
get_harvested_code_for_paper(arxiv_id="2006.11239")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2006.11239", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2006.11239")
Code
Syntology 253 code samples: 249 from 45 repositories linked to this paper, 4 identical to code harvested from another paper's repository. Across all 253: 186 ran (of which 81 constructed an object rather than computing a result; 142 with no instrument failure: 20 honoured, 8 violated, 114 with no contract checked; 44 where Syntology's instrument failed) · 67 unverified. Where Syntology's instrument failed: 27 where our contract draft was wrong; 17 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 2 samples from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 247 samples from 44 repositories, 181 ran (139 with no instrument failure; 42 where Syntology's instrument failed); 4 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 16 of its repositories that Syntology harvested for other papers:
- Janspiry/Palette-Image-to-Image-Diffusion-Models, community (archive-listed): harvested for another paper, listed under the repository
- glouppe/info8010-deep-learning, community (archive-listed): harvested for another paper, listed under the repository
- hankpipi/diffusers-hetu, community (archive-listed): harvested for another paper, listed under the repository
- henryaddison/score_sde_pytorch, community (archive-listed): harvested for another paper, listed under the repository
- ivanvovk/WaveGrad, community (archive-listed): harvested for another paper, listed under the repository
- kpandey008/DiffuseVAE, community (archive-listed): harvested for 2 other papers, listed under the repository
- lucidrains/ddpm-proteins, community (archive-listed): harvested for another paper, listed under the repository
- lucidrains/imagen-pytorch, community (archive-listed): harvested for another paper, listed under the repository
- ml-postech/robust-evaluation-of-diffusion-based-purification, community (archive-listed): harvested for another paper, listed under the repository
- samb-t/unleashing-transformers, community (archive-listed): harvested for another paper, listed under the repository
- xiaoiker/meta_dpm, community (archive-listed): harvested for another paper, listed under the repository
- yang-song/score_sde, community (archive-listed): harvested for another paper, listed under the repository
- yang-song/score_sde_pytorch, community (archive-listed): harvested for 2 other papers, listed under the repository
- MaximeVandegar/Papers-in-100-Lines-of-Code, community (archive-listed): harvested for 33 other papers, listed under the repository
- horenbergerb/BernoulliDiffusion, community (archive-listed): harvested for another paper, listed under the repository
- labmlai/annotated_deep_learning_paper_implementations, community (archive-listed): harvested for 15 other papers, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 8 of the 186 samples that ran have no recorded date.
70 repositories listed; official and paper-mentioned ones first.
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
253 samples harvested: 186 ran (of which 81 constructed an object rather than computing a result; 142 with no instrument failure: 20 honoured, 8 violated, 114 with no contract checked; 44 where Syntology's instrument failed) · 67 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 67 of the 253 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 45 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. 5 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 4 samples are 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 33 samples that ran, the graph records a signature this page does not show, each row saying why in its tooltip: for 32, 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; for 1, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.
ac0b112cced85e41 · report
fixture: signature shape:tuple/1/int, noise_fn:callable/0/?, repeat:bool/0/bool, dtype:DType/0/? · returned EagerTensor · level recorded 2026-09-22 aa7eeb8194013eed · report
39e408d858270810 · report
fixture: returned AttentionBlock · level recorded 2026-09-22 621e4b433c363624 · report
fixture: returned Downsample · level recorded 2026-09-22 da485dc2b10fd6d7 · report
fixture: returned GroupNorm32 · level recorded 2026-09-22 a5638e9931779103 · report
fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24 1c07b81f544f048b · report
fixture: returned QKVAttentionLegacy · level recorded 2026-09-22 census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket model.py ran · metamorphic tier: deterministic no licence file found · pointer only ·
d1ba7d3cb6a2ac54 · report
fixture: returned ResBlock · level recorded 2026-09-22 1ce7357760c5ddb5 · report
fixture: returned Upsample · level recorded 2026-09-22 census: 4 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket model.py ran · our draft was wrong no licence file found · pointer only ·
7bab05ad7b9fa652 · report
fixture: signature channels:int/0/int · returned GroupNorm32 · level recorded 2026-09-22 census: 22 implementations from 27 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 1, kind int, dtype int64 model.py ran · our draft was wrong fingerprinted no licence file found · pointer only ·
88867f4df8cef2a9 · report
fixture: signature timesteps:Tensor/1/int, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded 2026-09-22 d6cc5a7817ff7f5d · report
f7f131ff4e466645 · report
51950b12318e7d94 · report
49ff3519834529f3 · report
7705d2253b6cd3eb · report
6320459286032eed · report
fixture: returned MyDDPM · level recorded 2026-09-22 6acb9f0e096fbe2d · report
fixture: signature temp:Tensor/1/int · returned Tensor · level recorded 2026-09-22 5cb5c0a850bc1570 · report
fixture: signature tensor:Tensor/4/float, mode:str/0/str · returned int · level recorded 2026-09-22 7bd13464fab4e3ed · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:tuple/1/int, stride:int/0/int, dilation:int/0/int, padding:int/0/int, bias:bool/0/bool, padding_mode:str/0/str, init_scale:float/0/float · returned Conv2d · level recorded 2026-09-22 5aa603017b7bf9da · report
fixture: signature in_channels:int/0/int, out_channels:int/0/int, init_scale:float/0/float · returned Linear · level recorded 2026-09-22 1f1e204a00309655 · report
fixture: signature in_ch:int/0/int, with_conv:bool/0/bool · returned Conv2d · level recorded 2026-09-22 e2ba707f79fd3255 · report
fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded 2026-09-22 0ee1a2c94acafeca · report
fixture: signature out_ch:int/0/int · returned GroupNorm · level recorded 2026-09-22 ec54fc881e43f612 · report
fixture: signature tensor:Tensor/2/float, gain:float/0/float, mode:str/0/str · returned Tensor · level recorded 2026-09-22 census: 11 implementations from 16 papers, 9 distinct outputs across 3 buckets, one shared input per bucket lib/models/unet.py ran · our draft was wrong MIT (permissive) ·
e0872a9a65b8245f · report
fixture: signature in_ch:int/0/int, with_conv:bool/0/bool · returned Sequential · level recorded 2026-09-22 0e6c111dab2954fb · report
fixture: signature tensor:Tensor/2/float, scale:float/0/float · returned Tensor · level recorded 2026-09-22 c646ffa348cd258a · report
acc61062a727fa80 · report
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 music_diffusion/networks/diffusion.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only ·
7a279b81d71aae4b · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22 930974fb4f8770f1 · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22 2163b6edd24b8178 · report
fixture: signature t_index:Tensor/2/int · returned Tensor · level recorded 2026-09-22 100f8236e0919328 · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24 741695539e377a57 · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22 dce27c7197cf4b78 · report
fixture: signature factor:Tensor/4/float, t:Tensor/2/int · returned Tensor · level recorded 2026-09-22 5b63297f2f045c3c · report
c912ab9f4bd44da2 · report
185128441a55874c · report
b4d23e968a312973 · report
5567735bb1232884 · report
d76ac471b3d8fee5 · report
a65da7ad43a301d2 · report
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket DDPM/DDPM_pytorch.py ran · metamorphic tier: invariant MIT (permissive) ·
45c3ad11676d68ef · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 df61f4b08d71cdeb · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket DDPM/DDPM_pytorch.py ran · metamorphic tier: invariant MIT (permissive) ·
ab64db8c2a71e2ef · report
fixture: signature x:Tensor/4/float, time_emb:Tensor/2/float · returned Tensor · level recorded 2026-09-22 bd014f5d82f53c97 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 5d6a2169c601b2f9 · report
fixture: signature time:Tensor/1/float · returned Tensor · level recorded 2026-09-22 65f82eed2ed5c542 · report
fixture: signature timesteps:int/0/int, s:float/0/float · returned Tensor · level recorded 2026-09-22 34d469418e5abe5b · report
69f27ba78fe269cb · report
fixture: returned ChannelShuffle · level recorded 2026-09-22 b3f906bb8ffb9305 · report
fixture: returned ConvBnSiLu · level recorded 2026-09-22 61de5d0bdb038f95 · report
fixture: returned DecoderBlock · level recorded 2026-09-22 bfa427b1e754f31a · report
fixture: returned EncoderBlock · level recorded 2026-09-22 24efaae94384e2f2 · report
fixture: returned ResidualBottleneck · level recorded 2026-09-22 e34dd41cf488e665 · report
fixture: returned ResidualDownsample · level recorded 2026-09-22 8a7675ca34bf8e8c · report
fixture: returned TimeMLP · level recorded 2026-09-22 533ba10eceea02a7 · report
fixture: returned Unet · level recorded 2026-09-22 census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket Diffusion/DDPM/models/model.py ran MIT (permissive) ·
27a0c9621917d719 · report
fixture: returned Attention · level recorded 2026-09-22 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket Diffusion/DDPM/models/model.py ran MIT (permissive) ·
68c21a4e900cf84d · report
fixture: returned Block · level recorded 2026-09-22 6abe268a41063ca0 · report
fixture: returned ConvNextBlock · level recorded 2026-09-22 f5c52234eed97ee9 · report
fixture: returned Conv2d · level recorded 2026-09-22 e66e5ee5660ade9e · report
fixture: returned LinearAttention · level recorded 2026-09-22 1e735d15bf574858 · report
fixture: returned PreNorm · level recorded 2026-09-22 302d25b74ed63a41 · report
fixture: signature x:Tensor/4/float, time_emb:Tensor/2/float · returned Tensor · level recorded 2026-09-24 census: 5 implementations from 5 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32 Diffusion/DDPM/models/model.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) ·
52bb9e202a8ce9ef · report
fixture: signature time:Tensor/1/float · returned Tensor · level recorded 2026-09-22 8bee9b7a4832d4a1 · report
fixture: returned ConvTranspose2d · level recorded 2026-09-22 bf4172f6a11423b7 · report
f509a7f7b08b8f0f · report
fixture: signature c_mid:int/0/int, c_out:int/0/int, dropout_last:bool/0/bool · returned function · level recorded 2026-09-22 a640022279fbd102 · report
9e71dd35b94143ad · report
e05842cf30157453 · report
86ee0ef9ccc062c4 · report
fixture: returned GaussianDiffusion · level recorded 2026-09-22 62afec33f38bb212 · report
fixture: signature timesteps:int/0/int, s:float/0/float · returned Tensor · level recorded 2026-09-22 e3122a1351004542 · report
fixture: signature val:int/0/int, func:callable/0/? · returned int · level recorded 2026-09-22 census: 5 implementations from 103 papers, 1 distinct output on one shared input denoising_diffusion_pytorch/diffusion_models/denoising_diffusion_pytorch.py ran · violated contract fingerprinted MIT (permissive) ·
d98bef4c38be4932 · report
fixture: signature x:int/0/int · returned bool · level recorded 2026-09-22 a9907c856452e8f6 · report
fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-22 ae85de96d538f79a · report
fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22 34d3583abd61cff5 · report
fixture: returned EDMPrecond · level recorded 2026-09-22 d3705ec829eb39f1 · report
fixture: signature time_steps:Tensor/1/float, temb_dim:int/0/int · returned Tensor · level recorded 2026-09-22 6f2ab90303c6391c · report
fixture: returned GaussianDiffusion · level recorded 2026-09-22 7eb19b2d745af94f · report
fixture: signature num_diffusion_timesteps:int/0/int, alpha_bar:callable/0/?, max_beta:float/0/float · returned ndarray · level recorded 2026-09-22 97aabd2621b6733c · report
fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-22 fab86763be9d382c · report
fixture: signature scheduler_type:str/0/str, timesteps:int/0/int · returned ndarray · level recorded 2026-09-22 266880ccbbc9d9ba · report
fixture: signature noisy_latent:Tensor/2/float, latent_timestep:int/0/int, timestep_schedule:list/1/int, noise_prediction_model:callable/0/? · returned Tensor · level recorded 2026-09-22 43e4ae995dd446e2 · report
fixture: signature snr:Tensor/0/float · returned tuple · level recorded 2026-09-22 9fc5f1faba8dd549 · report
fixture: returned BetaSchedule · level recorded 2026-09-22 889d53276e702ee9 · report
fixture: returned DDPM · level recorded 2026-09-22 b0a153607e31ff3c · report
fixture: returned ConvNorm · level recorded 2026-09-22 312abccdd2ea163d · report
fixture: returned Denoiser · level recorded 2026-09-22 2bbf0db2a024a96d · report
fixture: returned DiffusionEmbedding · level recorded 2026-09-22 752e01f02bca6161 · report
fixture: returned LinearNorm · level recorded 2026-09-22 1c918e79d462a26b · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 17bc8409599d140b · report
fixture: returned ResidualBlock · level recorded 2026-09-22 372f8ce0b71e834d · report
fixture: signature schedule_mode:str/0/str, timesteps:int/0/int, min_beta:float/0/float, max_beta:float/0/float, s:float/0/float · returned ndarray · level recorded 2026-09-22 a68547100f9ac8f8 · report
fixture: signature shape:tuple/1/int, device:device/0/?, repeat:bool/0/bool · returned Tensor · level recorded 2026-09-22 5fe4f2d2663019c4 · report
fixture: signature t:float/0/float, T:float/0/float, min_beta:float/0/float, max_beta:float/0/float · returned float64 · level recorded 2026-09-22 2e2761f217d28ea2 · report
b7264db66c69b50f · report
fixture: returned DiffWave · level recorded 2026-09-22 198a1df7fb1572cc · report
fixture: returned Conv1d · level recorded 2026-09-22 497936a85c54bc6d · report
fixture: returned DBlock · level recorded 2026-09-22 ebb0bb469802a389 · report
fixture: signature x:Tensor/3/float, noise_scale:Tensor/1/float · returned tuple · level recorded 2026-09-24 census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket src/wavegrad/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) ·
8d79a54df4a930fd · report
fixture: returned PositionalEncoding · level recorded 2026-09-22 f8a3be5b06628873 · report
fixture: returned UBlock · level recorded 2026-09-22 6f8762dc1bda1dfb · report
fixture: returned GaussianDiffusion · level recorded 2026-09-22 69efa1a5ec74db25 · report
fixture: signature timesteps:int/0/int, s:float/0/float · returned Tensor · level recorded 2026-09-22 2e3e510714db10cd · report
fixture: returned Attend · level recorded 2026-09-22 census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket make_a_video_pytorch/make_a_video.py ran · metamorphic tier: deterministic MIT (permissive) ·
727d939a33684dc3 · report
fixture: returned Attention · level recorded 2026-09-22 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket make_a_video_pytorch/make_a_video.py ran MIT (permissive) ·
682c7d765393b80c · report
fixture: signature x:Tensor/5/float, scale_shift:NoneType/0/?, enable_time:bool/0/bool · returned Tensor · level recorded 2026-09-24 951372c74a4810b4 · report
fixture: returned ContinuousPositionBias · level recorded 2026-09-22 b1f2e26fa3f1c03a · report
fixture: returned Downsample · level recorded 2026-09-22 aa8e97ff112091d3 · report
fixture: returned FeedForward · level recorded 2026-09-22 census: 12 implementations from 12 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 make_a_video_pytorch/make_a_video.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) ·
06c174629a88b34c · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 072e27cc3f80a64a · report
fixture: returned PseudoConv3d · level recorded 2026-09-22 7b794fd52131431f · report
fixture: returned RMSNorm · level recorded 2026-09-22 census: 6 implementations from 6 papers, 3 distinct outputs on one shared input make_a_video_pytorch/make_a_video.py ran · metamorphic tier: deterministic MIT (permissive) ·
3af3c6dc4fb09bfb · report
fixture: returned SinusoidalPosEmb · level recorded 2026-09-22 64d7b9be58329479 · report
fixture: returned Upsample · level recorded 2026-09-22 20a66373c2e74197 · report
fixture: signature t:Tensor/3/float · returned Tensor · level recorded 2026-09-22 12943eeca6896a92 · report
5d41a4f1cec5bf10 · report
47c3145df9c0d78c · report
2f7a1370a8d67d2b · report
fixture: signature num:int/0/int · returned bool · level recorded, date not recorded d1ef6b8cb9a28a53 · report
fixture: signature val:str/0/str, d:callable/0/? · returned str · level recorded, date not recorded census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64 ddm/ema.py ran · violated contract MIT (permissive) here; the stored copy is pointer only ·
aa5486a3650902d8 · report
fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64 ddm/modules.py ran · violated contract MIT (permissive) ·
608e364a9d2376a3 · report
fixture: signature x:Tensor/1/int · returned bool · level recorded, date not recorded census: 9 implementations from 12 papers, 4 distinct outputs across 3 buckets, one shared input per bucket ddm/models/gussion_diffusion.py ran MIT (permissive) ·
ce6b157509d6ed0f · report
fixture: signature a:Tensor/1/float, t:Tensor/1/int, x_shape:tuple/1/int · returned Tensor · level recorded 2026-09-24 a6f51b5e4e043215 · report
fixture: signature tensor:ndarray/4/float, nrow:int/0/int, padding:int/0/int, normalize:bool/0/bool, value_range:NoneType/0/?, scale_each:bool/0/bool, pad_value:float/0/float · returned ndarray · level recorded 2026-09-24 census: 3 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 ddm/models/gussion_diffusion.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only ·
a1229a9f4df127e2 · report
fixture: signature img:Tensor/2/float · returned Tensor · level recorded 2026-09-22 4f66ae7f14b3b240 · report
fixture: signature num:int/0/int, divisor:int/0/int · returned list · level recorded, date not recorded 907096338f4aeb9d · report
fixture: signature head:int/0/int, inputs:Tensor/4/float · returned Tensor · level recorded 2026-09-24 census: 4 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 ddm/models/gussion_diffusion.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only ·
97e1bbd232dfe092 · report
fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 3 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket ddm/amp.py unverified MIT (permissive) ·
17220aac4f6143a3 · report
af603d69433386c6 · report
fixture: returned DDPM · level recorded 2026-09-22 fdb0c6d114ad91ec · report
fixture: signature x:Tensor/3/float, conditioner:Tensor/3/float, diffusion_step:Tensor/2/float · returned tuple · level recorded 2026-09-22 14c48643b0870b0d · report
7c0915765d3543c1 · report
fixture: returned DiffuSE · level recorded 2026-09-22 4774d75a47fa7f01 · report
fixture: returned DiffusionEmbedding · level recorded 2026-09-22 876bfe8ec5fd7b3f · report
fixture: returned ResidualBlock · level recorded 2026-09-22 e3b3ff81ba235015 · report
fixture: returned SpectrogramUpsampler · level recorded 2026-09-22 0ed3f19ad55fd03b · report
fixture: returned GaussianDiffusion · level recorded 2026-09-22 96879cdcee700e0c · report
fixture: returned AttentionBlock · level recorded 2026-09-22 29d0550cf741afb4 · report
fixture: returned ModuleWrap · level recorded 2026-09-22 3d856ddc63510520 · report
fixture: returned ResnetBlock · level recorded 2026-09-22 7c91727715c14937 · report
fixture: signature input:dict/0/? · returned Tensor · level recorded 2026-09-24 census: 22 implementations from 19 papers, 2 distinct outputs on one shared input models/ddpm.py ran fingerprinted no licence file found · pointer only ·
640816aac68f1f8f · report
fixture: signature input_tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24 2c66beaf7935d8b7 · report
fixture: returned Visualizer · level recorded 2026-09-22 0ca1e090f92a7ac0 · report
fixture: signature activation_type:str/0/str · returned Swish · level recorded 2026-09-22 7d38205f97f03644 · report
fixture: signature normtype:str/0/str, num_features:int/0/int · returned GroupNorm · level recorded 2026-09-22 62a8cdfdb51ec275 · report
fixture: signature optimizer:Adam/0/?, opt:Options/0/? · returned LambdaLR · level recorded 2026-09-22 4fd186d8450dbcbf · report
fixture: signature net:callable/0/?, init_type:str/0/str, init_gain:float/0/float, gpu_ids:list/1/empty · returned SimpleNet · level recorded 2026-09-22 53ce3c3d9973db95 · report
20198eca190672b9 · report
3aeedcf101d5dc7d · report
2a992226afc81b22 · report
e77dbd5dcd7a64e5 · report
fixture: returned GaussianDiffusion · level recorded 2026-09-22 c7b63e5eb0b6e746 · report
fixture: returned Diffusion · level recorded 2026-09-22 b98427172a08955f · report
fixture: signature x:Tensor/4/float, c:Tensor/1/int · returned Tensor · level recorded 2026-09-24 dc6d407a65eed128 · report
fixture: returned GaussianDiffusion · level recorded 2026-09-22 e01f81e69257f30b · report
fixture: signature n_batch:int/0/int, op_num:int/0/int, unmask_index:int/0/int · returned Tensor · level recorded 2026-09-22 cb41bf2d4dec5aee · report
fixture: signature timesteps:int/0/int, s:float/0/float · returned ndarray · level recorded 2026-09-22 11184d08b418b129 · report
fixture: signature shape:tuple/1/int, device:device/0/?, repeat:bool/0/bool · returned Tensor · level recorded 2026-09-22 6432978c0baf82e1 · report
fixture: returned Tensor · level recorded 2026-09-22 7a95890eb48f9268 · report
fixture: signature x:Tensor/4/float, start_dim:int/0/int · returned Tensor · level recorded 2026-09-22 census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32 ddpm_torch/diffusion.py ran; the contract check could not run (RAISES) MIT (permissive) ·
9537f40a55715a66 · report
fixture: returned Tensor · level recorded 2026-09-22 02ebfe09b5931a79 · report
87e2bccf5668836a · report
0f5e41584771596b · report
fixture: returned LitEma · level recorded 2026-09-22 613acd72145a95f2 · report
fixture: signature model:callable/0/?, verbose:bool/0/bool · returned int · level recorded 2026-09-22 221b2d116fdf1032 · report
fixture: signature string:str/0/str, reload:bool/0/bool · returned type · level recorded 2026-09-22 3bd7e0cdbd131fdb · report
fixture: signature schedule:str/0/str, n_timestep:int/0/int, linear_start:float/0/float, linear_end:float/0/float, cosine_s:float/0/float · returned ndarray · level recorded 2026-09-22 104973640b230918 · report
fixture: signature shape:tuple/1/int, device:device/0/?, repeat:bool/0/bool · returned Tensor · level recorded 2026-09-22 2ad71ed8f52e942e · report
fa3d1058fa2100f3 · report
ef52d142b2c30ac2 · report
8d308f1b5ff3e211 · report
fixture: returned AttentionBlock · level recorded 2026-09-22 census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket ddpm/unet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) ·
d66519493e45fa72 · report
fixture: returned Block · level recorded 2026-09-22 census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket ddpm/unet.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) ·
e7de96f8ca95ff5c · report
fixture: returned LayerNorm · level recorded 2026-09-22 46880829e38e0fff · report
fixture: signature x:Tensor/4/float, t_emb:Tensor/2/float · returned Tensor · level recorded 2026-09-24 18a00e244e252453 · report
fixture: returned SampleLayer · level recorded 2026-09-22 ad1a66ce6aa180ac · report
fixture: returned UNetLayer · level recorded 2026-09-22 2b763cdd31b8a4c3 · report
fixture: returned UNetSampleType · level recorded 2026-09-22 census: 22 implementations from 27 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 1, kind int, dtype int64 ddpm/unet.py ran · our draft was wrong fingerprinted MIT (permissive) ·
8ceaa69aae613a28 · report
fixture: signature timesteps:Tensor/1/int, dim:int/0/int, max_period:int/0/int · returned Tensor · level recorded 2026-09-22 427f4706bac6bec1 · report
fixture: returned GaussianDiffusionTrainer · level recorded 2026-09-22 0476332a30fa6566 · report
fixture: returned QKVAttention · level recorded 2026-09-22 census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket unet.py unverified MIT (permissive) ·
8dfdf43afb2d12f4 · report
22f97d8aaa08d367 · report
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket denoising_diffusion_flax/unet.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) ·
391c56da8c23eaf6 · report
fixture: returned Attention · level recorded 2026-09-22 1a4610fe4183ab35 · report
fixture: returned AttnBlock · level recorded 2026-09-22 9e2c1a5763e42fb3 · report
fixture: returned Downsample · level recorded 2026-09-22 48203972e3caa111 · report
fixture: returned LinearAttention · level recorded 2026-09-22 bcb584e0d38fcef9 · report
fixture: returned ResnetBlock · level recorded 2026-09-22 7707d2aa5d55bd96 · report
fixture: returned Upsample · level recorded 2026-09-22 675c702c25a4d07f · report
fixture: returned WeightStandardizedConv · level recorded 2026-09-22 census: 12 implementations from 20 papers, 3 distinct outputs on one shared input denoising_diffusion_flax/unet.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) ·
f79eff565a1e33e8 · report
fixture: signature t:ArrayImpl/2/float, axis:int/0/int, eps:float/0/float · returned ArrayImpl · level recorded 2026-09-22 census: 6 implementations from 6 papers, 3 distinct outputs on one shared input denoising_diffusion_flax/unet.py unverified Apache-2.0 (permissive) ·
211d2a73ffe6de6e · report
1a3194eda8c62a2c · report
c07e06bf97316eef · report
fixture: returned GaussianDDPM · level recorded 2026-09-22 e6864f1fb21437d9 · report
fixture: signature x_t:Tensor/4/float, x_0:Tensor/4/float, t:Tensor/1/int, alphas_hat:Tensor/1/float, alphas:Tensor/1/float, betas:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 f748e43b36cd3f91 · report
fixture: signature x_t:Tensor/4/float, t:Tensor/1/int, model_noise:Tensor/4/float, alphas_hat:Tensor/1/float, betas:Tensor/1/float, alphas:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 34101c2fbe0e2264 · report
fixture: signature t:Tensor/1/int, betas_hat:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 f032dcb3c370ac3f · report
fixture: signature v:Tensor/4/float, t:Tensor/1/int, betas_hat:Tensor/1/float, betas:Tensor/1/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 c876601a41eb2278 · report
fixture: signature x_0:Tensor/2/float, alpha_hat_t:Tensor/1/float, eps:Tensor/2/float · returned Tensor · level recorded 2026-09-22 9e3526b7844286a1 · report
fixture: returned DDPM · level recorded 2026-09-22 16240e26bc3e0d99 · report
fixture: signature timesteps:int/0/int, s:float/0/float, beta_max:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-22 census: 6 implementations from 10 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 ddpm.py ran · our draft was wrong MIT (permissive) ·
6b6f39a3cb3edfa0 · report
fixture: signature x:Tensor/2/float, means:Tensor/2/float, log_scales:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32 ddpm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) ·
4707efa98ac6b989 · report
fixture: signature mean1:Tensor/2/float, logvar1:Tensor/2/float, mean2:Tensor/2/float, logvar2:Tensor/2/float · returned Tensor · level recorded 2026-09-22 30c3da436cee282c · report
fixture: returned Downsample · level recorded 2026-09-22 cb5f0757b1434dbd · report
fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24 46dd240b397d0ec1 · report
fixture: returned Upsample · level recorded 2026-09-22 e31bdc2244961428 · report
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket improved_diffusion.py unverified MIT (permissive) ·
73d112b8468812a4 · report
a5df8cda37403c5f · report
c3f34c0ceb40ba85 · report
fixture: signature W:csr_matrix/2/float, levels:int/0/int, rid:NoneType/0/? · returned tuple · level recorded 2026-09-24 69c51b713d8043fd · report
fixture: signature rr:ndarray/1/int, cc:ndarray/1/int, vv:ndarray/1/float, rid:ndarray/1/int, weights:ndarray/1/float · returned ndarray · level recorded 2026-09-24 324537dd7c7ee111 · report
fixture: signature s:int/0/int · returned str · level recorded, date not recorded 8971e8a163275348 · report
fixture: signature z:ndarray/2/float, k:int/0/int, metric:str/0/str · returned tuple · level recorded 2026-09-24 e0f51f35088884b5 · report
fixture: returned ndarray · level recorded 2026-09-24 624de6558fcd216a · report
fixture: signature grid_side:int/0/int, number_edges:int/0/int, metric:str/0/str · returned csr_matrix · level recorded 2026-09-24 856759d3dba2362b · report
fixture: signature pretrained:bool/0/bool, progress:bool/0/bool, device:str/0/str · returned MobileNetV2 · level recorded 2026-09-24 c0a5b7ee10788222 · report
fixture: signature since:float/0/float, percent:float/0/float · returned str · level recorded, date not recorded 2c594da18d824eb0 · report
38feec1f0532bdfc · report
fixture: returned Denoiser · level recorded 2026-09-22 30be19e25a2628c7 · report
fixture: returned ResidualBlock · level recorded 2026-09-22 9554f61f6e36aaf8 · report
fixture: signature schedule_mode:str/0/str, timesteps:int/0/int, max_beta:float/0/float, s:float/0/float · returned ndarray · level recorded 2026-09-22 80b8e366c165fd50 · report
92366f7e00dfa95c · report
fixture: signature diffusion_times:EagerTensor/1/float · returned tuple · level recorded 2026-09-24 af6ff6a708f6b80c · report
fixture: returned SimpleDiffusion · level recorded 2026-09-22 4 samples are 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.
census: 4 implementations from 14 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 repository not located ran · honoured contract fingerprinted licence of this copy not recorded ·
9deab2a47adbf3b7 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 fbf9ec7be545688e · report
fixture: signature val:NoneType/0/?, d:str/0/str · returned str · level recorded 2026-09-22 census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32 · arg 2: rank 1, kind int, dtype int64 repository not located ran · our draft was wrong licence of this copy not recorded ·
a15cfd7932844ef9 · report
fixture: signature a:Tensor/1/float, t:Tensor/1/int, x_shape:tuple/1/int · returned Tensor · level recorded, date not recorded census: 5 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 repository not located ran · honoured contract licence of this copy not recorded ·
d9caeeced554450f · report
fixture: returned Tensor · 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.
43 assemblies on this paper: 43 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
43 sibling assemblies for Denoising Diffusion Probabilistic Models (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 43 sibling assemblies; the other 31 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 11 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- DDPM entry · level 0 · unverified ·
2ad71ed8f52e942e - DiffusionWrapper helper · level 0 · unverified ·
fa3d1058fa2100f3 - LitEma helper · level 1 · ran ·
0f5e41584771596b - count_params helper · level 1 · ran · honoured contract ·
613acd72145a95f2 - default helper · level 1 · ran · violated contract ·
fbf9ec7be545688e - exists helper · level 1 · ran · violated contract ·
608e364a9d2376a3 - extract_into_tensor helper · level 1 · ran · our draft was wrong ·
a15cfd7932844ef9 - make_beta_schedule helper · level 1 · ran · honoured contract ·
3bd7e0cdbd131fdb - noise_like helper · level 1 · ran; the contract check could not run (RAISES) ·
104973640b230918 - instantiate_from_config helper · level 0 · unverified ·
ef52d142b2c30ac2 - get_obj_from_str helper · level 1 · ran · our draft was wrong ·
221b2d116fdf1032
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 15 bricks; individually on a fixture: 10 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- DDPModel entry · level 0 · unverified ·
9d6fea4b2c4c1b1f - SpaceToDepth helper · level 1 · ran ·
7c91727715c14937 - Unet helper · level 0 · unverified ·
20198eca190672b9 - Visualizer helper · level 1 · ran ·
2c66beaf7935d8b7 - get_scheduler helper · level 1 · ran · our draft was wrong ·
62a8cdfdb51ec275 - init_net helper · level 1 · ran · our draft was wrong ·
4fd186d8450dbcbf - UnetSkipModule helper · level 0 · unverified ·
3aeedcf101d5dc7d - get_activation_class helper · level 1 · ran · our draft was wrong ·
0ca1e090f92a7ac0 - init_weights helper · level 0 · unverified ·
2a992226afc81b22 - AttentionBlock helper · level 1 · ran ·
96879cdcee700e0c - ModuleWrap helper · level 1 · ran ·
29d0550cf741afb4 - ResnetBlock helper · level 1 · ran ·
3d856ddc63510520 - get_norm_class helper · level 1 · ran · our draft was wrong ·
7d38205f97f03644 - Swish helper · level 1 · ran ·
640816aac68f1f8f - TensorLinear helper · level 0 · unverified ·
53ce3c3d9973db95
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 7 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 3 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- GaussianDiffusion entry · level 1 · ran ·
dc6d407a65eed128 - default helper · level 1 · ran · violated contract ·
fbf9ec7be545688e - exists helper · level 1 · ran · violated contract ·
608e364a9d2376a3 - extract helper · level 0 · unverified ·
09c8479d9a5b3e06 - generate_inprint_mask helper · level 1 · ran · violated contract ·
e01f81e69257f30b - linear_schedule scheduler · level 1 · ran · honoured contract ·
cb41bf2d4dec5aee - noise_like helper · level 1 · ran; the contract check could not run (RAISES) ·
11184d08b418b129
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- DiffuSE entry · level 1 · ran ·
7c0915765d3543c1 - Conv1d helper · level 1 · ran · our draft was wrong ·
2109126c17b0f297 - DiffusionEmbedding model · level 1 · ran ·
4774d75a47fa7f01 - ResidualBlock model · level 1 · ran ·
876bfe8ec5fd7b3f - SpectrogramUpsampler model · level 1 · ran ·
e3b3ff81ba235015 - silu helper · level 1 · ran · honoured contract ·
d9caeeced554450f
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 9 bricks; individually on a fixture: 8 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 8 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 43 siblings
- MNISTDiffusion entry · level 0 · unverified ·
19089005aa95a2cd - Unet model · level 1 · ran ·
533ba10eceea02a7 - ConvBnSiLu helper · level 1 · ran ·
b3f906bb8ffb9305 - DecoderBlock helper · level 1 · ran ·
61de5d0bdb038f95 - EncoderBlock helper · level 1 · ran ·
bfa427b1e754f31a - ResidualBottleneck helper · level 1 · ran ·
24efaae94384e2f2 - TimeMLP helper · level 1 · ran ·
8a7675ca34bf8e8c - ResidualDownsample helper · level 1 · ran ·
e34dd41cf488e665 - ChannelShuffle helper · level 1 · ran ·
69f27ba78fe269cb
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 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 43 siblings
- SimpleDiffusion entry · level 1 · ran ·
af6ff6a708f6b80c
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 4 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- GaussianDiffusion entry · level 1 · ran ·
6f2ab90303c6391c - ext helper · level 1 · ran; the contract check could not run (RAISES) ·
97aabd2621b6733c - get_betas scheduler · level 1 · ran · honoured contract ·
fab86763be9d382c - betas_for_alpha_bar helper · level 1 · ran · honoured contract ·
7eb19b2d745af94f
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 8 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- GaussianDiffusion entry · level 1 · ran ·
86ee0ef9ccc062c4 - cosine_beta_schedule helper · level 1 · ran · honoured contract ·
62afec33f38bb212 - default helper · level 1 · ran · honoured contract ·
e3122a1351004542 - extract helper · level 0 · unverified ·
09c8479d9a5b3e06 - linear_beta_schedule helper · level 1 · ran · honoured contract ·
482723f534770483 - normalise_to_negative_one_to_one helper · level 1 · ran · violated contract ·
a9907c856452e8f6 - unnormalise_to_zero_to_one helper · level 1 · ran · honoured contract ·
ae85de96d538f79a - exists helper · level 1 · ran · violated contract ·
d98bef4c38be4932
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 19 bricks; individually on a fixture: 16 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 3 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- SpaceTimeUnet entry · level 0 · unverified ·
5d41a4f1cec5bf10 - Downsample model · level 1 · ran ·
b1f2e26fa3f1c03a - PseudoConv3d model · level 1 · ran ·
072e27cc3f80a64a - ResnetBlock model · level 0 · unverified ·
12943eeca6896a92 - SinusoidalPosEmb helper · level 1 · ran ·
3af3c6dc4fb09bfb - SpatioTemporalAttention model · level 0 · unverified ·
47c3145df9c0d78c - Upsample model · level 1 · ran ·
64d7b9be58329479 - divisible_by helper · level 2 · ran · violated contract ·
856d86b39c6005b4 - exists helper · level 1 · ran · violated contract ·
aa5486a3650902d8 - default helper · level 1 · ran · violated contract ·
60fff7c3c400d7ff - Block model · level 1 · ran ·
682c7d765393b80c - Attention model · level 1 · ran ·
727d939a33684dc3 - ContinuousPositionBias helper · level 1 · ran ·
951372c74a4810b4 - FeedForward helper · level 1 · ran ·
aa8e97ff112091d3 - RMSNorm helper · level 1 · ran ·
7b794fd52131431f - Attend helper · level 1 · ran ·
2e3e510714db10cd - GEGLU helper · level 1 · ran ·
06c174629a88b34c - shift_token helper · level 1 · ran; the contract check could not run (RAISES) ·
20a66373c2e74197 - once helper · level 1 · ran · our draft was wrong ·
52e10a7d6b0fa036
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 13 bricks; individually on a fixture: 11 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 2 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- GaussianDiffusion entry · level 0 · unverified ·
2e2761f217d28ea2 - Denoiser model · level 1 · ran ·
312abccdd2ea163d - default helper · level 1 · ran · violated contract ·
fbf9ec7be545688e - extract helper · level 0 · unverified ·
09c8479d9a5b3e06 - get_noise_schedule_list helper · level 1 · ran · honoured contract ·
372f8ce0b71e834d - noise_like helper · level 1 · ran; the contract check could not run (RAISES) ·
a68547100f9ac8f8 - ConvNorm helper · level 1 · ran ·
b0a153607e31ff3c - DiffusionEmbedding helper · level 1 · ran ·
2bbf0db2a024a96d - LinearNorm helper · level 1 · ran ·
752e01f02bca6161 - Mish helper · level 1 · ran ·
1c918e79d462a26b - ResidualBlock helper · level 1 · ran ·
17bc8409599d140b - exists helper · level 1 · ran · violated contract ·
608e364a9d2376a3 - vpsde_beta_t helper · level 1 · ran · honoured contract ·
5fe4f2d2663019c4
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 17 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- TimeUnet entry · level 0 · unverified ·
603b6348fb74fb22 - AttentionBlock model · level 1 · ran ·
39e408d858270810 - Downsample model · level 1 · ran ·
621e4b433c363624 - ResBlock model · level 1 · ran ·
d1ba7d3cb6a2ac54 - TimestepEmbedSequential helper · level 0 · unverified ·
f7f131ff4e466645 - Upsample model · level 1 · ran ·
1ce7357760c5ddb5 - conv_nd helper · level 0 · unverified ·
49ff3519834529f3 - linear helper · level 0 · unverified ·
7705d2253b6cd3eb - normalization helper · level 1 · ran · our draft was wrong ·
7bab05ad7b9fa652 - timestep_embedding helper · level 1 · ran · our draft was wrong ·
88867f4df8cef2a9 - zero_module helper · level 1 · ran · our draft was wrong ·
129b804760b3115f - QKVAttention helper · level 1 · ran ·
a5638e9931779103 - QKVAttentionLegacy helper · level 1 · ran ·
1c07b81f544f048b - avg_pool_nd helper · level 0 · unverified ·
51950b12318e7d94 - TimestepBlock helper · level 0 · unverified ·
d6cc5a7817ff7f5d - GroupNorm32 helper · level 1 · ran ·
da485dc2b10fd6d7 - count_flops_attn helper · level 0 · unverified ·
6e9c81a619f204c5
harvested Assembly for Denoising Diffusion Probabilistic Models (graph method: Denoising Diffusion Probabilistic Models). 11 bricks; individually on a fixture: 8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 43 siblings
- UNet entry · level 0 · unverified ·
9be15362b1dd74ae - HelperModule helper · level 0 · unverified ·
394400bd8d814f2c - UNetLayer model · level 1 · ran ·
ad1a66ce6aa180ac - UNetSampleType helper · level 1 · ran ·
2b763cdd31b8a4c3 - timestep_embedding model · level 1 · ran · our draft was wrong ·
8ceaa69aae613a28 - AttentionBlock model · level 1 · ran ·
8d308f1b5ff3e211 - ResnetBlock model · level 1 · ran ·
46880829e38e0fff - SampleLayer model · level 1 · ran ·
18a00e244e252453 - LayerNorm model · level 1 · ran ·
e7de96f8ca95ff5c - Block model · level 1 · ran ·
d66519493e45fa72 - ScaleBlock model · level 0 · unverified ·
5f9cd1cf5c070128
- GaussianDiffusion · 360bd5d6e42c23e4 · 10 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 6 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
- Unet · 372bae93c1057fea · 10 bricks; individually on a fixture: 8 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; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
- GaussianDiffusion · 393ce06bab20a086 · 10 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 6 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
- WaveGrad · 39e995526e6df5ea · 6 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
- MyDDPM · 3c2f90d5146b8621 · 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 · assemblies[16] in the JSON twin
- GaussianDiffusion · 4082c6db308bde21 · 12 bricks; individually on a fixture: 10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
- denoise · 5020e87668455d14 · 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
- DDPM · 5061f7172418a016 · 6 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
- Diffusion · 5647c3846eafab5e · 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 · assemblies[20] in the JSON twin
- GaussianDiffusionTrainer · 5a2bf53c4496f6f9 · 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
- GaussianDiffusion · 6690df1b5a16b232 · 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 · assemblies[22] in the JSON twin
- UNetModel · 6885b4908ddd62c0 · 17 bricks; individually on a fixture: 8 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; 4 where Syntology's instrument failed) · 9 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
- CosineSchedule · 8029d8e11527eb22 · 2 bricks; 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
- EDMPrecond · 8e62cf03e8491df7 · 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 · assemblies[25] in the JSON twin
- DDPM · 94a0177f4eb8eb81 · 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 · assemblies[26] in the JSON twin
- GaussianDDPM · 97878809030fe2ac · 7 bricks; individually on a fixture: 6 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; 5 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[27] in the JSON twin
- GaussianDiffusion · 99773f90d1b9428b · 5 bricks; individually on a fixture: 3 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; 3 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
- diffusion_model · a204124bad1acf99 · 5 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) · 4 unverified · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
- UNet · a51bd1c903a3799d · 14 bricks; individually on a fixture: 11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
- DiffWave · a528fe11e6c876eb · 6 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[31] in the JSON twin
- DDPM · a5ba55b50bd03085 · 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 · assemblies[32] in the JSON twin
- Unet · b905ee9f30b17a03 · 13 bricks; individually on a fixture: 12 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
- UNetModel · b9de44efc2c5c5b6 · 20 bricks; individually on a fixture: 10 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified · The assembly has not been run end-to-end · assemblies[34] in the JSON twin
- GaussianDiffusion · bd20663f84db2a9f · 2 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[35] in the JSON twin
- DDPM · c5eda2bba95e3b71 · 10 bricks; individually on a fixture: 7 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[36] in the JSON twin
- Denoiser · ce08c89cf192552a · 13 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified · The assembly has not been run end-to-end · assemblies[37] in the JSON twin
- DiffusionModel · d752259d6d7c1fe4 · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[38] in the JSON twin
- DDPM · e63599da09892a24 · 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[39] in the JSON twin
- GaussianDiffusion · ef210444fbcb8488 · 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[40] in the JSON twin
- Unet · f1637ef028d9661b · 5 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) · 4 unverified · The assembly has not been run end-to-end · assemblies[41] in the JSON twin
- DiffWave · fdc040dbfb3c01eb · 6 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[42] 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="2006.11239") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Density Estimation | CIFAR-10 | DDPM | NLL (bits/dim) | 3.69 | #14 of 15 | Archive leaderboard | report |
| Image Generation | CIFAR-10 | Denoising Diffusion | FID | 3.17 | #28 of 78 | Archive leaderboard | report |
| Image Generation | ImageNet 32x32 | DDPM | FID | 16.18 | #11 of 35 | Archive leaderboard | report |
| Image Generation | ImageNet 32x32 | DDPM | bpd | 3.89 | #11 of 35 | Archive leaderboard | report |
| Image Generation | LSUN Bedroom | Denoising Diffusion Probabilistic Model | FID-50k | 4.9 | #2 of 3 | Archive leaderboard | report |
| Image Generation | LSUN Bedroom 256 x 256 | Denoising Diffusion Probabilistic Model (large) | FID | 4.9 | #11 of 32 | Archive leaderboard | report |
| Image Generation | LSUN Bedroom 256 x 256 | Denoising Diffusion Probabilistic Model | FID | 6.36 | #14 of 32 | Archive leaderboard | report |
| Image Generation | LSUN Bedroom 256 x 256 | Denoising Diffusion Probabilistic Model (large, DINOv2) | FD | 229.76 | #22 of 32 | Archive leaderboard | report |
| Image Generation | LSUN Bedroom 256 x 256 | Denoising Diffusion Probabilistic Model (large, DINOv2) | Precision | 0.79 | #22 of 32 | Archive leaderboard | report |
| Image Generation | LSUN Bedroom 256 x 256 | Denoising Diffusion Probabilistic Model (large, DINOv2) | Recall | 0.61 | #22 of 32 | Archive leaderboard | report |
| Image Generation | LSUN Cat 256 x 256 | Denoising Diffusion Probabilistic Model | FID | 19.75 | #6 of 8 | Archive leaderboard | report |
| Image Generation | LSUN Churches 256 x 256 | Denoising Diffusion Probabilistic Model | FID | 7.89 | #22 of 27 | 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: Diffusion
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