Papers › Neural Ordinary Differential Equations

Neural Ordinary Differential Equations

19 Jun 2018NeurIPS 2018 12arXiv:1806.07366archive 2025-07-28

Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud

We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black-box differential equation solver. These continuous-depth models have constant memory cost, adapt their evaluation strategy to each input, and can explicitly trade numerical precision for speed. We demonstrate these properties in continuous-depth residual networks and continuous-time latent variable models. We also construct continuous normalizing flows, a generative model that can train by maximum likelihood, without partitioning or ordering the data dimensions. For training, we show how to scalably backpropagate through any ODE solver, without access to its internal operations. This allows end-to-end training of ODEs within larger models.

PaperPDFConference PDFCodeCode 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

No sample from the archive's official repository (rtqichen/torchdiffeq) is linked to this paper; the 124 samples below come from 25 community repositories. Syntology harvested code from rtqichen/torchdiffeq for 2 other papers.

rtqichen/torchdiffeq: Syntology's graph links these samples to "Hey, that's not an ODE": Faster ODE Adjoints via Seminorms (arXiv:2009.09457; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified) and Speeding up astrochemical reaction networks with autoencoders and neural ODEs (arXiv:2312.06015; that paper's own run record: 5 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; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.

Syntology 124 code samples harvested from 25 repositories linked to this paper: 98 ran (of which 44 constructed an object rather than computing a result; 64 with no instrument failure: 2 honoured, 5 violated, 57 with no contract checked; 34 where Syntology's instrument failed) · 26 unverified. Where Syntology's instrument failed: 26 where our contract draft was wrong; 8 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 124 samples from 25 repositories, 98 ran (64 with no instrument failure; 34 where Syntology's instrument failed). 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 10 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.

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

rtqichen/torchdiffeq officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to "Hey, that's not an ODE": Faster ODE Adjoints via Seminorms (arXiv:2009.09457; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified) and Speeding up astrochemical reaction networks with autoencoders and neural ODEs (arXiv:2312.06015; that paper's own run record: 5 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; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
000Justin000/torchdiffeq mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Jump Stochastic Differential Equations (arXiv:1905.10403; that paper's own run record: 4 ran (of which 0 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) · 1 unverified); nothing checks that they implement this paper's method. report
5yearsKim/HamiltonianFlow mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
AlphaGergedan/Sampling-HNNs mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training Hamiltonian neural networks without backpropagation (arXiv:2411.17511; that paper's own run record: 0 ran · 5 unverified); nothing checks that they implement this paper's method. report
BruceNolascoFC/RN-2021-1 mentioned on GitHubpytorchSyntology: 10 samples, 8 ran (5 instrument-failed) · 2 unverified report
DrChainsaw/neuralODE4j mentioned on GitHubpytorchMITSyntology: not harvested report
GitTeaching/Predicting-using-Neural-ODE mentioned on GitHubSyntology: not harvested report
HolmesShuan/OISR-PyTorch mentioned on GitHubpytorchBSD-2-ClauseSyntology: 6 samples, 6 ran (3 instrument-failed) · 0 unverified report
HosseinEbrahimiK/Normalizing-Flows-Reproducing mentioned on GitHubpytorchSyntology: not harvested report
HosseinEbrahimiK/TrajectoryNet-Reproducing mentioned on GitHubpytorchSyntology: not harvested report
JSeam2/Neural-Ordinary-Differential-Equations mentioned on GitHubSyntology: not harvested report
Junghwan-brian/SDE-Net mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (arXiv:1612.01474; that paper's own run record: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified) and SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates (arXiv:2008.10546; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Lauu1023/ODENet mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
MilesCranmer/lagrangian_nns mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hamiltonian Neural Networks (arXiv:1906.01563; that paper's own run record: 4 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; 3 where Syntology's instrument failed) · 3 unverified) and Lagrangian Neural Networks (arXiv:2003.04630; that paper's own run record: 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) · 0 unverified); nothing checks that they implement this paper's method. report
PranavMahajan25/Neural-ODE mentioned on GitHubSyntology: not harvested report
RainerGasper/NeuralODE mentioned on GitHubSyntology: not harvested report
StuartHadfield/neural-odes mentioned on GitHubSyntology: not harvested report
TheStageAI/TorchIntegral mentioned on GitHubpytorchSyntology: 11 samples, 8 ran (4 instrument-failed) · 3 unverified report
UofTrees/ProjectX2020 mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
ZainRaza14/Neural-ODE mentioned on GitHubSyntology: not harvested report
abaietto/neural_ode_classification mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
alexandrejash/Chivvo mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (1 instrument-failed) · 0 unverified report
amirgholami/anode mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs (arXiv:1902.10298; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
boschresearch/numerics_independent_neural_odes mentioned on GitHubpytorchSyntology: 10 samples, 4 ran (3 instrument-failed) · 6 unverified report
caidao22/pkg-cams mentioned on GitHubBSD-2-ClauseSyntology: not harvested report
copperwire/neural_ode mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
dlinzner-bcs/min_neuralODEs mentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
feicccccccc/Neural-ODE-Ex mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
gabrevaya/LatentDiffEq mentioned on GitHubMITSyntology: not harvested report
gabrevaya/LatentDiffEq.jl mentioned on GitHubMITSyntology: not harvested report
geoffsmith/gan-ode mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
ipeter50/graph_ode mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
jacobjinkelly/easy-neural-ode mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Differential Equations that are Easy to Solve (arXiv:2007.04504; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
johnhw/simple_neural_ode mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
jrbotvinick/learning-dynamics-on-invariant-measures mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
kakao/DAFT mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
kfallah/NODE-Denoiser mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
locuslab/monotone_op_net mentioned on GitHubpytorchSyntology: not harvested report
lye0618/torchdiffeq mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
m-qiang/cortexode mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
mandubian/neural-ode mentioned on GitHubtfMITSyntology: not harvested report
mandubian/pytorch-neural-ode mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
msurtsukov/neural-ode mentioned on GitHubpytorchSyntology: not harvested report
narock/machine_learning mentioned on GitHubGPL-3.0Syntology: not harvested report
patrick-kidger/FasterNeuralDiffEq mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to "Hey, that's not an ODE": Faster ODE Adjoints via Seminorms (arXiv:2009.09457; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
rg321/anode_mtvso mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
teopb/ode-net-examples mentioned on GitHubpytorchSyntology: 33 samples, 27 ran (9 instrument-failed) · 6 unverified report
tianfr/mononerf mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
titu1994/tfdiffeq mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Universal Differential Equations for Scientific Machine Learning (arXiv:2001.04385; that paper's own run record: 4 ran (of which 0 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); nothing checks that they implement this paper's method. report
wkirgsn/thermal-nn mentioned on GitHubtfMITSyntology: not harvested report
xuanqing94/torchdiffeq mentioned on GitHubpytorchSyntology: 14 samples, 12 ran (2 instrument-failed) · 2 unverified report
xwinxu/bayesde mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scalable Gradients for Stochastic Differential Equations (arXiv:2001.01328; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified) and Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations (arXiv:2102.06559; that paper's own run record: 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) · 3 unverified); nothing checks that they implement this paper's method. report
xwinxu/bayesian-sde mentioned on GitHubjaxSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
zhuqunxi/My_numpy_NODE mentioned on GitHubSyntology: not harvested report
MichaelKonobeev/neuralode-rl tfMITSyntology: not harvested report
dungxibo123/neural_ode pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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

124 samples harvested: 98 ran (of which 44 constructed an object rather than computing a result; 64 with no instrument failure: 2 honoured, 5 violated, 57 with no contract checked; 34 where Syntology's instrument failed) · 26 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.

2ran · honoured contract
5ran · violated contract
26ran · our draft was wrong
8ran; the contract check could not run
57ran
26unverified

Licence: 43 of the 124 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 25 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. “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 2 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.

5yearsKim/HamiltonianFlow community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
Euler anode/odesolver.py ran GPL-3.0 (copyleft) · pointer only · 9406c2abc025c528 · report fixture: returned Euler · level recorded 2026-09-22
RK2 anode/odesolver.py ran GPL-3.0 (copyleft) · pointer only · 33a0d576e23c028f · report fixture: returned RK2 · level recorded 2026-09-22
RK4 anode/odesolver.py ran GPL-3.0 (copyleft) · pointer only · 1fc91b40082e955e · report fixture: returned RK4 · level recorded 2026-09-22
Time_Stepper anode/odesolver.py ran GPL-3.0 (copyleft) · pointer only · 78706994d851e4b4 · report fixture: returned Time_Stepper · level recorded 2026-09-22
odesolver anode/odesolver.py ran; the contract check could not run (RAISES) GPL-3.0 (copyleft) · pointer only · 3479205146fe5947 · report fixture: signature func:callable/0/?, z0:Tensor/2/float, options:dict/0/?, reverse:bool/0/bool · returned Tensor · level recorded 2026-09-22
BruceNolascoFC/RN-2021-1 community (archive-listed) 10 samples, 8 ran (5 instrument-failed) · 2 unverified
build_case tensor_ode_solver.py ran no licence file found · pointer only · 1954ce4f7b5742a7 · report fixture: returned dict · level recorded 2026-09-22
dynamic_from_signals tensor_ode_solver.py ran · our draft was wrong no licence file found · pointer only · 2aee82e2cf39316d · report fixture: signature us:callable/0/?, ls:callable/0/? · returned function · level recorded 2026-09-22
input_jacobian tensor_ode_solver.py ran · our draft was wrong no licence file found · pointer only · a06d1d8f938ae9f4 · report fixture: signature model:callable/0/?, t:float/0/float, z:list/1/float, numpy_comp:bool/0/bool · returned ndarray · level recorded 2026-09-22
integrable_from_model tensor_ode_solver.py ran · our draft was wrong no licence file found · pointer only · 2285415039c52b05 · report fixture: signature model:callable/0/?, input_shape:Size/1/int · returned function · level recorded 2026-09-22
randomGaussianWalk tensor_ode_solver.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a69334ba86c0588e · report fixture: signature starttime:float/0/float, endtime:float/0/float, samples:int/0/int, initial:float/0/float, drift:float/0/float, std:float/0/float · returned tuple · level recorded 2026-09-22
randomState tensor_ode_solver.py ran no licence file found · pointer only · c58084b51168dca6 · report fixture: returned ndarray · level recorded 2026-09-22
x tensor_ode_solver.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 93721216ebb5b002 · report fixture: signature state:Tensor/1/float · returned Tensor · level recorded 2026-09-22
y tensor_ode_solver.py ran · violated contract fingerprinted no licence file found · pointer only · 0dcc609ed16c99d9 · report fixture: signature state:Tensor/1/float · returned Tensor · level recorded 2026-09-22
Dynamic tensor_ode_solver.py unverified no licence file found · pointer only · 02793af9d30a0ad2 · report
flat_param_jacobian tensor_ode_solver.py unverified no licence file found · pointer only · 0b628441d9a6d4da · report
HolmesShuan/OISR-PyTorch community (archive-listed) 6 samples, 6 ran (3 instrument-failed) · 0 unverified
calc_psnr in 26 papers NTIRE2019/OISR/src/utility.py ran BSD-2-Clause (permissive) here; the stored copy is pointer only · d4592ac83c04a5fd · report fixture: signature sr:Tensor/4/float, hr:Tensor/4/float, scale:int/0/int, rgb_range:int/0/int, dataset:DummyDatasetWrapper/0/? · returned float · level recorded 2026-09-24
default_conv in 70 papers NTIRE2019/OISR/src/model/common.py ran · our draft was wrong BSD-2-Clause (permissive) · 8b0e794d4d8f9b13 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, bias:bool/0/bool · returned Conv2d · level recorded 2026-09-22
logsumexp_2d in 14 papers NTIRE2019/OISR/src/model/cbam.py ran · our draft was wrong fingerprinted BSD-2-Clause (permissive) · 7abfa32a2f1d7424 · report fixture: signature tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-22
make_optimizer in 32 papers NTIRE2019/OISR/src/utility.py ran BSD-2-Clause (permissive) · f250aafdaa7f4526 · report fixture: signature args:Args/0/?, my_model:callable/0/? · returned Adam · level recorded 2026-09-26
projection_conv NTIRE2019/OISR/src/model/ddbpn.py ran BSD-2-Clause (permissive) · 3cadb1fed3be1893 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, scale:int/0/int, up:bool/0/bool · returned ConvTranspose2d · level recorded 2026-09-25
quantize in 70 papers
census: 8 implementations from 11 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
NTIRE2019/OISR/src/utility.py ran · our draft was wrong fingerprinted BSD-2-Clause (permissive) here; the stored copy is pointer only · b1c1acd3c89a39f3 · report fixture: signature img:Tensor/2/float, rgb_range:float/0/float · returned Tensor · level recorded 2026-09-24
Lauu1023/ODENet community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
find_parameters _impl/adjoint.py ran MIT (permissive) · 216ff008ef437b80 · report fixture: signature module:callable/0/? · returned list · level recorded 2026-09-26
g_and_explicit_phi _impl/adams.py ran MIT (permissive) · 94c5d03613990039 · report fixture: signature prev_t:list/1/Tensor, next_t:Tensor/0/float, implicit_phi:list/1/tuple, k:int/0/int · returned tuple · level recorded 2026-09-25
rk4_alt_step_func in 5 papers _impl/rk_common.py ran MIT (permissive) · 40dadd966f2c36ab · report fixture: signature func:callable/0/?, t:Tensor/0/float, dt:Tensor/0/float, y:Tensor/2/float, k1:NoneType/0/? · returned Tensor · level recorded 2026-09-26
rk4_step_func _impl/rk_common.py ran MIT (permissive) · a4138cedf5f8608e · report fixture: signature func:callable/0/?, t:Tensor/0/float, dt:Tensor/0/float, y:Tensor/2/float, k1:NoneType/0/? · returned Tensor · level recorded 2026-09-26
odeint_adjoint _impl/adjoint.py unverified MIT (permissive) · 773c458752a32b7a · report
TheStageAI/TorchIntegral community (archive-listed) 11 samples, 8 ran (4 instrument-failed) · 3 unverified
IGrid torch_integral/model.py ran Apache-2.0 (permissive) · 62feec9141b4e5c3 · report fixture: returned IGrid · level recorded 2026-09-22
ParametrizedModel torch_integral/model.py ran Apache-2.0 (permissive) · 6a10221436726b78 · report fixture: returned ParametrizedModel · level recorded 2026-09-22
PrunableModel torch_integral/model.py ran Apache-2.0 (permissive) · d8a06e2aaf08a085 · report fixture: returned PrunableModel · level recorded 2026-09-22
TrainableGrid1D torch_integral/model.py ran Apache-2.0 (permissive) · 60b35461edf3f214 · report fixture: returned TrainableGrid1D · level recorded 2026-09-22
get_attr_by_name torch_integral/model.py ran · our draft was wrong Apache-2.0 (permissive) · aa235b32d88c1eed · report fixture: signature module:callable/0/?, name:str/0/str · returned Linear · level recorded 2026-09-22
get_parent_module torch_integral/model.py ran · our draft was wrong Apache-2.0 (permissive) · ddb0f75fbab8b97a · report fixture: signature module:callable/0/?, attr_path:str/0/str · returned Linear · level recorded 2026-09-22
get_parent_name torch_integral/model.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 019bd750e2303b7e · report fixture: signature qualname:str/0/str · returned tuple · level recorded 2026-09-22
remove_parametrizations torch_integral/model.py ran · our draft was wrong Apache-2.0 (permissive) · 63dd824e61be8e94 · report fixture: signature model:callable/0/? · returned dict · level recorded 2026-09-22
IntegralModel torch_integral/model.py unverified Apache-2.0 (permissive) · 9e070cde035db353 · report
reapply_parametrizations torch_integral/model.py unverified Apache-2.0 (permissive) · 242605ed25603835 · report
reset_batchnorm torch_integral/model.py unverified Apache-2.0 (permissive) · 897a3625721985ef · report
UofTrees/ProjectX2020 community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
Data in 7 papers mr_node/model/odefunc.py ran no licence file found · pointer only · afcd5754477bf8a7 · report fixture: returned Data · level recorded 2026-09-22
pairwise in 27 papers mr_node/model/odefunc.py ran · our draft was wrong no licence file found · pointer only · acc109795f939462 · report fixture: signature iterable:list/1/int · returned zip · level recorded 2026-09-22
ODEFunc in 9 papers mr_node/model/odefunc.py unverified no licence file found · pointer only · ca95388e3abbb9e0 · report
abaietto/neural_ode_classification community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ODENet models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 6bbb55a0b9a1ee9c · report fixture: returned ODENet · level recorded 2026-09-22
alexandrejash/Chivvo community (archive-listed) 5 samples, 5 ran (1 instrument-failed) · 0 unverified
Euler anode/odesolver.py ran GPL-3.0 (copyleft) · pointer only · 6fba12214cae5e2d · report fixture: returned Euler · level recorded 2026-09-22
RK2 anode/odesolver.py ran GPL-3.0 (copyleft) · pointer only · 5512b8d472ebad2a · report fixture: returned RK2 · level recorded 2026-09-22
RK4 anode/odesolver.py ran GPL-3.0 (copyleft) · pointer only · 127c92027e96c4f8 · report fixture: returned RK4 · level recorded 2026-09-22
Time_Stepper anode/odesolver.py ran GPL-3.0 (copyleft) · pointer only · 2c812a9f084716eb · report fixture: returned Time_Stepper · level recorded 2026-09-22
odesolver anode/odesolver.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant GPL-3.0 (copyleft) · pointer only · d1f5a2c0003cf2df · report fixture: signature func:callable/0/?, z0:Tensor/2/float, options:dict/0/? · returned Tensor · level recorded 2026-09-22
boschresearch/numerics_independent_neural_odes community (archive-listed) 10 samples, 4 ran (3 instrument-failed) · 6 unverified
ODENet models/models.py ran · metamorphic tier: deterministic fingerprinted AGPL-3.0 (copyleft) · pointer only · ce3b538793b44a3f · report fixture: returned ODENet · level recorded 2026-09-22
load_yaml in 107 papers models/models.py ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · 0e64c9442199a010 · report fixture: returned dict · level recorded 2026-09-22
load_yaml_values models/models.py ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · e0a9dd130bc8e029 · report fixture: returned dict · level recorded 2026-09-22
merge_dicts in 14 papers models/models.py ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · 5c104e6fea609913 · report fixture: signature opts_dict:dict/0/?, parser_opts:Namespace/0/? · returned dict · level recorded 2026-09-22
BaseDataset in 5 papers models/models.py unverified AGPL-3.0 (copyleft) · pointer only · abebc71e7f1ca56a · report
ExperimentOptions models/models.py unverified AGPL-3.0 (copyleft) · pointer only · a20f8065b0c3fffe · report
ODEBlock models/models.py unverified AGPL-3.0 (copyleft) · pointer only · 9158a9a96f605d3f · report
find_dataset_class models/models.py unverified AGPL-3.0 (copyleft) · pointer only · 762ad558c1d13aeb · report
mkdir in 12 papers models/models.py unverified AGPL-3.0 (copyleft) · pointer only · 9012d6958edc86f1 · report
mkdirs in 7 papers models/models.py unverified AGPL-3.0 (copyleft) · pointer only · f81cc7d6c4c87870 · report
copperwire/neural_ode community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
OdeSolver src/ode_solvers/solvers.py ran no licence file found · pointer only · fd17b14e17a04cc7 · report fixture: returned OdeSolver · level recorded 2026-09-22
dlinzner-bcs/min_neuralODEs community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
neuralODE neuralODEs/neuralODE.py ran no licence file found · pointer only · a94209f6fc808fe0 · report fixture: returned neuralODE · level recorded 2026-09-22
feicccccccc/Neural-ODE-Ex community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
ODEAdjoint NeuralODE.py ran MIT (permissive) · a932ba75143e9ecb · report fixture: returned ODEAdjoint · level recorded 2026-09-22
ode_solve NeuralODE.py ran · our draft was wrong MIT (permissive) · 8193789421b9bce3 · report fixture: signature z0:Tensor/2/float, t0:Tensor/0/float, t1:Tensor/0/float, f:callable/0/? · returned Tensor · level recorded 2026-09-22
NeuralODE NeuralODE.py unverified MIT (permissive) · 0be1257af72d80c3 · report
ODEfunc in 6 papers NeuralODE.py unverified MIT (permissive) · c05e6f04ee48cfca · report
geoffsmith/gan-ode community (archive-listed) 1 sample, 0 ran · 1 unverified
odeint torchdiffeq/_impl/odeint.py unverified MIT (permissive) · 442b903271deea5e · report
ipeter50/graph_ode community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
MLP in 375 papers odegnn.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · a963843951a2916d · report fixture: signature inputs:Tensor/3/float · returned Tensor · level recorded 2026-09-22
EncoderFunc odegnn.py unverified MIT (permissive) · 257d0ccfbbff4f5d · report
johnhw/simple_neural_ode community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
forward in 75 papers neural_ode.py ran; the contract check could not run (RAISES) MIT (permissive) · 6a5e35d9dcd92ff6 · report fixture: signature x0:ndarray/1/float, f:callable/0/?, t0:float/0/float, t1:float/0/float · returned ndarray · level recorded 2026-09-22
jrbotvinick/learning-dynamics-on-invariant-measures community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
traj_NODE Comparison/NODE_func.py ran · our draft was wrong no licence file found · pointer only · 6874ebf43b4dccd5 · report fixture: returned tuple · level recorded 2026-09-22
kakao/DAFT community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
DAFT model.py ran Apache-2.0 (permissive) · 43b0462e8ae59a39 · report fixture: returned DAFT · level recorded 2026-09-22
linear in 88 papers model.py ran · our draft was wrong Apache-2.0 (permissive) · e9ac3eb9d2ad7232 · report fixture: signature in_dim:int/0/int, out_dim:int/0/int, bias:bool/0/bool · returned Linear · level recorded 2026-09-22
kfallah/NODE-Denoiser community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ODEBlock models/NODE.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 59f408ca8aaaf9f3 · report fixture: returned ODEBlock · level recorded 2026-09-22
lye0618/torchdiffeq community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
rk4_alt_step_func in 5 papers torchdiffeq/_impl/rk_common.py ran MIT (permissive) · 915f7ec0ef60ec9a · report fixture: signature func:callable/0/?, t:float/0/float, dt:float/0/float, y:tuple/1/Tensor, k1:tuple/1/Tensor · returned tuple · level recorded 2026-09-25
rk4_step_func torchdiffeq/_impl/rk_common.py ran MIT (permissive) · 3e2bf9b07fd9cfc5 · report fixture: signature func:callable/0/?, t:Tensor/0/float, dt:Tensor/0/float, y:tuple/1/Tensor, k1:NoneType/0/? · returned tuple · level recorded 2026-09-25
odeint_adjoint torchdiffeq/_impl/adjoint.py unverified MIT (permissive) · 71df735edec0d658 · report
m-qiang/cortexode community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
CortexODE model/net.py ran · metamorphic tier: deterministic no licence file found · pointer only · 042c58847599eec2 · report fixture: returned CortexODE · level recorded 2026-09-22
teopb/ode-net-examples community (archive-listed) 33 samples, 27 ran (9 instrument-failed) · 6 unverified
AdamsBashforth torchdiffeq/_impl/odeint.py ran MIT (permissive) · 7980b2520b28c2f2 · report fixture: returned AdamsBashforth · level recorded 2026-09-22
AdamsBashforthMoulton torchdiffeq/_impl/odeint.py ran MIT (permissive) · 1cbcd7f7db72e996 · report fixture: returned AdamsBashforthMoulton · level recorded 2026-09-22
AdaptiveStepsizeODESolver torchdiffeq/_impl/odeint.py ran MIT (permissive) · e8208a8b9886cd85 · report fixture: returned AdaptiveStepsizeODESolver · level recorded 2026-09-22
Dopri5Solver torchdiffeq/_impl/odeint.py ran MIT (permissive) · 2f030eba6be5e4b6 · report fixture: returned Dopri5Solver · level recorded 2026-09-22
Euler torchdiffeq/_impl/odeint.py ran MIT (permissive) · 43e9e562dc3f595e · report fixture: returned Euler · level recorded 2026-09-22
Midpoint torchdiffeq/_impl/odeint.py ran MIT (permissive) · 6a98a0fc2403db3c · report fixture: returned Midpoint · level recorded 2026-09-22
RK4 torchdiffeq/_impl/odeint.py ran MIT (permissive) · 26fbbe135361b126 · report fixture: returned RK4 · level recorded 2026-09-22
Tsit5Solver torchdiffeq/_impl/odeint.py ran MIT (permissive) · a04d5636674a9ec2 · report fixture: returned Tsit5Solver · level recorded 2026-09-22
VariableCoefficientAdamsBashforth torchdiffeq/_impl/odeint.py ran MIT (permissive) · 180e9fe199764f78 · report fixture: returned VariableCoefficientAdamsBashforth · level recorded 2026-09-22
_RungeKuttaState torchdiffeq/_impl/odeint.py ran MIT (permissive) · 443bb371b2a31d9b · report fixture: returned _RungeKuttaState · level recorded 2026-09-22
_VCABMState torchdiffeq/_impl/odeint.py ran MIT (permissive) · 4b236303800173d5 · report fixture: returned _VCABMState · level recorded 2026-09-22
_check_inputs torchdiffeq/_impl/odeint.py ran; the contract check could not run (RAISES) MIT (permissive) · ea3c58d4e24eebb6 · report fixture: signature func:callable/0/?, y0:Tensor/2/float, t:Tensor/1/float · returned tuple · level recorded 2026-09-22
_compute_error_ratio torchdiffeq/_impl/odeint.py ran · our draft was wrong MIT (permissive) · 8b87a183c9dbf249 · report fixture: signature error_estimate:tuple/1/Tensor, error_tol:NoneType/0/?, rtol:list/1/float, atol:list/1/float, y0:list/1/Tensor, y1:list/1/Tensor · returned tuple · level recorded 2026-09-22
_convert_to_tensor torchdiffeq/_impl/odeint.py ran · our draft was wrong MIT (permissive) · baa65f15f31a9777 · report fixture: signature a:list/1/float, dtype:dtype/0/?, device:device/0/? · returned Tensor · level recorded 2026-09-22
_decreasing torchdiffeq/_impl/odeint.py ran · violated contract MIT (permissive) · ec95d60f4289b25e · report fixture: signature t:Tensor/1/float · returned Tensor · level recorded 2026-09-22
_has_converged torchdiffeq/_impl/odeint.py ran · violated contract MIT (permissive) · 80aaab169a92f738 · report fixture: signature y0:list/1/Tensor, y1:list/1/Tensor, rtol:float/0/float, atol:float/0/float · returned bool · level recorded 2026-09-22
_interp_coeff_tsit5 torchdiffeq/_impl/odeint.py ran · honoured contract MIT (permissive) · a80bde1c9ec425d6 · report fixture: signature t0:float/0/float, dt:float/0/float, eval_t:float/0/float · returned list · level recorded 2026-09-22
_interp_eval_tsit5 torchdiffeq/_impl/odeint.py ran · our draft was wrong MIT (permissive) · 69c9ce066153b90b · report fixture: signature t0:float/0/float, t1:float/0/float, k:tuple/1/tuple, eval_t:float/0/float · returned tuple · level recorded 2026-09-22
_is_finite torchdiffeq/_impl/odeint.py ran · our draft was wrong fingerprinted MIT (permissive) · 443e9b25ad3ae079 · report fixture: signature tensor:Tensor/2/float · returned bool · level recorded 2026-09-22
_is_iterable torchdiffeq/_impl/odeint.py ran · violated contract fingerprinted MIT (permissive) · 9d72df2efb3a66fe · report fixture: signature inputs:list/1/int · returned bool · level recorded 2026-09-22
_norm torchdiffeq/_impl/odeint.py ran · our draft was wrong fingerprinted MIT (permissive) · c3ee29e30b47fb06 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
_possibly_nonzero torchdiffeq/_impl/odeint.py ran · violated contract MIT (permissive) · 285104682369ab82 · report fixture: signature x:Tensor/1/float · returned bool · level recorded 2026-09-22
_runge_kutta_step torchdiffeq/_impl/odeint.py ran · our draft was wrong MIT (permissive) · 2a9f0b547af9d443 · report fixture: signature func:callable/0/?, y0:tuple/1/Tensor, f0:tuple/1/Tensor, t0:Tensor/0/float, dt:Tensor/0/float, tableau:ButcherTableau/0/? · returned tuple · level recorded 2026-09-22
_scaled_dot_product torchdiffeq/_impl/odeint.py ran MIT (permissive) · de5906cda333c484 · report fixture: signature scale:float/0/float, xs:list/1/Tensor, ys:list/1/Tensor · returned Tensor · level recorded 2026-09-25
_select_initial_step torchdiffeq/_impl/odeint.py ran · honoured contract MIT (permissive) · 95dcacc99376ec95 · report fixture: signature fun:callable/0/?, t0:Tensor/0/float, y0:tuple/1/Tensor, order:int/0/int, rtol:float/0/float, atol:float/0/float, f0:tuple/1/Tensor · returned Tensor · level recorded 2026-09-22
compute_implicit_phi torchdiffeq/_impl/odeint.py ran; the contract check could not run (RAISES) MIT (permissive) · a269dfdac4e51213 · report fixture: signature explicit_phi:list/1/tuple, f_n:tuple/1/float, k:int/0/int · returned deque · level recorded 2026-09-22
g_and_explicit_phi torchdiffeq/_impl/odeint.py ran · our draft was wrong MIT (permissive) · b2a5ce23e7055fe3 · report fixture: signature prev_t:list/1/Tensor, next_t:Tensor/0/float, implicit_phi:list/1/tuple, k:int/0/int · returned tuple · level recorded 2026-09-22
FixedGridODESolver torchdiffeq/_impl/odeint.py unverified MIT (permissive) · c15fe1bc655d0b37 · report
_assert_increasing torchdiffeq/_impl/odeint.py unverified MIT (permissive) · 33a06d298681bf50 · report
_handle_unused_kwargs torchdiffeq/_impl/odeint.py unverified MIT (permissive) · f1350edaaca6f9b0 · report
_interp_fit_dopri5 torchdiffeq/_impl/odeint.py unverified MIT (permissive) · 2e6b4dc52e187e03 · report
_optimal_step_size torchdiffeq/_impl/odeint.py unverified MIT (permissive) · cc5817a5b29775b5 · report
odeint torchdiffeq/_impl/odeint.py unverified MIT (permissive) · 3642eb84474d80fc · report
tianfr/mononerf community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
VelocityField src/model/velocity_field.py ran licence not identified · pointer only · f031bcc19da6d85a · report fixture: returned VelocityField · level recorded 2026-09-22
xuanqing94/torchdiffeq community (archive-listed) 14 samples, 12 ran (2 instrument-failed) · 2 unverified
AdamsBashforth torchdiffeq/_impl/odeint.py ran MIT (permissive) · 106d95c9ca4a144c · report fixture: returned AdamsBashforth · level recorded 2026-09-22
AdamsBashforthMoulton torchdiffeq/_impl/odeint.py ran MIT (permissive) · 279f4f78d04ad28b · report fixture: returned AdamsBashforthMoulton · level recorded 2026-09-22
AdaptiveStepsizeODESolver torchdiffeq/_impl/odeint.py ran MIT (permissive) · 2f5e41ed5c35fa64 · report fixture: returned AdaptiveStepsizeODESolver · level recorded 2026-09-22
Dopri5Solver torchdiffeq/_impl/odeint.py ran MIT (permissive) · f121c10d5d8c5250 · report fixture: returned Dopri5Solver · level recorded 2026-09-22
Euler torchdiffeq/_impl/odeint.py ran MIT (permissive) · 70d97d2f6b74251c · report fixture: returned Euler · level recorded 2026-09-22
FixedGridODESolver torchdiffeq/_impl/odeint.py ran MIT (permissive) · 10f0d6dfa6f48005 · report fixture: returned FixedGridODESolver · level recorded 2026-09-22
Midpoint torchdiffeq/_impl/odeint.py ran MIT (permissive) · 99ec31db7c208dcf · report fixture: returned Midpoint · level recorded 2026-09-22
RK4 torchdiffeq/_impl/odeint.py ran MIT (permissive) · 52750e1480f37d55 · report fixture: returned RK4 · level recorded 2026-09-22
Tsit5Solver torchdiffeq/_impl/odeint.py ran MIT (permissive) · a65d81dc9b13762d · report fixture: returned Tsit5Solver · level recorded 2026-09-22
VariableCoefficientAdamsBashforth torchdiffeq/_impl/odeint.py ran MIT (permissive) · 0875a31606cadf64 · report fixture: returned VariableCoefficientAdamsBashforth · level recorded 2026-09-22
_check_inputs torchdiffeq/_impl/odeint.py ran; the contract check could not run (RAISES) MIT (permissive) · 2224684f11a7a3c9 · report fixture: signature func:callable/0/?, y0:Tensor/2/float, t:Tensor/1/float · returned tuple · level recorded 2026-09-22
_decreasing torchdiffeq/_impl/odeint.py ran; the contract check could not run (RAISES) MIT (permissive) · aef26a4386aa599b · report fixture: signature t:Tensor/1/float · returned bool · level recorded 2026-09-22
_assert_increasing torchdiffeq/_impl/odeint.py unverified MIT (permissive) · b4d1b587fdffa06d · report
odeint torchdiffeq/_impl/odeint.py unverified MIT (permissive) · 8ab361e64d240962 · report
xwinxu/bayesian-sde community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
DiffEqWrapper brax/_impl/diffeq_layers.py ran · our draft was wrong MIT (permissive) · b4e4766812fea13a · report fixture: signature layer:tuple/1/callable · returned tuple · level recorded 2026-09-22
dungxibo123/neural_ode community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ODEBlock utils/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 92137b4f2c7365e8 · report fixture: returned ODEBlock · 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.

22 assemblies on this paper: 22 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

22 sibling assemblies for Neural Ordinary Differential Equations (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 22 sibling assemblies; the other 10 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 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 22 siblings

  1. ODENet entry · level 1 · ran · 6bbb55a0b9a1ee9c

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 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 22 siblings

  1. ODEBlock entry · level 1 · ran · 59f408ca8aaaf9f3

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 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 22 siblings

  1. CortexODE entry · level 1 · ran · 042c58847599eec2

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 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 22 siblings

  1. ODEBlock entry · level 1 · ran · 92137b4f2c7365e8

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 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 22 siblings

  1. neuralODE entry · level 1 · ran · a94209f6fc808fe0

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 3 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) · 1 unverified. The assembly has not been run end-to-end.

one of 22 siblings

  1. ODEFunc entry · level 0 · unverified · ca95388e3abbb9e0
  2. Data helper · level 1 · ran · afcd5754477bf8a7
  3. pairwise helper · level 1 · ran · our draft was wrong · acc109795f939462

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 10 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 22 siblings

  1. Dynamic entry · level 0 · unverified · 02793af9d30a0ad2
  2. build_case helper · level 1 · ran · 1954ce4f7b5742a7
  3. flat_param_jacobian helper · level 0 · unverified · 0b628441d9a6d4da
  4. input_jacobian helper · level 1 · ran · our draft was wrong · a06d1d8f938ae9f4
  5. integrable_from_model helper · level 1 · ran · our draft was wrong · 2285415039c52b05
  6. y helper · level 1 · ran · violated contract · 0dcc609ed16c99d9
  7. dynamic_from_signals helper · level 1 · ran · our draft was wrong · 2aee82e2cf39316d
  8. randomGaussianWalk helper · level 1 · ran · our draft was wrong · a69334ba86c0588e
  9. randomState helper · level 1 · ran · c58084b51168dca6
  10. x helper · level 1 · ran; the contract check could not run (RAISES) · 93721216ebb5b002

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 10 bricks; individually on a fixture: 4 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; 3 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 22 siblings

  1. ODEBlock entry · level 0 · unverified · 9158a9a96f605d3f
  2. ExperimentOptions helper · level 0 · unverified · a20f8065b0c3fffe
  3. ODENet model · level 1 · ran · ce3b538793b44a3f
  4. find_dataset_class helper · level 0 · unverified · 762ad558c1d13aeb
  5. load_yaml_values helper · level 1 · ran · our draft was wrong · e0a9dd130bc8e029
  6. merge_dicts helper · level 1 · ran · our draft was wrong · 5c104e6fea609913
  7. mkdirs helper · level 0 · unverified · f81cc7d6c4c87870
  8. BaseDataset helper · level 0 · unverified · abebc71e7f1ca56a
  9. load_yaml helper · level 1 · ran · our draft was wrong · 0e64c9442199a010
  10. mkdir helper · level 0 · unverified · 9012d6958edc86f1

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 4 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) · 2 unverified. The assembly has not been run end-to-end.

one of 22 siblings

  1. NeuralODE entry · level 0 · unverified · 0be1257af72d80c3
  2. ODEAdjoint helper · level 1 · ran · a932ba75143e9ecb
  3. ODEfunc model · level 0 · unverified · c05e6f04ee48cfca
  4. ode_solve helper · level 1 · ran · our draft was wrong · 8193789421b9bce3

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 33 bricks; individually on a fixture: 27 ran (of which 11 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 4 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 22 siblings

  1. odeint entry · level 0 · unverified · 3642eb84474d80fc
  2. _check_inputs helper · level 1 · ran; the contract check could not run (RAISES) · ea3c58d4e24eebb6
  3. _decreasing helper · level 1 · ran · violated contract · ec95d60f4289b25e
  4. AdaptiveStepsizeODESolver helper · level 1 · ran · e8208a8b9886cd85
  5. Dopri5Solver helper · level 1 · ran · 2f030eba6be5e4b6
  6. FixedGridODESolver helper · level 0 · unverified · c15fe1bc655d0b37
  7. Midpoint helper · level 1 · ran · 6a98a0fc2403db3c
  8. RK4 helper · level 1 · ran · 26fbbe135361b126
  9. Tsit5Solver helper · level 1 · ran · a04d5636674a9ec2
  10. _RungeKuttaState helper · level 1 · ran · 443bb371b2a31d9b
  11. _VCABMState helper · level 1 · ran · 4b236303800173d5
  12. _assert_increasing helper · level 0 · unverified · 33a06d298681bf50
  13. _compute_error_ratio helper · level 1 · ran · our draft was wrong · 8b87a183c9dbf249
  14. _convert_to_tensor helper · level 1 · ran · our draft was wrong · baa65f15f31a9777
  15. _handle_unused_kwargs helper · level 0 · unverified · f1350edaaca6f9b0
  16. _has_converged helper · level 1 · ran · violated contract · 80aaab169a92f738
  17. _interp_coeff_tsit5 helper · level 1 · ran · honoured contract · a80bde1c9ec425d6
  18. _interp_eval_tsit5 helper · level 1 · ran · our draft was wrong · 69c9ce066153b90b
  19. _interp_fit_dopri5 helper · level 0 · unverified · 2e6b4dc52e187e03
  20. _is_finite helper · level 1 · ran · our draft was wrong · 443e9b25ad3ae079
  21. _is_iterable helper · level 1 · ran · violated contract · 9d72df2efb3a66fe
  22. _norm helper · level 1 · ran · our draft was wrong · c3ee29e30b47fb06
  23. _optimal_step_size helper · level 0 · unverified · cc5817a5b29775b5
  24. _possibly_nonzero helper · level 1 · ran · violated contract · 285104682369ab82
  25. _runge_kutta_step helper · level 1 · ran · our draft was wrong · 2a9f0b547af9d443
  26. _scaled_dot_product helper · level 1 · ran · de5906cda333c484
  27. _select_initial_step helper · level 1 · ran · honoured contract · 95dcacc99376ec95
  28. compute_implicit_phi helper · level 1 · ran; the contract check could not run (RAISES) · a269dfdac4e51213
  29. g_and_explicit_phi helper · level 1 · ran · our draft was wrong · b2a5ce23e7055fe3
  30. AdamsBashforthMoulton helper · level 1 · ran · 1cbcd7f7db72e996
  31. Euler helper · level 1 · ran · 43e9e562dc3f595e
  32. VariableCoefficientAdamsBashforth helper · level 1 · ran · 180e9fe199764f78
  33. AdamsBashforth helper · level 1 · ran · 7980b2520b28c2f2

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 1 brick; 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) · 0 unverified. The assembly has not been run end-to-end.

one of 22 siblings

  1. DiffEqWrapper entry · level 1 · ran · our draft was wrong · b4e4766812fea13a

harvested Assembly for Neural Ordinary Differential Equations (graph method: Neural Ordinary Differential Equations). 11 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) · 3 unverified. The assembly has not been run end-to-end.

one of 22 siblings

  1. IntegralModel entry · level 0 · unverified · 9e070cde035db353
  2. PrunableModel helper · level 1 · ran · d8a06e2aaf08a085
  3. TrainableGrid1D helper · level 1 · ran · 60b35461edf3f214
  4. get_parent_module helper · level 1 · ran · our draft was wrong · ddb0f75fbab8b97a
  5. reapply_parametrizations helper · level 0 · unverified · 242605ed25603835
  6. remove_parametrizations helper · level 1 · ran · our draft was wrong · 63dd824e61be8e94
  7. reset_batchnorm helper · level 0 · unverified · 897a3625721985ef
  8. ParametrizedModel helper · level 1 · ran · 6a10221436726b78
  9. IGrid helper · level 1 · ran · 62feec9141b4e5c3
  10. get_attr_by_name helper · level 1 · ran · our draft was wrong · aa235b32d88c1eed
  11. get_parent_name helper · level 1 · ran · our draft was wrong · 019bd750e2303b7e
  1. DAFT · 836e53ae05b084cf · 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[12] in the JSON twin
  2. odesolver · 875691df9fbcdca3 · 5 bricks; individually on a fixture: 5 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; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. odeint · 9881bf34658d9b73 · 33 bricks; individually on a fixture: 27 ran (of which 11 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 4 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. OdeSolver · 9be09b6348f5c6fb · 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[15] in the JSON twin
  5. odeint · a3d1e3707d79e964 · 33 bricks; individually on a fixture: 28 ran (of which 12 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 3 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. VelocityField · afbac8f0458579f4 · 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[17] in the JSON twin
  7. odesolver · b0ecf0d3d1006677 · 5 bricks; individually on a fixture: 5 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; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. EncoderFunc · edc7e910239dee32 · 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[19] in the JSON twin
  9. traj_NODE · f5e1d6e0a36eeafe · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. forward · fb40476f6f129bf7 · 1 brick; 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[21] 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="1806.07366") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Multivariate Time Series ForecastingMultivariate Time Series ImputationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multivariate Time Series Forecasting MuJoCo Latent ODE (RNN enc.) MSE (10^-2, 50% missing) 1.377 #2 of 6 Archive leaderboard report
Multivariate Time Series Forecasting MuJoCo RNN-VAE MSE (10^-2, 50% missing) 1.782 #3 of 6 Archive leaderboard report
Multivariate Time Series Forecasting PhysioNet Challenge 2012 RNN-VAE MSE stdev 0.145 #3 of 4 Archive leaderboard report
Multivariate Time Series Forecasting PhysioNet Challenge 2012 RNN-VAE mse (10^-3) 3.055 #3 of 4 Archive leaderboard report
Multivariate Time Series Forecasting PhysioNet Challenge 2012 Latent ODE (RNN enc.) MSE stdev 0.052 #4 of 4 Archive leaderboard report
Multivariate Time Series Forecasting PhysioNet Challenge 2012 Latent ODE (RNN enc.) mse (10^-3) 3.162 #4 of 4 Archive leaderboard report
Multivariate Time Series Forecasting USHCN-Daily NeuralODE-VAE-Mask MSE 0.83 #7 of 8 Archive leaderboard report
Multivariate Time Series Forecasting USHCN-Daily NeuralODE-VAE MSE 0.96 #8 of 8 Archive leaderboard report
Multivariate Time Series Imputation MuJoCo Latent ODE (RNN enc.) MSE (10^2, 50% missing) 0.447 #2 of 6 Archive leaderboard report
Multivariate Time Series Imputation MuJoCo RNN-VAE MSE (10^2, 50% missing) 6.100 #6 of 6 Archive leaderboard report
Multivariate Time Series Imputation PhysioNet Challenge 2012 Latent ODE (RNN enc.) mse (10^-3) 3.907 #8 of 9 Archive leaderboard report
Multivariate Time Series Imputation PhysioNet Challenge 2012 RNN-VAE mse (10^-3) 5.930 #9 of 9 Archive leaderboard report
Pose Estimation !(()&&!|*|*| Nate 0..5sec Jaau #1 of 1 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.

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