SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.03907 · 2019

Latent ODEs for Irregularly-Sampled Time Series

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1907.03907.json · badge: /api/ran/1907.03907.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
YuliaRubanova/latent_ode canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
BorealisAI/continuous-time-flow-process extension (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
gkrudah/ODEnet community (classifier label)
classifier basis: plan_row
1 ran · 0 no recorded run
FunctionStatusWhere it lives
sample_rademacher_like Ran
ran; our contract draft was wrong, not the code
BorealisAI/continuous-time-flow-process/lib/layers/odefunc.py
pointer only (licence: NOASSERTION) · get_code("7b0725913f7abbbb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, BorealisAI/continuous-time-flow-process (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

assign_value_or_sample Ran
ran on a synthesized input
YuliaRubanova/latent_ode/generate_timeseries.py
code served (permissive licence) · get_code("4128b3f4ab1a5a81")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "value": None,
    "sampling_interval": [0.0, 1.0]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_classifier Ran
ran; our contract draft was wrong, not the code
gkrudah/ODEnet/lib/base_models.py
pointer only (licence: MIT); the stored copy get_code serves, from BenJMaurel/PharmaNODE, is pointer only (licence: NONE) · get_code("fc9a64735be0911c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from BenJMaurel/PharmaNODE, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

divergence_bf Ran
ran; our contract draft was wrong, not the code
BorealisAI/continuous-time-flow-process/lib/layers/odefunc.py
pointer only (licence: NOASSERTION) · get_code("b03151f58b6fe757")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, BorealisAI/continuous-time-flow-process (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_periodic Ran
ran on a synthesized input
YuliaRubanova/latent_ode/generate_timeseries.py
code served (permissive licence) · get_code("dd0fe112d9664002")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (6, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct time_steps as a numpy array
time_steps = np.array([0.0, 0.1, 0.2, 0.3, 0.4, 0.5])

# Define scalar parameters for the periodic signal
init_freq = 1.0
init_amplitude = 2.0
starting_point = 0.5
final_freq = 2.0
final_amplitude = 3.0
phi_offset = 0.0

ARGS = {
    "time_steps": time_steps,
    "init_freq": init_freq,
    "init_amplitude": init_amplitude,
    "starting_point": starting_point,
    "final_freq": final_freq,
    "final_amplitude": final_amplitude,
    "phi_offset": phi_offset,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (6, 2) — shape (6, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_data_min_max Ran
ran, honoured the contract we drafted
YuliaRubanova/latent_ode/physionet.py
code served (permissive licence) · get_code("97cefd1ecd9fcbca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Build records as a list of tuples
# Each record contains: (record_id, tt, vals, mask, labels)
# vals shape: (time_steps, n_features)
# mask shape: (time_steps, n_features) with values 0 or 1
# tt: time values
# record_id: identifier
# labels: target labels

record_1 = (
    "record_001",
    torch.tensor([0.0, 1.0, 2.0]),  # tt: 3 time steps
    torch.tensor([[1.0, 2.0, 3.0, 4.0],
                  [5.0, 6.0, 7.0, 8.0],
                  [9.0, 10.0, 11.0, 12.0]]),  # vals: (3, 4)
    torch.tensor([[1, 1, 1, 1],
                  [1, 0, 1, 1],
                  [0, 1, 1, 0]]),  # mask: (3, 4)
    torch.tensor([0, 1])  # labels
)

record_2 = (
    "record_002",
    torch.tensor([0.0, 1.0, 2.0]),  # tt: 3 time steps
    torch.tensor([[2.0, 3.0, 4.0, 5.0],
                  [6.0, 7.0, 8.0, 9.0],
                  [10.0, 11.0, 12.0, 13.0]]),  # vals: (3, 4)
    torch.tensor([[1, 1, 1, 1],
                  [1, 1, 0, 1],
                  [1, 1, 1, 1]]),  # mask: (3, 4)
    torch.tensor([1, 0])  # labels
)

records = [record_1, record_2]

ARGS = {
    "records": records
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_next_val Ran
ran on a synthesized input
YuliaRubanova/latent_ode/generate_timeseries.py
code served (permissive licence) · get_code("14d893a51ceea2f1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "init": 10.0,
    "t": 5.0,
    "tmin": 0.0,
    "tmax": 10.0,
    "final": 20.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
divergence_approx Not yet run
unverified (harvested, no recorded run)
BorealisAI/continuous-time-flow-process/lib/layers/odefunc.py
pointer only (licence: NOASSERTION) · get_code("f3c69a82cb618229")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, BorealisAI/continuous-time-flow-process (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 5 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
sample_rademacher_like 6 other papers
1 dated earlier, 5 later · 3 only as an assembly brick
1810.01367 (2018-10)
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
2002.04461 (2020-02)
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
2006.04598 (2020-06)
WaveNODE: A Continuous Normalizing Flow for Speech Synthesis
and 3 more not named here
divergence_approx 5 other papers
1 dated earlier, 4 later · 3 only as an assembly brick
1810.01367 (2018-10)
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
2002.04461 (2020-02)
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
2006.04598 (2020-06)
WaveNODE: A Continuous Normalizing Flow for Speech Synthesis
and 2 more not named here
divergence_bf 4 other papers
1 dated earlier, 3 later · 2 only as an assembly brick
1810.01367 (2018-10)
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
2002.04461 (2020-02)
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
2006.10254 (2020-06)
Neural Manifold Ordinary Differential Equations
and 1 more not named here
create_classifier 3 other papers
3 later
2206.04843 (2022-06)
Neural Laplace: Learning diverse classes of differential equations in the Laplace domain
2302.12604 (2023-02)
Neural Laplace Control for Continuous-time Delayed Systems
2602.03215 (2026-02)
Latent Neural Ordinary Differential Equations for Model-Informed Precision Dosing: Overcoming Structural Assumptions in Pharmacokinetics
get_data_min_max 2 other papers
2 later
2006.04727 (2020-06)
Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering
2605.17804 (2026-05)
GenTS: A Comprehensive Benchmark Library for Generative Time Series Models

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace the recognition network of the recently-proposed Latent ODE model. Both ODE-RNNs and Latent ODEs can naturally handle arbitrary time gaps between observations, and can explicitly model the probability of observation times using Poisson processes. We show experimentally that these ODE-based models outperform their RNN-based counterparts on irregularly-sampled data.

For agents

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

get_harvested_code_for_paper("1907.03907")
get_code_for_paper("1907.03907")
have("1907.03907")

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

curl https://syntology.ai/api/ran/1907.03907.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.03907.svg)](https://syntology.ai/paper/1907.03907)

Connect an agent — have() is free.