SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.09601 · 2020

Hypersolvers: Toward Fast Continuous-Depth Models

arXiv · PDF · Open in the Atlas

Code that ran

8 of 15 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 6 have no contract verdict; 1 failure of our instrument; 7 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 2026-11-21; 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/2007.09601.json · badge: /api/ran/2007.09601.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
DiffEqML/diffeqml-research canonical (classifier label)
classifier basis: census
8 ran · 7 no recorded run
FunctionStatusWhere it lives
get_mgrid Ran
ran, honoured the contract we drafted
DiffEqML/diffeqml-research/hypersolvers-control/src/activations.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from GGorMM1/QIREN, is pointer only (licence: NONE) · get_code("6993cad8937592ca")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from GGorMM1/QIREN, 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.

circle_loss Ran
ran on a synthesized input
DiffEqML/diffeqml-research/hypersolvers-control/src/cost.py
code served (permissive licence) · get_code("de23a0d8342f36d6")
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 Tensor, 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)

# Create a small tensor with shape (2, 4) where last 2 dims are x, y coordinates
# The function accesses z[..., :1] and z[..., 1:] so we need at least 2 features
z = torch.randn(2, 4)

# The function uses a as a scalar in the loss computation
a = 1

ARGS = {
    "z": z,
    "a": a,
}
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 Tensor, 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
circus_loss Ran
ran on a synthesized input
DiffEqML/diffeqml-research/hypersolvers-control/src/cost.py
code served (permissive licence) · get_code("e8e6e7289ccb550b")
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 Tensor, 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)

# z is indexed with [..., :1] and [..., 1:], so it needs at least 2 features in last dimension
# Create a small tensor with shape (batch=2, features=4)
z = torch.randn(2, 4)

# a and k are floats with default values
a = 1.0
k = 2.1

ARGS = {
    "z": z,
    "a": a,
    "k": k,
}
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 Tensor, 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
density_scatter Ran
ran on a synthesized input
DiffEqML/diffeqml-research/hypersolver/src/utils.py
code served (permissive licence) · get_code("ed8adea15e61e3bc")
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 Axes. The image it ran in was not recorded. If your copy returns the same type 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
import numpy as np
import matplotlib.pyplot as plt

torch.manual_seed(0)

# Create sample data as torch tensors
x_tensor = torch.randn(50)
y_tensor = torch.randn(50)

# Create a matplotlib axis
fig, ax = plt.subplots()

# Construct ARGS dictionary with all parameters
ARGS = {
    'x': x_tensor,
    'y': y_tensor,
    'ax': ax,
    'bins': 20
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, scipy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Axes — a Axes output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Axes output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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 Ran
ran; our contract draft was wrong, not the code
DiffEqML/diffeqml-research/hypersolvers-control/src/activations.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from 19reborn/pict_smoke, is pointer only (licence: NONE) · get_code("754f3e0cdb026116")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from 19reborn/pict_smoke, 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.

mape Ran
ran on a synthesized input
DiffEqML/diffeqml-research/hypersolvers-control/src/utils.py
code served (permissive licence) · get_code("036472db72b08a56")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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)

# Create small tensors for yhat and y
# The function computes torch.abs((yhat - y) / yhat)
# So both should be tensors of the same shape
yhat = torch.randn(2, 4)
y = torch.randn(2, 4)

ARGS = {
    "yhat": yhat,
    "y": y,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
one_hot Ran
ran on a synthesized input
DiffEqML/diffeqml-research/neural-hybrid-automata/src/nn.py
code served (permissive licence) · get_code("c6a6548ef8385b9a")
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 Tensor, ndim 2, dtype family int, shape (4, 3) 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)

# The function takes:
# - idx: a tensor of class indices
# - n_classes: number of classes (default 3)
#
# It uses len(idx) to get batch size, calls idx.unsqueeze(1) to reshape,
# and uses idx.to() implicitly via .to(idx) on the zeros tensor.
# So idx must be a 1D tensor of integers.

idx = torch.tensor([0, 2, 1, 0], dtype=torch.long)
n_classes = 3

ARGS = {
    'idx': idx,
    'n_classes': n_classes
}
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 Tensor, ndim 2, dtype family int, shape (4, 3) — shape (4, 3) 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
smape Ran
ran on a synthesized input
DiffEqML/diffeqml-research/hypersolvers-control/src/utils.py
code served (permissive licence) · get_code("dc53a4c9f0d50895")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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)

# Create small tensors for yhat and y
# The function performs element-wise operations, so they need compatible shapes
yhat = torch.randn(2, 4)
y = torch.randn(2, 4)

ARGS = {
    "yhat": yhat,
    "y": y,
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
autograd_trace Not yet run
unverified (harvested, no recorded run)
DiffEqML/diffeqml-research/hypersolver/src/models.py
code served (permissive licence) · get_code("53b4a26700518185")
How it ran

no invocation recorded.

continuous_lqr Not yet run
unverified (harvested, no recorded run)
DiffEqML/diffeqml-research/hypersolvers-control/src/controllers.py
code served (permissive licence) · get_code("503b76247e05ecc8")
How it ran

no invocation recorded.

discrete_lqr Not yet run
unverified (harvested, no recorded run)
DiffEqML/diffeqml-research/hypersolvers-control/src/controllers.py
code served (permissive licence) · get_code("efd45a3ed6ab2f76")
How it ran

no invocation recorded.

get_cifar_dloaders Not yet run
unverified (harvested, no recorded run)
DiffEqML/diffeqml-research/dissecting-neural-odes/image_classification/utils.py
code served (permissive licence) · get_code("fdae332b7c150576")
How it ran

no invocation recorded.

grid_apply Not yet run
unverified (harvested, no recorded run)
DiffEqML/diffeqml-research/hypersolver/src/utils.py
code served (permissive licence) · get_code("f4b106b4f1fbbe33")
How it ran

no invocation recorded.

jagged_fixed_odeint Not yet run
unverified (harvested, no recorded run)
DiffEqML/diffeqml-research/neural-hybrid-automata/src/odeint.py
code served (permissive licence) · get_code("c43fd3e765748d8b")
How it ran

no invocation recorded.

laplace Not yet run
unverified (harvested, no recorded run)
DiffEqML/diffeqml-research/hypersolvers-control/src/activations.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from 19reborn/pict_smoke, is pointer only (licence: NONE) · get_code("5719cf26510d50ea")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from 19reborn/pict_smoke, 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. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 later) and 11 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

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

FunctionAlso present inEarliest-datedOthers named
laplace 6 other papers
1 dated earlier, 5 later
2006.09661 (2020-06)
Implicit Neural Representations with Periodic Activation Functions
2108.08478 (2021-08)
Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction
2303.14092 (2023-03)
NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images
and 3 more not named here
get_mgrid 3 other papers
1 the same month, 2 later
2007.02798 (2020-07)
Gradient Origin Networks
2406.02529 (2024-06)
ReLUs Are Sufficient for Learning Implicit Neural Representations
2406.03873 (2024-06)
Quantum Implicit Neural Representations
autograd_trace 1 other paper
1 later
2510.26645 (2025-10)
Curly Flow Matching for Learning Non-gradient Field Dynamics
divergence 1 other paper
1 later
2407.09679 (2024-07)
Physics-Informed Learning of Characteristic Trajectories for Smoke Reconstruction

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 2026-11-21.

Repositories linked to this paper

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

Abstract

The infinite-depth paradigm pioneered by Neural ODEs has launched a renaissance in the search for novel dynamical system-inspired deep learning primitives; however, their utilization in problems of non-trivial size has often proved impossible due to poor computational scalability. This work paves the way for scalable Neural ODEs with time-to-prediction comparable to traditional discrete networks. We introduce hypersolvers, neural networks designed to solve ODEs with low overhead and theoretical guarantees on accuracy. The synergistic combination of hypersolvers and Neural ODEs allows for cheap inference and unlocks a new frontier for practical application of continuous-depth models. Experimental evaluations on standard benchmarks, such as sampling for continuous normalizing flows, reveal consistent pareto efficiency over classical numerical methods.

For agents

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

get_harvested_code_for_paper("2007.09601")
get_code_for_paper("2007.09601")
have("2007.09601")

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

curl https://syntology.ai/api/ran/2007.09601.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.09601.svg)](https://syntology.ai/paper/2007.09601)

Connect an agent — have() is free.