SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.06345 · 2021

Proximal Optimal Transport Modeling of Population Dynamics

arXiv · PDF · Open in the Atlas

Code that ran

7 of 18 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; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 11 no recorded run), 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/2106.06345.json · badge: /api/ran/2106.06345.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
bunnech/jkonet canonical (classifier label)
classifier basis: census
5 ran · 7 no recorded run
gjhuizing/wsingular community (classifier label)
classifier basis not recorded on the link
2 ran · 4 no recorded run
FunctionStatusWhere it lives
create_train_state Ran
ran on a synthesized input
bunnech/jkonet/jkonet/utils/optim.py
code served (permissive licence) · get_code("ac6b25b6c65de42b")
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 TrainState. 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 jax
import jax.numpy as jnp
from flax import linen as nn
import optax
from functools import partial

# Define a minimal Flax model
class SimpleModel(nn.Module):
    features: int = 8
    
    @nn.compact
    def __call__(self, x):
        x = nn.Dense(self.features)(x)
        x = nn.relu(x)
        x = nn.Dense(4)(x)
        return x

# Create the model instance
model = SimpleModel(features=8)

# Create an optimizer
optimizer = optax.adam(learning_rate=0.001)

# Create RNG
rng = jax.random.PRNGKey(0)

# Define input shape - using (2, 5) for batch=2, feature_dim=5
input_shape = (2, 5)

# Build ARGS dictionary
ARGS = {
    'rng': rng,
    'model': model,
    'optimizer': optimizer,
    'input': input_shape
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
flax, jax, optax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TrainState — a TrainState output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TrainState 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
get_optimizer Ran
ran on a synthesized input
bunnech/jkonet/jkonet/utils/optim.py
code served (permissive licence) · get_code("17f10de7cdd420b8")
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 GradientTransformationExtraArgs. 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 optax

class Config:
    def __init__(self):
        self.optim = OptimConfig()

class OptimConfig:
    def __init__(self):
        self.optimizer = 'Adam'
        self.lr = 0.001
        self.beta1 = 0.9
        self.beta2 = 0.999
        self.eps = 1e-8
        self.grad_clip = 1.0

config = Config()

ARGS = {
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
optax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GradientTransformationExtraArgs — a GradientTransformationExtraArgs output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GradientTransformationExtraArgs output the recorded ndim 1 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
hilbert_distance Ran
ran on a synthesized input
gjhuizing/wsingular/wsingular/utils.py
code served (permissive licence) · get_code("0de8d23263fbc339")
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)

# Create two small distance-like matrices (non-negative, same shape)
# Using 4x4 matrices as specified (tiny, batch 2 would be inappropriate for distance matrices)
D_1 = torch.tensor([
    [0.0, 1.0, 2.0, 3.0],
    [1.0, 0.0, 1.5, 2.5],
    [2.0, 1.5, 0.0, 1.0],
    [3.0, 2.5, 1.0, 0.0]
], dtype=torch.float32)

D_2 = torch.tensor([
    [0.0, 1.2, 2.1, 3.2],
    [1.2, 0.0, 1.6, 2.6],
    [2.1, 1.6, 0.0, 1.1],
    [3.2, 2.6, 1.1, 0.0]
], dtype=torch.float32)

ARGS = {
    "D_1": D_1,
    "D_2": D_2
}
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
nest_dict Ran
ran on a synthesized input
bunnech/jkonet/jkonet/utils/helper.py
code served (permissive licence) · get_code("ce20d1aa574c915d")
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 dict. 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

torch.manual_seed(0)

# Analyzing the function:
# nest_dict takes a dict `d` and processes it
# It iterates over d.items(), extracting keys and values
# Keys are split by a separator (default '.')
# split_rec recursively builds nested dicts

# Construct a simple flat dict with dotted keys
d = {
    'a.b.c': 1,
    'a.b.d': 2,
    'a.e': 3,
    'f': 4,
    'g.h': 5
}

ARGS = {
    'd': d
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
plot_energy_potential Ran
ran on a synthesized input
bunnech/jkonet/jkonet/utils/plotting.py
code served (permissive licence) · get_code("8d07e2b8d00342e1")
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 Figure. 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 numpy as np
import matplotlib.pyplot as plt

class MockStateEnergy:
    """Mock state_energy object that mimics a Flax model state."""
    def __init__(self):
        self.params = {}
    
    def apply_fn(self, variables, x, training):
        """Mock apply_fn that returns energy values for input points."""
        # Return a simple scalar energy for each input point
        return np.sum(x ** 2, axis=1, keepdims=True).squeeze()

# Create sample data with shape (num_batches, num_points, num_features)
# Using distinct sizes: 3 batches, 5 points per batch, 4 features
data = np.random.randn(3, 5, 4).astype(np.float32)

# Create mock state_energy object
state_energy = MockStateEnergy()

ARGS = {
    'state_energy': state_energy,
    'data': data,
    'name': 'test_plot',
    'save_loc': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
plot_predictions Ran
ran on a synthesized input
bunnech/jkonet/jkonet/utils/plotting.py
code served (permissive licence) · get_code("e6ad4d626be42164")
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 Figure. 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 numpy as np
import matplotlib.pyplot as plt

# Create sample data: 5 time steps, each with 3 points in 2D space
data = np.array([
    np.random.randn(3, 2) * 5 + np.array([0, 0]),
    np.random.randn(3, 2) * 5 + np.array([1, 1]),
    np.random.randn(3, 2) * 5 + np.array([2, 2]),
    np.random.randn(3, 2) * 5 + np.array([3, 3]),
    np.random.randn(3, 2) * 5 + np.array([4, 4]),
])

# Create sample predictions: 4 time steps (future predictions), each with 3 points in 2D space
predicted = np.array([
    np.random.randn(3, 2) * 5 + np.array([1, 1]),
    np.random.randn(3, 2) * 5 + np.array([2, 2]),
    np.random.randn(3, 2) * 5 + np.array([3, 3]),
    np.random.randn(3, 2) * 5 + np.array([4, 4]),
])

ARGS = {
    'predicted': predicted,
    'data': data,
    'name': 'test_plot',
    'save_loc': None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
random_distance Ran
ran on a synthesized input
gjhuizing/wsingular/wsingular/utils.py
code served (permissive licence) · get_code("8af9799ef20cae1d")
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 (5, 5) 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 = {
    "size": 5,
    "dtype": torch.float32,
    "device": "cpu",
}
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 (5, 5) — shape (5, 5) 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
count_parameters Not yet run
unverified (harvested, no recorded run)
bunnech/jkonet/jkonet/utils/helper.py
code served (permissive licence) · get_code("53329584a0074de3")
How it ran

no invocation recorded.

fixpoint_iter Not yet run
unverified (harvested, no recorded run)
bunnech/jkonet/jkonet/models/fixpoint_loop.py
code served (permissive licence) · get_code("27f1ad1350106a8f")
How it ran

no invocation recorded.

fixpoint_iter_bwd Not yet run
unverified (harvested, no recorded run)
bunnech/jkonet/jkonet/models/fixpoint_loop.py
code served (permissive licence) · get_code("877c4d34650ae7b4")
How it ran

no invocation recorded.

fixpoint_iter_fwd Not yet run
unverified (harvested, no recorded run)
bunnech/jkonet/jkonet/models/fixpoint_loop.py
code served (permissive licence) · get_code("1b1462db6c2a66d1")
How it ran

no invocation recorded.

flat_dict Not yet run
unverified (harvested, no recorded run)
bunnech/jkonet/jkonet/utils/helper.py
code served (permissive licence) · get_code("c9db724f06b72877")
How it ran

no invocation recorded.

global_norm Not yet run
unverified (harvested, no recorded run)
bunnech/jkonet/jkonet/utils/optim.py
code served (permissive licence) · get_code("fea2f5c067ec6d73")
How it ran

no invocation recorded.

plot_psi_field Not yet run
unverified (harvested, no recorded run)
bunnech/jkonet/jkonet/utils/plotting.py
code served (permissive licence) · get_code("f15544ced3cc6314")
How it ran

no invocation recorded.

regularization_matrix Not yet run
unverified (harvested, no recorded run)
gjhuizing/wsingular/wsingular/utils.py
code served (permissive licence) · get_code("c0473bd90ef0f17e")
How it ran

no invocation recorded.

sinkhorn_map Not yet run
unverified (harvested, no recorded run)
gjhuizing/wsingular/wsingular/distance.py
code served (permissive licence) · get_code("2b21c508c7119652")
How it ran

no invocation recorded.

stochastic_wasserstein_map Not yet run
unverified (harvested, no recorded run)
gjhuizing/wsingular/wsingular/distance.py
code served (permissive licence) · get_code("046c37b100dfe5b3")
How it ran

no invocation recorded.

wasserstein_map Not yet run
unverified (harvested, no recorded run)
gjhuizing/wsingular/wsingular/distance.py
code served (permissive licence) · get_code("2971d6beb84a3130")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 17 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
fixpoint_iter_fwd 1 other paper
1 dated earlier
2006.02575 (2020-06)
Debiased Sinkhorn barycenters

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

We propose a new approach to model the collective dynamics of a population of particles evolving with time. As is often the case in challenging scientific applications, notably single-cell genomics, measuring features for these particles requires destroying them. As a result, the population can only be monitored with periodic snapshots, obtained by sampling a few particles that are sacrificed in exchange for measurements. Given only access to these snapshots, can we reconstruct likely individual trajectories for all other particles? We propose to model these trajectories as collective realizations of a causal Jordan-Kinderlehrer-Otto (JKO) flow of measures: The JKO scheme posits that the new configuration taken by a population at time $t+1$ is one that trades off an improvement, in the sense that it decreases an energy, while remaining close (in Wasserstein distance) to the previous configuration observed at $t$. In order to learn such an energy using only snapshots, we propose JKOnet, a neural architecture that computes (in end-to-end differentiable fashion) the JKO flow given a parametric energy and initial configuration of points. We demonstrate the good performance and robustness of the JKOnet fitting procedure, compared to a more direct forward method.

For agents

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

get_harvested_code_for_paper("2106.06345")
get_code_for_paper("2106.06345")
have("2106.06345")

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

curl https://syntology.ai/api/ran/2106.06345.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.06345.svg)](https://syntology.ai/paper/2106.06345)

Connect an agent — have() is free.