SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.13093 · NeurIPS · 2022

Learning Deep Input-Output Stable Dynamics

Ryosuke Kojima, Yuji Okamoto

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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 2 have no contract verdict; 0 failures of our instrument; 2 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/2206.13093.json · badge: /api/ran/2206.13093.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
clinfo/deepiostability canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
FunctionStatusWhere it lives
DiosDataset Ran
ran on a synthesized input
clinfo/deepiostability/dios/model.py
code served (permissive licence) · get_code("c45847cb00314189")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) 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

# Create a simple data object that mimics the expected structure
class SimpleData:
    def __init__(self, num_samples):
        self.num = num_samples
        self.input = torch.randn(num_samples, 5)
        self.state = torch.randn(num_samples, 3)
        self.obs = torch.randn(num_samples, 7)

# Create a simple transform function
def simple_transform(x):
    return x * 2.0

# Create the data object
data_obj = SimpleData(num_samples=10)

INIT_ARGS = {
    'data': data_obj,
    'transform': simple_transform,
    'train': True
}

# For Dataset classes, the computation method is __getitem__
METHOD = '__getitem__'

ARGS = {
    'idx': 3
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
DiosSSM Ran
ran on a synthesized input
clinfo/deepiostability/dios/model.py
code served (permissive licence) · get_code("2f26bc5bbbf2c465")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was 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
import torch.nn as nn
import logging

# Set up a minimal logger
logging.basicConfig(level=logging.INFO)

# Create a minimal system_model stand-in
class MinimalSystemModel(nn.Module):
    def __init__(self, state_dim=5, obs_dim=7, input_dim=3):
        super().__init__()
        self.state_dim = state_dim
        self.obs_dim = obs_dim
        self.input_dim = input_dim
        self.fc = nn.Linear(state_dim, state_dim)
        
    def forward(self, obs, input_=None, state=None, with_generated=False, step_wise_loss=False, epoch=None):
        batch_size = obs.shape[0]
        seq_len = obs.shape[1] if len(obs.shape) > 2 else 1
        
        loss_dict = {
            'reconstruction': torch.tensor(0.5),
            'kl': torch.tensor(0.3),
            '*metric': torch.tensor(0.1)
        }
        
        if with_generated:
            state_generated = torch.randn(batch_size, seq_len, self.state_dim)
            obs_generated = torch.randn(batch_size, seq_len, self.obs_dim)
            hh = torch.randn(batch_size, seq_len, self.state_dim)
            return loss_dict, state_generated, obs_generated, hh
        
        return loss_dict
    
    def simulate_one_step(self, state):
        return self.fc(state)
    
    def simulate(self, init_state, batch_size=None, step=100, input_data=None):
        if batch_size is None:
            batch_size = init_state.shape[0]
        state = init_state
        states = [state]
        for _ in range(step):
            state = self.simulate_one_step(state)
            states.append(state)
        state_traj = torch.stack(states, dim=1)
        obs_generated = torch.randn(batch_size, step + 1, 7)
        return state_traj, obs_generated

# Create config dict
config = {
    'state_dim': 5,
    'obs_dim': 7,
    'input_dim': 3,
    'learning_rate': 0.001
}

# Create system model
system_model = MinimalSystemModel(state_dim=5, obs_dim=7, input_dim=3)

# Device
device = torch.device('cpu')

INIT_ARGS = {
    'config': config,
    'system_model': system_model,
    'device': device
}

# Create a batch for _compute_batch_loss
batch = {
    'obs': torch.randn(2, 10, 7),  # batch_size=2, seq_len=10, obs_dim=7
    'input': torch.randn(2, 10, 3),  # batch_size=2, seq_len=10, input_dim=3
    'state': torch.randn(2, 10, 5)   # batch_size=2, seq_len=10, state_dim=5
}

epoch = 5

ARGS = {
    'batch': batch,
    'epoch': epoch
}

METHOD = '_compute_batch_loss'
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
LossLogger Not yet run
unverified (harvested, no recorded run)
clinfo/deepiostability/dios/model.py
code served (permissive licence) · get_code("b000dd20e6eb805e")
How it ran

no invocation recorded.

generate_cmap Not yet run
unverified (harvested, no recorded run)
clinfo/deepiostability/dios/plot.py
code served (permissive licence) · get_code("d18ae76c346d9f11")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Learning stable dynamics from observed time-series data is an essential problem in robotics, physical modeling, and systems biology. Many of these dynamics are represented as an inputs-output system to communicate with the external environment. In this study, we focus on input-output stable systems, exhibiting robustness against unexpected stimuli and noise. We propose a method to learn nonlinear systems guaranteeing the input-output stability. Our proposed method utilizes the differentiable projection onto the space satisfying the Hamilton-Jacobi inequality to realize the input-output stability. The problem of finding this projection can be formulated as a quadratic constraint quadratic programming problem, and we derive the particular solution analytically. Also, we apply our method to a toy bistable model and the task of training a benchmark generated from a glucoseinsulin simulator. The results show that the nonlinear system with neural networks by our method achieves the input-output stability, unlike naive neural networks. Our code is available at https://github.com/clinfo/DeepIOStability.

For agents

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

get_harvested_code_for_paper("2206.13093")
get_code_for_paper("2206.13093")
have("2206.13093")

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

curl https://syntology.ai/api/ran/2206.13093.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.13093.svg)](https://syntology.ai/paper/2206.13093)

Connect an agent — have() is free.