Immanuel Sulzer, Tobias Buck
5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 4 failures of our instrument; 1 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/2312.06015.json · badge: /api/ran/2312.06015.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.
| Repository | Role | Ran |
|---|---|---|
| rtqichen/torchdiffeq | canonical (classifier label) classifier basis: classifier_2025 |
2 ran · 1 no recorded run |
| Immi000/ChemicalNeuralODE | canonical (classifier label) classifier basis: census |
2 ran · 0 no recorded run |
| immi000/chemicalneuralode | canonical (classifier label) classifier basis: classifier_2025 |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| NeuralODE | Ran ran on a synthesized input · constructed an object; no result was computed |
immi000/chemicalneuralode/models.py pointer only (licence: NONE) · get_code("d57c386627f127d8") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, immi000/chemicalneuralode 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. |
| deriv | Ran ran; our contract draft was wrong, not the code |
Immi000/ChemicalNeuralODE/utilities.py pointer only (licence: NONE) · get_code("5ffc1681cd25c0a4") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, Immi000/ChemicalNeuralODE 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. |
| deriv2 | Ran ran; our contract draft was wrong, not the code |
Immi000/ChemicalNeuralODE/utilities.py pointer only (licence: NONE) · get_code("da79c61c5cedce35") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, Immi000/ChemicalNeuralODE 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. |
| log_normal_pdf | Ran ran; our contract draft was wrong, not the code |
rtqichen/torchdiffeq/examples/latent_ode.py code served (permissive licence) · get_code("f126b8e6ddaf1641") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) 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.
|
| normal_kl | Ran ran; our contract draft was wrong, not the code |
rtqichen/torchdiffeq/examples/latent_ode.py code served (permissive licence) · get_code("ef202a31135044d3") How it ranRan in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) 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.
|
| generate_spiral2d | Not yet run unverified (harvested, no recorded run) |
rtqichen/torchdiffeq/examples/latent_ode.py code served (permissive licence) · get_code("8349d08a3b7d71f1") How it ranno invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back. |
Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| normal_kl | 4 other papers 3 dated earlier, 1 later |
2102.02248 (2021-02) Reduced-order Model for Fluid Flows via Neural Ordinary Differential Equations |
2107.11350 (2021-07) Heteroscedastic Temporal Variational Autoencoder for Irregular Time Series 2202.12373 (2022-02) Learning Proper Orthogonal Decomposition of Complex Dynamics Using Heavy-ball Neural ODEs and 1 more not named here |
| log_normal_pdf | 1 other paper 1 later |
2402.10635 (2024-02) ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling |
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In astrophysics, solving complex chemical reaction networks is essential but computationally demanding due to the high dimensionality and stiffness of the ODE systems. Traditional approaches for reducing computational load are often specialized to specific chemical networks and require expert knowledge. This paper introduces a machine learning-based solution employing autoencoders for dimensionality reduction and a latent space neural ODE solver to accelerate astrochemical reaction network computations. Additionally, we propose a cost-effective latent space linear function solver as an alternative to neural ODEs. These methods are assessed on a dataset comprising 29 chemical species and 224 reactions. Our findings demonstrate that the neural ODE achieves a 55x speedup over the baseline model while maintaining significantly higher accuracy by up to two orders of magnitude reduction in relative error. Furthermore, the linear latent model enhances accuracy and achieves a speedup of up to 4000x compared to standard methods. Chemistry plays a pivotal role in astrophysical simulations, influencing phenomena in the interstellar medium [11] and star formation processes [6]. The chemical composition of species not only impacts physical processes but also affects observational outcomes, particularly line emissions [e.g. 9]. However, solving chemical reaction networks poses challenges, given the need to handle numerous tightly coupled stiff ODEs, arising from distinct reaction timescales. Existing simplification techniques, such as species omission and grouping [16], instantaneous equilibrium assumption [7], or exploiting sparse reaction matrices [8], often rely heavily on specific chemical networks and may not always yield effective results. As an alternative, Grassi et al. demonstrated the effectiveness of autoencoders for dimensionality reduction in astrochemistry. Furthermore, the advent of neural ODEs [4,12] has opened new possibilities for novel ODE solver methods in astrochemical modelling. Our approach seeks to integrate these techniques, aiming to create an easily implementable and efficient solver for chemical reaction networks. Our code is publicly available on Github: (URL: https://github.com/Immi000/ChemicalNeuralODE). The code is documented and can easily adapted for reuse. A neural ODE essentially uses a neural network (NN) f to model the derivative of a vector valued function x(t) that depends on a parameter t (time in our application): dx(t) dt = f (x(t), t). Our model for solving chemical reaction networks comprises three components: an encoder φ, the Preprint. Under review.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2312.06015")
get_code_for_paper("2312.06015")
have("2312.06015")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2312.06015.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2312.06015)
Connect an agent — have() is free.