SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.31063 · 2026

Free energy Estimation on Any State Space

José Hernández-Lobato, Yingzhen Li, Yuanqi Du, Jiajun He, Francisco Vargas, Zijing Ou, Carles Domingo-Enrich

arXiv · PDF

Code that ran

5 of 7 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 4 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2605.31063.json · badge: /api/ran/2605.31063.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
ml-jku/DiffUCO canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
J-zin/DNFS community
Papers with Code archive
4 ran · 2 no recorded run
FunctionStatusWhere it lives
AggregationAttentionBlock Ran
ran on a synthesized input
J-zin/DNFS/model.py
pointer only (licence: NONE) · get_code("c3eedc9a8dafba14")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, J-zin/DNFS 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.

AttentionBlock Ran
ran on a synthesized input
J-zin/DNFS/model.py
pointer only (licence: NONE) · get_code("4a0e6e84d5179a79")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, J-zin/DNFS 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.

CausalBlock Ran
ran on a synthesized input
J-zin/DNFS/model.py
pointer only (licence: NONE) · get_code("cc8990444ec48b0e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, J-zin/DNFS 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.

LEOutputLayer Ran
ran on a synthesized input
J-zin/DNFS/model.py
pointer only (licence: NONE) · get_code("08f39766cbfa72f8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, J-zin/DNFS 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.

get_sinusoidal_positional_encoding Ran
ran, honoured the contract we drafted
ml-jku/DiffUCO/Networks/DiffModel.py
pointer only (licence: NONE) · get_code("923527cb6aeb4f92")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ml-jku/DiffUCO 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.

Attention Not yet run
unverified (harvested, no recorded run)
J-zin/DNFS/model.py
pointer only (licence: NONE) · get_code("6ade5b78758c8379")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, J-zin/DNFS 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.

LEquiTFRtModel Not yet run
unverified (harvested, no recorded run)
J-zin/DNFS/model.py
pointer only (licence: NONE) · get_code("2c012ed9cfa16955")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, J-zin/DNFS 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 6 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
get_sinusoidal_positional_encoding 1 other paper
1 dated earlier
2406.01661 (2024-06)
A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization

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

Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformations, ranging from direct estimation, quasistatic integration, to finite-time averaging. Recent work [He and Du et al., 2025] learns neural transports to significantly accelerate the efficiency in the finite-time regime. In this paper, we generalize this framework to arbitrary state spaces. Building on this view, we develop a generalized neural transport learning approach for efficient estimation. Experiments validate the effectiveness and efficiency of the proposed method beyond continuous settings, extending to discrete and multimodal spaces as well as autoregressive settings. Beyond free energy estimation, we establish algebraic identities and reveal a group-theoretic structure linking infinitesimal time reversal and generalized Doob's h-transforms, showing that their compositions form a generalized dihedral group. X P (dx) and Z Q = Q(X ) = X Q(dx), and normalized probability measures P (dx) = P (dx)/Z P and Q(dx) = Q(dx)/Z Q . Assuming Q(dx) ≪ P (dx), the relative free energy is (2) Here, d Q/d P denotes the Radon-Nikodym derivative between the two unnormalized measures. We keep this formulation measure-theoretic, since the state space X does not always need to have a Lebesgue measure, and P and Q may therefore not admit a canonical notion of density, while Equation ( 1) is only the special case where Z P = 1 and Q admit density to Lebesgue measure. This perspective gives rise to a broad family of free energy estimators [Lelièvre et al., 2010], ranging from direct sample reweighting to finite-time path averaging. Representative examples include free energy perturbation (FEP) and the Jarzynski equality (JE), which we discuss in Section B.

For agents

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

get_harvested_code_for_paper("2605.31063")
get_code_for_paper("2605.31063")
have("2605.31063")

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

curl https://syntology.ai/api/ran/2605.31063.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.31063.svg)](https://syntology.ai/paper/2605.31063)

Connect an agent — have() is free.