SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.12934 · 2023

Generative Flow Networks as Entropy-Regularized RL

arXiv · PDF · Open in the Atlas

Code that ran

4 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; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 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/2310.12934.json · badge: /api/ran/2310.12934.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
d-tiapkin/gflownet-rl canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
FunctionStatusWhere it lives
edge_match Ran
ran, violated the contract we drafted
d-tiapkin/gflownet-rl/mols/mol_mdp_ext.py
code served (permissive licence) · get_code("6b452c8d0cc45c99")
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 1, dtype family float, shape (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)

# The function edge_match compares the 'bond' key in two dictionaries
# x1 and x2 are expected to be dicts with a 'bond' key

x1 = {
    'bond': torch.tensor([1, 0, 1, 0], dtype=torch.int32)
}

x2 = {
    'bond': torch.tensor([1, 0, 1, 0], dtype=torch.int32)
}

ARGS = {
    'x1': x1,
    'x2': x2
}
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 1, dtype family float, shape (4,) — shape (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
mol2graph Ran
ran; our contract draft was wrong, not the code
d-tiapkin/gflownet-rl/mols/model_block.py
pointer only (licence: MIT); the stored copy get_code serves, from ZRNB/PLUS, is pointer only (licence: NONE) · get_code("f763f98f79152e0e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ZRNB/PLUS, 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.

mols2batch Ran
ran; our contract draft was wrong, not the code
d-tiapkin/gflownet-rl/mols/model_atom.py
pointer only (licence: MIT); the stored copy get_code serves, from ZRNB/PLUS, is pointer only (licence: NONE) · get_code("06477cbf36090384")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from ZRNB/PLUS, 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.

node_match Ran
ran, violated the contract we drafted
d-tiapkin/gflownet-rl/mols/mol_mdp_ext.py
code served (permissive licence) · get_code("514f704ea4cae3e4")
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 bool, 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)

x1 = {'block': 1}
x2 = {'block': 1}

ARGS = {
    'x1': x1,
    'x2': x2
}
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 bool, 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
detailed_balance_loss Not yet run
unverified (harvested, no recorded run)
d-tiapkin/gflownet-rl/mols/gflownet.py
pointer only (licence: MIT); the stored copy get_code serves, from GFNOrg/GFN_vs_HVI, is pointer only (licence: NONE) · get_code("c8525326061a88fd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from GFNOrg/GFN_vs_HVI, 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.

tb_lambda_loss Not yet run
unverified (harvested, no recorded run)
d-tiapkin/gflownet-rl/mols/gflownet.py
code served (permissive licence) · get_code("f99fcc80e4f63a87")
How it ran

no invocation recorded.

trajectory_balance_loss Not yet run
unverified (harvested, no recorded run)
d-tiapkin/gflownet-rl/mols/gflownet.py
pointer only (licence: MIT); the stored copy get_code serves, from GFNOrg/GFN_vs_HVI, is pointer only (licence: NONE) · get_code("afa974460f51f1a5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from GFNOrg/GFN_vs_HVI, 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 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, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 2 later) and 1 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
mols2batch 4 other papers
3 dated earlier, 1 later
2106.04399 (2021-06)
Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
2302.04040 (2023-02)
Sample-efficient Multi-objective Molecular Optimization with GFlowNets
2302.05793 (2023-02)
Distributional GFlowNets with Quantile Flows
and 1 more not named here
edge_match 2 other papers
2 dated earlier
2302.04040 (2023-02)
Sample-efficient Multi-objective Molecular Optimization with GFlowNets
2302.05793 (2023-02)
Distributional GFlowNets with Quantile Flows
mol2graph 2 other papers
1 dated earlier, 1 later
2106.04399 (2021-06)
Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
2510.00805 (2025-10)
Planning-Augmented Sampling with Early Guidance for High-Reward Discovery
node_match 2 other papers
2 dated earlier
2302.04040 (2023-02)
Sample-efficient Multi-objective Molecular Optimization with GFlowNets
2302.05793 (2023-02)
Distributional GFlowNets with Quantile Flows
detailed_balance_loss 1 other paper
1 dated earlier
2210.00580 (2022-10)
GFlowNets and variational inference
trajectory_balance_loss 1 other paper
1 dated earlier
2210.00580 (2022-10)
GFlowNets and variational inference

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

The recently proposed generative flow networks (GFlowNets) are a method of training a policy to sample compositional discrete objects with probabilities proportional to a given reward via a sequence of actions. GFlowNets exploit the sequential nature of the problem, drawing parallels with reinforcement learning (RL). Our work extends the connection between RL and GFlowNets to a general case. We demonstrate how the task of learning a generative flow network can be efficiently redefined as an entropy-regularized RL problem with a specific reward and regularizer structure. Furthermore, we illustrate the practical efficiency of this reformulation by applying standard soft RL algorithms to GFlowNet training across several probabilistic modeling tasks. Contrary to previously reported results, we show that entropic RL approaches can be competitive against established GFlowNet training methods. This perspective opens a direct path for integrating RL principles into the realm of generative flow networks.

For agents

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

get_harvested_code_for_paper("2310.12934")
get_code_for_paper("2310.12934")
have("2310.12934")

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

curl https://syntology.ai/api/ran/2310.12934.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.12934.svg)](https://syntology.ai/paper/2310.12934)

Connect an agent — have() is free.