SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.13755 · ICML · 2023

Retrosynthetic Planning with Dual Value Networks

Yingce Xia, Tao Qin, Tie-Yan Liu, Austin Tripp, Shufang Xie, Marwin Segler, Guoqing Liu, Krzysztof Maziarz, Zongzhang Zhang, Di Xue

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 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; 2 failures of our instrument; 4 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/2301.13755.json · badge: /api/ran/2301.13755.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
DiXue98/PDVN canonical (classifier label)
classifier basis: classifier_2025
4 ran · 4 no recorded run
FunctionStatusWhere it lives
MDTreeMolNode Ran
ran on a synthesized input · constructed an object; no result was computed
DiXue98/PDVN/retro_star/alg/online_mcts.py
pointer only (licence: NONE) · get_code("975ee49ff6d10faa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DiXue98/PDVN 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.

MDTreeReactionNode Ran
ran on a synthesized input · constructed an object; no result was computed
DiXue98/PDVN/retro_star/alg/online_mcts.py
pointer only (licence: NONE) · get_code("94b1fe17449d8abc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DiXue98/PDVN 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.

generate_training_data Ran
ran; our contract draft was wrong, not the code
DiXue98/PDVN/retro_star/alg/online_mcts.py
pointer only (licence: NONE) · get_code("682acc4827c8797e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DiXue98/PDVN 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.

take_reaction Ran
ran; our contract draft was wrong, not the code
DiXue98/PDVN/retro_star/alg/online_mcts.py
pointer only (licence: NONE) · get_code("9f8d6d847adf5805")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DiXue98/PDVN 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.

OnlineSearchTree Not yet run
unverified (harvested, no recorded run)
DiXue98/PDVN/retro_star/alg/online_mcts.py
pointer only (licence: NONE) · get_code("9e6372aa6ff505fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DiXue98/PDVN 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.

final_backup Not yet run
unverified (harvested, no recorded run)
DiXue98/PDVN/retro_star/alg/online_mcts.py
pointer only (licence: NONE) · get_code("f22ffa6d1768e32f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DiXue98/PDVN 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.

online_mcts Not yet run
unverified (harvested, no recorded run)
DiXue98/PDVN/retro_star/alg/online_mcts.py
pointer only (licence: NONE) · get_code("7b98ce5005a17b93")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DiXue98/PDVN 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.

simulate Not yet run
unverified (harvested, no recorded run)
DiXue98/PDVN/retro_star/alg/online_mcts.py
pointer only (licence: NONE) · get_code("d9c6080c1c0cf43e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DiXue98/PDVN 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery and materials design. Recently, the combination of ML-based single-step reaction predictors with multi-step planners has led to promising results. However, the single-step predictors are mostly trained offline to optimize the single-step accuracy, without considering complete routes. Here, we leverage reinforcement learning (RL) to improve the single-step predictor, by using a tree-shaped MDP to optimize complete routes. Specifically, we propose a novel online training algorithm, called Planning with Dual Value Networks (PDVN), which alternates between the planning phase and updating phase. In PDVN, we construct two separate value networks to predict the synthesizability and cost of molecules, respectively. To maintain the singlestep accuracy, we design a two-branch network structure for the single-step predictor. On the widely-used USPTO dataset, our PDVN algorithm improves the search success rate of existing multi-step planners (e.g., increasing the success rate from 85.79% to 98.95% for Retro*). Additionally, PDVN helps find shorter synthesis routes (e.g., reducing the average route length from 5.76 to 4.83 for Retro*). Our code is available at https://github.com/DiXue98/PDVN.

For agents

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

get_harvested_code_for_paper("2301.13755")
get_code_for_paper("2301.13755")
have("2301.13755")

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

curl https://syntology.ai/api/ran/2301.13755.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.13755.svg)](https://syntology.ai/paper/2301.13755)

Connect an agent — have() is free.