SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.13838 · ICLR · 2025

Circuit Transformer: A Transformer That Preserves Logical Equivalence

Jun Wang, Lei Chen, Mingxuan Yuan, Xihan Li, Xing Li, Xing Zhang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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 0 have no contract verdict; 1 failure 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/2403.13838.json · badge: /api/ran/2403.13838.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
snowkylin/circuit-transformer canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
masked_accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
snowkylin/circuit-transformer/circuit_transformer/tensorflow_transformer.py
pointer only (licence: NONE) · get_code("b6eb0e75ece3119a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, snowkylin/circuit-transformer 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.

int_to_node Not yet run
unverified (harvested, no recorded run)
snowkylin/circuit-transformer/circuit_transformer/model.py
pointer only (licence: NONE) · get_code("aaace84da64c1b81")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, snowkylin/circuit-transformer 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.

plot_network Not yet run
unverified (harvested, no recorded run)
snowkylin/circuit-transformer/circuit_transformer/utils.py
pointer only (licence: NONE) · get_code("b7fdc20493e7a402")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, snowkylin/circuit-transformer 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Implementing Boolean functions with circuits consisting of logic gates is fundamental in digital computer design. However, the implemented circuit must be exactly equivalent, which hinders generative neural approaches on this task due to their occasionally wrong predictions. In this study, we introduce a generative neural model, the "Circuit Transformer", which eliminates such wrong predictions and produces logic circuits strictly equivalent to given Boolean functions. The main idea is a carefully designed decoding mechanism that builds a circuit step-by-step by generating tokens, which has beneficial "cutoff properties" that block a candidate token once it invalidate equivalence. In such a way, the proposed model works similar to typical LLMs while logical equivalence is strictly preserved. A Markov decision process formulation is also proposed for optimizing certain objectives of circuits. Experimentally, we trained an 88-million-parameter Circuit Transformer to generate equivalent yet more compact forms of input circuits, outperforming existing neural approaches on both synthetic and real world benchmarks, without any violation of equivalence constraints.

For agents

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

get_harvested_code_for_paper("2403.13838")
get_code_for_paper("2403.13838")
have("2403.13838")

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

curl https://syntology.ai/api/ran/2403.13838.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.13838.svg)](https://syntology.ai/paper/2403.13838)

Connect an agent — have() is free.