SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.08629 · ICML · 2026

CauScale: Neural Causal Discovery at Scale

Chaochao Lu, Yu Qiao, Bo Peng, Sirui Chen, Jiaguo Tian, Col Attn, Row Attn, Ffn Col, Attn 𝜔, Row Ffn

arXiv · PDF · Open in the Atlas

Code that ran

5 of 13 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 4 have no contract verdict; 1 failure of our instrument; 8 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/2602.08629.json · badge: /api/ran/2602.08629.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
OpenCausaLab/CauScale community
Papers with Code archive
5 ran · 8 no recorded run
FunctionStatusWhere it lives
ColumnSelfAttention Ran
ran on a synthesized input
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("2ed678a1841e3e19")
How it ran

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

FeedForwardNetwork Ran
ran on a synthesized input
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("a6ebf0e756f9f41e")
How it ran

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

ReductionUnit Ran
ran on a synthesized input
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("f49ecb7cdd1e7573")
How it ran

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

RowSelfAttention Ran
ran on a synthesized input
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("87e39a6a2a2e4d2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenCausaLab/CauScale 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_params_groups Ran
ran; our contract draft was wrong, not the code
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("1813b57d661711e4")
How it ran

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

AxialTransformerLayer Not yet run
unverified (harvested, no recorded run)
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("fec691e51c077063")
How it ran

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

CauScale Not yet run
unverified (harvested, no recorded run)
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("9e5aef6bee42b631")
How it ran

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

Data2GraphLayer Not yet run
unverified (harvested, no recorded run)
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("719d106a1829b091")
How it ran

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

DataGraphBlock Not yet run
unverified (harvested, no recorded run)
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("a952c9b2bb724d19")
How it ran

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

NormalizedResidualBlock Not yet run
unverified (harvested, no recorded run)
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("cdf5909ba05b3e63")
How it ran

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

PoolingFFN Not yet run
unverified (harvested, no recorded run)
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("1136ad6033a74155")
How it ran

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

TopLayer Not yet run
unverified (harvested, no recorded run)
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("476515971241c019")
How it ran

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

TwoStreamEncoder Not yet run
unverified (harvested, no recorded run)
OpenCausaLab/CauScale/src/model/causcale.py
pointer only (licence: NONE) · get_code("75d5435bd71790c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, OpenCausaLab/CauScale 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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

Causal discovery is essential for advancing datadriven fields such as scientific AI and data analysis, yet existing approaches face significant time-and space-efficiency bottlenecks when scaling to large graphs. To address this challenge, we present CauScale, a neural architecture designed for efficient causal discovery that scales inference to graphs with up to 1000 nodes. CauScale improves time efficiency via a reduction unit that compresses data embeddings and improves space efficiency by adopting tied attention weights to avoid maintaining axis-specific attention maps. To keep high causal discovery accuracy, CauScale adopts a two-stream design: a data stream extracts relational evidence from high-dimensional observations, while a graph stream integrates statistical graph priors and preserves key structural signals. CauScale successfully scales to 500node graphs during training, where prior work fails due to space limitations. Across testing data with varying graph scales and causal mechanisms, CauScale achieves 99.6% mAP on indistribution data and 84.4% on out-of-distribution data, while delivering 4×-13,000× inference speedups over prior methods. Our project page is at https://github.com/OpenCausaLab/CauScale.

For agents

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

get_harvested_code_for_paper("2602.08629")
get_code_for_paper("2602.08629")
have("2602.08629")

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

curl https://syntology.ai/api/ran/2602.08629.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.08629.svg)](https://syntology.ai/paper/2602.08629)

Connect an agent — have() is free.