SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.14892 · ICML · 2026

Relational Structural Causal Models

Elias Bareinboim, Adiba Ejaz, B}, U X ⊕ {s, W } ∨ {p, U B ⊕ ∅ ∨ {p, X}, 𝗆𝖺𝗃𝗈𝗋𝗂𝗍𝗒 𝗆𝖺𝗃𝗈𝗋𝗂𝗍𝗒

arXiv · PDF · Open in the Atlas

Code that ran

10 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (10 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 0 failures of our instrument; 9 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/2606.14892.json · badge: /api/ran/2606.14892.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
CausalAILab/RelationalCausalModels community
Papers with Code archive
10 ran · 9 no recorded run
FunctionStatusWhere it lives
CTFTerm Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("939ddc776d91b25d")
How it ran

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

GroundAttribute Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("e9d44abc2f9da368")
How it ran

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

GroundEntity Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("69a3534e8d9a4fb9")
How it ran

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

GroundRelation Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("991bc0cbb1f5f10d")
How it ran

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

RelationalInstance Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("ce5853a972d13b3c")
How it ran

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

RelationalSchema Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("f8137fae0c342028")
How it ran

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

RelationalSkeleton Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("5f1c149faae8e7af")
How it ran

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

TemplateAttr Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("990e1718e1842af4")
How it ran

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

TemplateEntity Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("f03c15cabc74a95c")
How it ran

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

TemplateRelation Ran
ran on a synthesized input · constructed an object; no result was computed
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("3f2e894d16cfa20c")
How it ran

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

CTF Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("a7652c5cdbe68979")
How it ran

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

Distribution Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("96a0e19b5dcd8a3e")
How it ran

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

SCM Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("921c1cbfb7221616")
How it ran

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

TemplateRSCM Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("2129b7cc0a03385d")
How it ran

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

TemplateRSF Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("865ef8cd65ed603c")
How it ran

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

check_equal Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("6104808ca0104544")
How it ran

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

expand_do Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("3eb413bf692fc9ce")
How it ran

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

gen_ground_attributes Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("84bf74f02146b2d4")
How it ran

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

log Not yet run
unverified (harvested, no recorded run)
CausalAILab/RelationalCausalModels/NCMCounterfactuals/src/scm/rscm.py
pointer only (licence: NONE) · get_code("d4ce1643876ab796")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CausalAILab/RelationalCausalModels 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 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 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 19 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

An artificial intelligence must have a model of its environment that is causal, supporting reasoning about interventions and counterfactuals, and also combinatorial, supporting generalization to unseen combinations of objects. In this work, we formally study when and how such a model can be learned. We develop relational structural causal models, extending structural causal models (Pearl, 2009) to settings where objects and their relations vary. First, we show how answers to not only causal but also observational queries about unseen combinations of objects can not be identified without further assumptions. To enable such identification-including in the presence of unobserved confounding-we define relational causal graphs and derive symbolic identification criteria. Finally, we propose relational neural causal models, a provably correct approach that outperforms non-relational baselines on simulated traffic scenes with varying cars, signals, and pedestrians.

For agents

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

get_harvested_code_for_paper("2606.14892")
get_code_for_paper("2606.14892")
have("2606.14892")

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

curl https://syntology.ai/api/ran/2606.14892.json

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

[![Syntology run record](https://syntology.ai/api/ran/2606.14892.svg)](https://syntology.ai/paper/2606.14892)

Connect an agent — have() is free.