SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.01207 · 2024

Efficient Causal Graph Discovery Using Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

10 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 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/2402.01207.json · badge: /api/ran/2402.01207.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
superkaiba/causal-llm-bfs canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; our contract draft was wrong, not the code
superkaiba/causal-llm-bfs/metrics.py
pointer only (licence: NONE) · get_code("46bfc96909c4ee22")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

adj_mat_to_edge_list Ran
ran, honoured the contract we drafted
superkaiba/causal-llm-bfs/utils.py
pointer only (licence: NONE) · get_code("e4418d76e51236a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

adjacency_matrix_to_edge_list Ran
ran, honoured the contract we drafted
superkaiba/causal-llm-bfs/algs/llm/utils.py
pointer only (licence: NONE) · get_code("932f6c45fffdc7c2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

dag_to_adj_mat Ran
ran, honoured the contract we drafted
superkaiba/causal-llm-bfs/utils.py
pointer only (licence: NONE) · get_code("2856ad4b6b397b6c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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_data_prompt Ran
ran; our contract draft was wrong, not the code
superkaiba/causal-llm-bfs/algs/llm/bfs_prompts.py
pointer only (licence: NONE) · get_code("d2f102469e9957c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

is_dag Ran
ran, violated the contract we drafted
superkaiba/causal-llm-bfs/utils.py
pointer only (licence: NONE) · get_code("5bd72185d3deeffe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

precision Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
superkaiba/causal-llm-bfs/algs/llm/utils.py
pointer only (licence: NONE) · get_code("ab810b4b69cebe75")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

precision Ran
ran; our contract draft was wrong, not the code
superkaiba/causal-llm-bfs/metrics.py
pointer only (licence: NONE) · get_code("b1a73044ab13bc1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

recall Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
superkaiba/causal-llm-bfs/algs/llm/utils.py
pointer only (licence: NONE) · get_code("4e1ec21825865428")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

recall Ran
ran; our contract draft was wrong, not the code
superkaiba/causal-llm-bfs/metrics.py
pointer only (licence: NONE) · get_code("99eaef19e981c387")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

llm_bfs Not yet run
unverified (harvested, no recorded run)
superkaiba/causal-llm-bfs/algs/llm/bfs.py
pointer only (licence: NONE) · get_code("e2b8b14caa84e2c7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

llm_pairwise Not yet run
unverified (harvested, no recorded run)
superkaiba/causal-llm-bfs/algs/llm/pairwise.py
pointer only (licence: NONE) · get_code("7f36cd5159296995")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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.

notears_linear Not yet run
unverified (harvested, no recorded run)
superkaiba/causal-llm-bfs/algs/notears/linear.py
pointer only (licence: NONE) · get_code("8121d0e3bc3faff7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, superkaiba/causal-llm-bfs 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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 12 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
notears_linear 8 other papers
6 dated earlier, 2 later
1803.01422 (2018-03)
DAGs with NO TEARS: Continuous Optimization for Structure Learning
1909.13189 (2019-09)
Learning Sparse Nonparametric DAGs
2006.10201 (2020-06)
On the Role of Sparsity and DAG Constraints for Learning Linear DAGs
and 5 more not named here

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

We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this requires a quadratic number of queries which quickly becomes impractical for larger causal graphs. In contrast, the proposed framework uses a breadth-first search (BFS) approach which allows it to use only a linear number of queries. We also show that the proposed method can easily incorporate observational data when available, to improve performance. In addition to being more time and data-efficient, the proposed framework achieves state-of-the-art results on real-world causal graphs of varying sizes. The results demonstrate the effectiveness and efficiency of the proposed method in discovering causal relationships, showcasing its potential for broad applicability in causal graph discovery tasks across different domains.

For agents

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

get_harvested_code_for_paper("2402.01207")
get_code_for_paper("2402.01207")
have("2402.01207")

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

curl https://syntology.ai/api/ran/2402.01207.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.01207.svg)](https://syntology.ai/paper/2402.01207)

Connect an agent — have() is free.