SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.09353 · ICLR · 2025

Causal Graphical Models for Vision-Language Compositional Understanding

Enver Sangineto, Rita Cucchiara, Lorenzo Baraldi, Fiorenzo Parascandolo, Nicholas Moratelli, Aimagelab

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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, 1 violated it and 0 have no contract verdict; 5 failures 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/2412.09353.json · badge: /api/ran/2412.09353.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
aimagelab/COGT canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
aimagelab/COGT/dataset.py
pointer only (licence: NONE) · get_code("bc629eb0de6e6850")
How it ran

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

compute_binary_attention Ran
ran, violated the contract we drafted
aimagelab/COGT/dataset.py
pointer only (licence: NONE) · get_code("1104139f9c22fb14")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aimagelab/COGT 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_xvlm_transform Ran
ran; our contract draft was wrong, not the code
aimagelab/COGT/paths.py
pointer only (licence: NONE) · get_code("ce1862d4252d2941")
How it ran

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

list_of_strings Ran
ran; our contract draft was wrong, not the code
aimagelab/COGT/paths.py
pointer only (licence: NONE) · get_code("19ee4683eda506c6")
How it ran

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

metrics_format Ran
ran; our contract draft was wrong, not the code
aimagelab/COGT/trainer.py
pointer only (licence: NONE) · get_code("1e895ae90b71ab57")
How it ran

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

process_metrics Ran
ran; our contract draft was wrong, not the code
aimagelab/COGT/trainer.py
pointer only (licence: NONE) · get_code("7c436ff0c99d4f94")
How it ran

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

compute_likelihood Not yet run
unverified (harvested, no recorded run)
aimagelab/COGT/trainer.py
pointer only (licence: NONE) · get_code("23bd7ad447a39f68")
How it ran

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

get_compositional_data_loader Not yet run
unverified (harvested, no recorded run)
aimagelab/COGT/dataset.py
pointer only (licence: NONE) · get_code("0bc8abbd7998fcf8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aimagelab/COGT 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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 0 later) and 7 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
list_of_strings 8 other papers
6 dated earlier, 2 the same month
2112.05745 (2021-12)
A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis
2308.13320 (2023-08)
Fine-tuning can cripple your foundation model; preserving features may be the solution
2310.19046 (2023-10)
Large Language Models as Evolutionary Optimizers
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

Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image caption as a "bag of words". As a result, they perform poorly on compositional tasks, which require a deeper understanding of the different entities of a sentence (subject, verb, etc.) jointly with their mutual relationships in order to be solved. In this paper, we model the dependency relations among textual and visual tokens using a Causal Graphical Model (CGM), built using a dependency parser, and we train a decoder conditioned by the VLM visual encoder. Differently from standard autoregressive or parallel predictions, our decoder's generative process is partially-ordered following the CGM structure. This structure encourages the decoder to learn only the main causal dependencies in a sentence discarding spurious correlations. Using extensive experiments on five compositional benchmarks, we show that our method significantly outperforms all the state-of-the-art compositional approaches by a large margin, and it also improves over methods trained using much larger datasets. Our model weights and code are publicly available. 1

For agents

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

get_harvested_code_for_paper("2412.09353")
get_code_for_paper("2412.09353")
have("2412.09353")

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

curl https://syntology.ai/api/ran/2412.09353.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.09353.svg)](https://syntology.ai/paper/2412.09353)

Connect an agent — have() is free.