SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.00393 · 2026

Brazilian Portuguese Image Captioning with Transformers: A Study on Cross-Native-Translated Dataset

Thiago Paixão, Gabriel Bromonschenkel, Alessandro Koerich, Hilário Tomaz, Alves De Oliveira

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 4 failures of our instrument; 0 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/2602.00393.json · badge: /api/ran/2602.00393.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
laicsiifes/transformer-caption-ptbr canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
config_vars Ran
ran; our contract draft was wrong, not the code
laicsiifes/transformer-caption-ptbr/metrics_analysis/utils/config.py
pointer only (licence: NONE) · get_code("9433e74de602c013")
How it ran

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

encode_image Ran
ran; our contract draft was wrong, not the code
laicsiifes/transformer-caption-ptbr/vlm_zero_shot/src/inference_sambanova_openai.py
pointer only (licence: NONE) · get_code("9303356715a06b3c")
How it ran

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

join_datasets Ran
ran; our contract draft was wrong, not the code
laicsiifes/transformer-caption-ptbr/metrics_analysis/utils/data_processing.py
pointer only (licence: NONE) · get_code("cd5c340cf2b35248")
How it ran

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

select_incorrect_data Ran
ran; our contract draft was wrong, not the code
laicsiifes/transformer-caption-ptbr/metrics_analysis/utils/data_processing.py
pointer only (licence: NONE) · get_code("ec88284c1848a453")
How it ran

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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Image captioning (IC) refers to the automatic generation of natural language descriptions for images, with applications ranging from social media content generation to assisting individuals with visual impairments. While most research has been focused on English-based models, low-resource languages such as Brazilian Portuguese face significant challenges due to the lack of specialized datasets and models. Several studies create datasets by automatically translating existing ones to mitigate resource scarcity. This work addresses this gap by proposing a cross-native-translated evaluation of Transformer-based vision and language models for Brazilian Portuguese IC. We use a version of Flickr30K comprised of captions manually created by native Brazilian Portuguese speakers and compare it to a version with captions automatically translated from English to Portuguese. The experiments include a cross-context approach, where models trained on one dataset are tested on the other to assess the translation impact. Additionally, we incorporate attention maps for model inference interpretation and use the CLIP-Score metric to evaluate the image-description alignment. Our findings show that Swin-DistilBERTimbau consistently outperforms other models, demonstrating strong generalization across datasets. ViTucano, a Brazilian Portuguese pre-trained VLM, surpasses larger multilingual models (GPT-4o, LLaMa 3.2 Vision) in traditional text-based evaluation metrics, while GPT-4 models achieve the highest CLIP-Score, highlighting improved image-text alignment. Attention analysis reveals systematic biases, including gender misclassification, object enumeration errors, and spatial inconsistencies. The datasets and the models generated and analyzed during the current study are available in: https://github.com/laicsiifes/transformer-caption-ptbr.

For agents

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

get_harvested_code_for_paper("2602.00393")
get_code_for_paper("2602.00393")
have("2602.00393")

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

curl https://syntology.ai/api/ran/2602.00393.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.00393.svg)](https://syntology.ai/paper/2602.00393)

Connect an agent — have() is free.