SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.09453 · 2021

RoBERTuito: a pre-trained language model for social media text in Spanish

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 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 3 have no contract verdict; 0 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/2111.09453.json · badge: /api/ran/2111.09453.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
pysentimiento/robertuito canonical (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
compute_category_metrics Ran
ran on a synthesized input
pysentimiento/robertuito/finetune_vs_scratch/context_hate.py
code served (permissive licence) · get_code("23a3786b397491b8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from sklearn.metrics import precision_recall_fscore_support

torch.manual_seed(0)

# Create a simple object to hold predictions and labels
class PredictionOutput:
    def __init__(self, predictions, label_ids):
        self.predictions = predictions
        self.label_ids = label_ids

# Number of categories in extended_hate_categories
# extended_hate_categories = ['CALLS'] + hate_categories (9 categories total)
num_categories = 9
batch_size = 2

# Create random predictions (logits before sigmoid)
predictions = np.random.randn(batch_size, num_categories).astype(np.float32)

# Create binary labels (0 or 1)
label_ids = np.random.randint(0, 2, size=(batch_size, num_categories)).astype(np.int64)

# Create the prediction object
pred = PredictionOutput(predictions=predictions, label_ids=label_ids)

ARGS = {
    'pred': pred
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_datasets Ran
ran on a synthesized input
pysentimiento/robertuito/finetune_vs_scratch/context_hate.py
code served (permissive licence) · get_code("cc949dfaed31c76b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import json
import pandas as pd
import pathlib
import tempfile
from sklearn.model_selection import train_test_split
from datasets import Dataset, Value, ClassLabel, Features

# Create temporary directory and files for testing
temp_dir = tempfile.mkdtemp()

# Create minimal training data
train_data = [
    {
        "title": "Article 1",
        "comments": [
            {
                "id": 1,
                "text": "This is a comment",
                "HATEFUL": 0,
                "CALLS": 0,
                "WOMEN": 0,
                "LGBTI": 0,
                "RACISM": 0,
                "CLASS": 0,
                "POLITICS": 0,
                "DISABLED": 0,
                "APPEARANCE": 0,
                "CRIMINAL": 0
            },
            {
                "id": 2,
                "text": "Another comment here",
                "HATEFUL": 1,
                "CALLS": 1,
                "WOMEN": 0,
                "LGBTI": 0,
                "RACISM": 1,
                "CLASS": 0,
                "POLITICS": 0,
                "DISABLED": 0,
                "APPEARANCE": 0,
                "CRIMINAL": 0
            }
        ]
    },
    {
        "title": "Article 2",
        "comments": [
            {
                "id": 3,
                "text": "Yet another comment",
                "HATEFUL": 0,
                "CALLS": 0,
                "WOMEN": 0,
                "LGBTI": 0,
                "RACISM": 0,
                "CLASS": 0,
                "POLITICS": 0,
                "DISABLED": 0,
                "APPEARANCE": 0,
                "CRIMINAL": 0
            }
        ]
    }
]

# Create minimal test data
test_data = [
    {
        "title": "Test Article",
        "comments": [
            {
                "id": 4,
                "text": "Test comment",
                "HATEFUL": 0,
                "CALLS": 0,
                "WOMEN": 0,
                "LGBTI": 0,
                "RACISM": 0,
                "CLASS": 0,
                "POLITICS": 0,
                "DISABLED": 0,
                "APPEARANCE": 0,
                "CRIMINAL": 0
            }
        ]
    }
]

# Write files
train_path = os.path.join(temp_dir, 'train.json')
test_path = os.path.join(temp_dir, 'test.json')

with open(train_path, 'w') as f:
    json.dump(train_data, f)

with open(test_path, 'w') as f:
    json.dump(test_data, f)

# Define a simple preprocess function that does nothing
def preprocess(text, preprocess_args=None):
    return text

ARGS = {
    'train_path': train_path,
    'test_path': test_path,
    'limit': 2,
    'preprocess_data': False,
    'preprocess_args': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
datasets, pandas, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
serialize Ran
ran on a synthesized input
pysentimiento/robertuito/finetune_vs_scratch/context_hate.py
code served (permissive licence) · get_code("6bd359037885bc59")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    'article': {
        'title': 'Sample Article Title'
    },
    'comment': {
        'text': 'This is a comment',
        'author': 'John Doe',
        'timestamp': '2024-01-01'
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_datasets Not yet run
unverified (harvested, no recorded run)
pysentimiento/robertuito/finetune_vs_scratch/irony.py
code served (permissive licence) · get_code("968608fa8e0a82dc")
How it ran

no invocation recorded.

load_tokenizer Not yet run
unverified (harvested, no recorded run)
pysentimiento/robertuito/finetune_vs_scratch/model.py
code served (permissive licence) · get_code("6898279b83309763")
How it ran

no invocation recorded.

run Not yet run
unverified (harvested, no recorded run)
pysentimiento/robertuito/finetune_vs_scratch/irony.py
code served (permissive licence) · get_code("1cf00f986d4f797e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Since BERT appeared, Transformer language models and transfer learning have become state-of-the-art for Natural Language Understanding tasks. Recently, some works geared towards pre-training specially-crafted models for particular domains, such as scientific papers, medical documents, user-generated texts, among others. These domain-specific models have been shown to improve performance significantly in most tasks. However, for languages other than English such models are not widely available. In this work, we present RoBERTuito, a pre-trained language model for user-generated text in Spanish, trained on over 500 million tweets. Experiments on a benchmark of tasks involving user-generated text showed that RoBERTuito outperformed other pre-trained language models in Spanish. In addition to this, our model achieves top results for some English-Spanish tasks of the Linguistic Code-Switching Evaluation benchmark (LinCE) and has also competitive performance against monolingual models in English tasks. To facilitate further research, we make RoBERTuito publicly available at the HuggingFace model hub together with the dataset used to pre-train it.

For agents

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

get_harvested_code_for_paper("2111.09453")
get_code_for_paper("2111.09453")
have("2111.09453")

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

curl https://syntology.ai/api/ran/2111.09453.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.09453.svg)](https://syntology.ai/paper/2111.09453)

Connect an agent — have() is free.