SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.17848 · 2024

ArabicaQA: A Comprehensive Dataset for Arabic Question Answering

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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; 1 failure of our instrument; 1 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/2403.17848.json · badge: /api/ran/2403.17848.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
datascienceuibk/arabicaqa canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
get_bert_tensorizer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
datascienceuibk/arabicaqa/DPR/DPR_module/hf_models.py
code served (permissive licence) · get_code("7733153419c4eaf0")
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 BertTensorizer. 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
from transformers import BertTokenizer, BertConfig, BertModel

torch.manual_seed(0)

# Create a minimal stand-in tokenizer that has the required attributes/methods
class MinimalTokenizer:
    def __init__(self):
        self.pad_token_id = 0
        self.sep_token_id = 102
        self.vocab = {
            '[CLS]': 101,
            '[SEP]': 102,
            '[PAD]': 0,
            'hello': 7592,
            'world': 2088,
        }
    
    def encode(self, text, text_pair=None, add_special_tokens=True, max_length=128, pad_to_max_length=False, truncation=True):
        # Simple mock: return a list of token ids
        tokens = [101] + [7592, 2088] + [102]  # [CLS] hello world [SEP]
        if text_pair:
            tokens = tokens + [2088] + [102]  # add text_pair tokens and [SEP]
        if len(tokens) > max_length:
            tokens = tokens[:max_length]
            tokens[-1] = 102  # ensure last token is [SEP]
        return tokens
    
    def convert_ids_to_tokens(self, token_ids):
        id_to_token = {v: k for k, v in self.vocab.items()}
        id_to_token[101] = '[CLS]'
        id_to_token[102] = '[SEP]'
        id_to_token[0] = '[PAD]'
        id_to_token[7592] = 'hello'
        id_to_token[2088] = 'world'
        return [id_to_token.get(tid, f'token_{tid}') for tid in token_ids]
    
    def decode(self, token_ids, skip_special_tokens=True):
        tokens = self.convert_ids_to_tokens(token_ids)
        if skip_special_tokens:
            tokens = [t for t in tokens if not t.startswith('[')]
        return ' '.join(tokens)

# Prepare arguments for get_bert_tensorizer
tokenizer = MinimalTokenizer()

ARGS = {
    'sequence_length': 128,
    'pretrained_model_cfg': 'bert-base-uncased',
    'do_lower_case': True,
    'tokenizer': tokenizer,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BertTensorizer — a BertTensorizer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BertTensorizer 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
get_bert_tokenizer Not yet run
unverified (harvested, no recorded run)
datascienceuibk/arabicaqa/DPR/DPR_module/hf_models.py
code served (permissive licence) · get_code("95a1256ca79d5495")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

In this paper, we address the significant gap in Arabic natural language processing (NLP) resources by introducing ArabicaQA, the first large-scale dataset for machine reading comprehension and open-domain question answering in Arabic. This comprehensive dataset, consisting of 89,095 answerable and 3,701 unanswerable questions created by crowdworkers to look similar to answerable ones, along with additional labels of open-domain questions marks a crucial advancement in Arabic NLP resources. We also present AraDPR, the first dense passage retrieval model trained on the Arabic Wikipedia corpus, specifically designed to tackle the unique challenges of Arabic text retrieval. Furthermore, our study includes extensive benchmarking of large language models (LLMs) for Arabic question answering, critically evaluating their performance in the Arabic language context. In conclusion, ArabicaQA, AraDPR, and the benchmarking of LLMs in Arabic question answering offer significant advancements in the field of Arabic NLP. The dataset and code are publicly accessible for further research https://github.com/DataScienceUIBK/ArabicaQA.

For agents

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

get_harvested_code_for_paper("2403.17848")
get_code_for_paper("2403.17848")
have("2403.17848")

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

curl https://syntology.ai/api/ran/2403.17848.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.17848.svg)](https://syntology.ai/paper/2403.17848)

Connect an agent — have() is free.