SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.05017 · 2019

Question Generation by Transformers

arXiv · PDF · Open in the Atlas

Code that ran

5 of 14 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 9 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/1909.05017.json · badge: /api/ran/1909.05017.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
artitw/BERT_QA community (classifier label)
classifier basis not recorded on the link
5 ran · 9 no recorded run
FunctionStatusWhere it lives
gelu Ran
ran, honoured the contract we drafted
artitw/BERT_QA/bert_qa/activations.py
code served (permissive licence) · get_code("0194c7c12ff4afda")
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 EagerTensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 math
import tensorflow as tf
import numpy as np

# Create a small test tensor for x
x = tf.constant([[-0.5, 0.0, 0.5, 1.0],
                 [2.0, -1.5, 0.25, -0.75]], dtype=tf.float32)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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_initializer Ran
ran; our contract draft was wrong, not the code
artitw/BERT_QA/bert_qa/bert_modeling.py
code served (permissive licence) · get_code("591598c6e9e9294a")
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 TruncatedNormal. 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 tensorflow as tf

# The function get_initializer takes one parameter: initializer_range
# It's a float that specifies the standard deviation for the TruncatedNormal initializer
# The function simply returns a tf.keras.initializers.TruncatedNormal with the given stddev

ARGS = {
    "initializer_range": 0.02
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TruncatedNormal — a TruncatedNormal output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TruncatedNormal 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
hard_swish Ran
ran on a synthesized input
artitw/BERT_QA/bert_qa/activations.py
code served (permissive licence) · get_code("31f5129e21532bbf")
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 EagerTensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 tensorflow as tf
import numpy as np

# Create a small tensor for testing
features = tf.constant([[-2.0, -1.0, 0.0, 1.0],
                        [2.0, 3.0, 4.0, 5.0]], dtype=tf.float32)

ARGS = {
    "features": features
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
simple_swish Ran
ran on a synthesized input
artitw/BERT_QA/bert_qa/activations.py
code served (permissive licence) · get_code("91f68cb072b261f2")
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 EagerTensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 tensorflow as tf
import numpy as np

# Create a small tensor to pass to simple_swish
# The function expects a Tensor-like object
features_input = tf.constant([[1.0, 2.0, 3.0, 4.0],
                               [-1.0, -2.0, 0.5, 1.5]], dtype=tf.float32)

ARGS = {
    "features": features_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
steps_to_run Ran
ran on a synthesized input
artitw/BERT_QA/bert_qa/model_training_utils.py
code served (permissive licence) · get_code("c509d695494f63fb")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Analyze the function:
# - current_step: an integer representing the current step number
# - steps_per_epoch: an integer representing steps per epoch
# - steps_per_loop: an integer representing steps per loop
# The function performs arithmetic operations on these integers.

ARGS = {
    'current_step': 5,
    'steps_per_epoch': 10,
    'steps_per_loop': 3
}
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 int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
convert_single_example Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/classifier_data_lib.py
code served (permissive licence) · get_code("7346ad7b1d174de0")
How it ran

no invocation recorded.

create_attention_mask_from_input_mask Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/bert_modeling.py
code served (permissive licence) · get_code("37b7e327abf6ebe3")
How it ran

no invocation recorded.

file_based_convert_examples_to_features Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/classifier_data_lib.py
code served (permissive licence) · get_code("342ecb2772b332ff")
How it ran

no invocation recorded.

gather_indexes Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/bert_models.py
code served (permissive licence) · get_code("8148682084ad8025")
How it ran

no invocation recorded.

generate_tf_record_from_data_file Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/classifier_data_lib.py
code served (permissive licence) · get_code("0d0191d0adf31881")
How it ran

no invocation recorded.

get_bert_model Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/bert_modeling.py
code served (permissive licence) · get_code("7cb07bdfa1f42eeb")
How it ran

no invocation recorded.

get_transformer_encoder Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/bert_models.py
code served (permissive licence) · get_code("0ef881d517628d47")
How it ran

no invocation recorded.

pretrain_model Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/bert_models.py
code served (permissive licence) · get_code("fc44a0dfc06deb6b")
How it ran

no invocation recorded.

run_customized_training_loop Not yet run
unverified (harvested, no recorded run)
artitw/BERT_QA/bert_qa/model_training_utils.py
code served (permissive licence) · get_code("8cffcf8ba6ef99cc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 2 the same month, 3 later) and 10 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
get_initializer 6 other papers
1 dated earlier, 1 the same month, 4 later · 1 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
1910.01108 (2019-10)
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
and 3 more not named here
gelu 2 other papers
2 later
2004.02349 (2020-04)
TAPAS: Weakly Supervised Table Parsing via Pre-training
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
create_attention_mask_from_input_mask 1 other paper
1 the same month
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
steps_to_run 1 other paper
1 later
2005.07503 (2020-05)
COVID-Twitter-BERT: A Natural Language Processing Model to Analyse COVID-19 Content on Twitter

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

A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers, an attention-based model eschewing the paradigm of existing recurrent neural networks (RNNs). The model was trained on the inverted Stanford Question Answering Dataset (SQuAD), which is a reading comprehension dataset consisting of 100,000+ questions posed by crowdworkers on a set of Wikipedia articles. After training, the question generation model is able to generate simple questions relevant to unseen passages and answers containing an average of 8 words per question. The word error rate (WER) was used as a metric to compare the similarity between SQuAD questions and the model-generated questions. Although the high average WER suggests that the questions generated differ from the original SQuAD questions, the questions generated are mostly grammatically correct and plausible in their own right.

For agents

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

get_harvested_code_for_paper("1909.05017")
get_code_for_paper("1909.05017")
have("1909.05017")

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

curl https://syntology.ai/api/ran/1909.05017.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.05017.svg)](https://syntology.ai/paper/1909.05017)

Connect an agent — have() is free.