SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.01107 · 2020

Simplifying Paragraph-level Question Generation via Transformer Language Models

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, 0 violated it and 5 have no contract verdict; 1 failure 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/2005.01107.json · badge: /api/ran/2005.01107.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
AndreasInk/Quiz-APIv2 community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
liamdugan/question_generation community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
filter_e2e_qg Ran
ran on a synthesized input
AndreasInk/Quiz-APIv2/prepare_data.py
code served (permissive licence) · get_code("adf103ca18b5fd78")
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 bool, ndim 0, dtype family float, 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
import numpy as np

def filter_e2e_qg(example):
    return example['task'] == 'e2e_qg'

# Construct a valid example dict that will be passed to filter_e2e_qg
example = {
    'task': 'e2e_qg',
    'data': torch.randn(2, 4),
    'other_field': 'some_value'
}

ARGS = {
    'example': example
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, 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
filter_qa Ran
ran on a synthesized input
AndreasInk/Quiz-APIv2/prepare_data.py
code served (permissive licence) · get_code("4643e380618fe0c5")
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 bool, ndim 0, dtype family float, 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
import torch.nn as nn

torch.manual_seed(0)

# The function filter_qa takes one parameter: example
# It checks if example['task'] == 'qa'
# So example needs to be a dict with a 'task' key

example = {
    'task': 'qa',
    'text': 'What is the capital of France?',
    'answer': 'Paris'
}

ARGS = {
    'example': example
}
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 bool, ndim 0, dtype family float, 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
filter_qg Ran
ran on a synthesized input
AndreasInk/Quiz-APIv2/prepare_data.py
code served (permissive licence) · get_code("7ab6ed8c2d373657")
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 bool, ndim 0, dtype family float, 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)

example = {
    'task': 'qg'
}

ARGS = {
    'example': example
}
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 bool, ndim 0, dtype family float, 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
grad_status Ran
ran on a synthesized input
AndreasInk/Quiz-APIv2/utils.py
code served (permissive licence) · get_code("3e6b2aa920dd0f89")
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 generator. 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 torch import nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
model = SimpleModel()

ARGS = {
    "model": model
}
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 generator — a generator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a generator 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
label_smoothed_nll_loss Ran
ran on a synthesized input
AndreasInk/Quiz-APIv2/utils.py
code served (permissive licence) · get_code("2e8522233e82d5b1")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch.nn as nn

torch.manual_seed(0)

# Build tiny tensors for the function
batch_size = 2
vocab_size = 4
seq_len = 3

# lprobs: log probabilities, shape (batch_size, seq_len, vocab_size)
# These should be log softmax outputs
lprobs = torch.log_softmax(torch.randn(batch_size, seq_len, vocab_size), dim=-1)

# target: token indices, shape (batch_size, seq_len)
# Values should be in range [0, vocab_size) or ignore_index
target = torch.randint(0, vocab_size, (batch_size, seq_len))

# epsilon: label smoothing parameter (typically 0.1)
epsilon = 0.1

# ignore_index: padding index (default -100, but we use it to mask certain positions)
ignore_index = -100

ARGS = {
    "lprobs": lprobs,
    "target": target,
    "epsilon": epsilon,
    "ignore_index": ignore_index,
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
trim_batch Ran
ran; our contract draft was wrong, not the code
AndreasInk/Quiz-APIv2/data_collator.py
pointer only (licence: MIT); the stored copy get_code serves, from Sahandfer/CEM, is pointer only (licence: NONE) · get_code("eeb8dc60c6ef1fa4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Sahandfer/CEM, and GitHub detected no licence in that repository 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.

pipeline Not yet run
unverified (harvested, no recorded run)
AndreasInk/Quiz-APIv2/pipelines.py
code served (permissive licence) · get_code("9bdd29f2eb570b1d")
How it ran

no invocation recorded.

pipeline Not yet run
unverified (harvested, no recorded run)
liamdugan/question_generation/pipelines.py
code served (permissive licence) · get_code("0b723c5ee79bdf83")
How it ran

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 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
trim_batch 9 other papers
9 later
2104.08661 (2021-04)
Explaining Answers with Entailment Trees
2108.02866 (2021-08)
Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering
2204.06239 (2022-04)
Can Question Rewriting Help Conversational Question Answering?
and 6 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

Question generation (QG) is a natural language generation task where a model is trained to ask questions corresponding to some input text. Most recent approaches frame QG as a sequence-to-sequence problem and rely on additional features and mechanisms to increase performance; however, these often increase model complexity, and can rely on auxiliary data unavailable in practical use. A single Transformer-based unidirectional language model leveraging transfer learning can be used to produce high quality questions while disposing of additional task-specific complexity. Our QG model, finetuned from GPT-2 Small, outperforms several paragraph-level QG baselines on the SQuAD dataset by 0.95 METEOR points. Human evaluators rated questions as easy to answer, relevant to their context paragraph, and corresponding well to natural human speech. Also introduced is a new set of baseline scores on the RACE dataset, which has not previously been used for QG tasks. Further experimentation with varying model capacities and datasets with non-identification type questions is recommended in order to further verify the robustness of pretrained Transformer-based LMs as question generators.

For agents

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

get_harvested_code_for_paper("2005.01107")
get_code_for_paper("2005.01107")
have("2005.01107")

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

curl https://syntology.ai/api/ran/2005.01107.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.01107.svg)](https://syntology.ai/paper/2005.01107)

Connect an agent — have() is free.