SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.05574 · EACL Findings · 2023

NapSS: Paragraph-level Medical Text Simplification via Narrative Prompting and Sentence-matching Summarization

Jiazheng Li, Yulan He, Byron Wallace, Junru Lu, Gabriele Pergola

arXiv · PDF · Open in the Atlas

Code that ran

17 of 24 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; 2 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 8 failures of our instrument; 7 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/2302.05574.json · badge: /api/ran/2302.05574.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
LuJunru/NapSS canonical (classifier label)
classifier basis not recorded on the link
10 ran · 4 no recorded run
google-research/bert canonical (classifier label)
classifier basis not recorded on the link
7 ran · 3 no recorded run
FunctionStatusWhere it lives
abs_length Ran
ran on a synthesized input
LuJunru/NapSS/prepare_data/process.py
code served (permissive licence) · get_code("6e4e375353d94915")
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)

# Construct a valid article dict with abstract containing text entries
article = {
    'abstract': [
        {'text': 'This is the first abstract sentence.'},
        {'text': 'This is the second one.'},
        {'text': 'And a third.'}
    ]
}

ARGS = {
    'article': article
}
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_to_unicode Ran
ran; our contract draft was wrong, not the code
google-research/bert/tokenization.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from huawei-noah/Pretrained-Language-Model, is pointer only (licence: NONE) · get_code("1923fc05163d207d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from huawei-noah/Pretrained-Language-Model, 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.

count_trainable_parameters Ran
ran, honoured the contract we drafted
LuJunru/NapSS/modeling/callbacks.py
pointer only (licence: MIT); the stored copy get_code serves, from manga-uofa/fdistill, is pointer only (licence: NONE) · get_code("a3826392847cbef3")
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 manga-uofa/fdistill, 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.

create_float_feature Ran
ran; our contract draft was wrong, not the code
google-research/bert/create_pretraining_data.py
code served (permissive licence) · get_code("b24b3b9c700da839")
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 Feature. 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
import numpy as np

def create_float_feature(values):
    feature = tf.train.Feature(float_list=tf.train.FloatList(value=list(values)))
    return feature

# The function takes 'values' parameter and converts it to a list, then creates a FloatList
# We need to provide an iterable of numeric values

values = [1.0, 2.5, 3.7, 4.2]

ARGS = {
    "values": values
}
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 Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
create_int_feature Ran
ran; our contract draft was wrong, not the code
google-research/bert/create_pretraining_data.py
code served (permissive licence) · get_code("dd3ef48a15aec0cd")
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 Feature. 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 create_int_feature takes 'values' as a parameter
# It converts values to a list and passes it to tf.train.Int64List
# So values should be an iterable of integers

ARGS = {
    "values": [1, 2, 3, 4, 5]
}
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 Feature — a Feature output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Feature 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
create_weight_vector Ran
ran on a synthesized input
LuJunru/NapSS/modeling/finetune.py
code served (permissive licence) · get_code("f4d3f88ead3ef8e6")
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 2, 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 tempfile
import os

torch.manual_seed(0)

# Create a temporary file with weight data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("0 -0.5\n")
temp_file.write("1 -0.3\n")
temp_file.write("2 0.2\n")
temp_file.write("3 -0.8\n")
temp_file.write("4 -0.1\n")
temp_file.close()

# Create a mock model with the required attributes
class MockModel:
    def __init__(self):
        self.unlikelihood_exclude_tokens = {2}  # Exclude token 2
        self.unlikelihood_num_weights = 3  # Keep only 3 weights

model = MockModel()

ARGS = {
    "fname": temp_file.name,
    "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 tuple, ndim 2, 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
gelu Ran
ran, honoured the contract we drafted
google-research/bert/modeling.py
code served (permissive licence) · get_code("d08f324f950148de")
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) 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 numpy as np
import tensorflow as tf

# Create a small TensorFlow tensor for testing
x = tf.constant([[-0.5, 0.0, 0.5, 1.0], [0.2, -0.3, 0.8, -0.1]], dtype=tf.float32)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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_abstract Ran
ran on a synthesized input
LuJunru/NapSS/modeling/train_logr_cochrane.py
code served (permissive licence) · get_code("63e60d2c27206a83")
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 str. 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

torch.manual_seed(0)

article = {
    'abstract': [
        {'text': 'This'},
        {'text': 'is'},
        {'text': 'an'},
        {'text': 'abstract'}
    ]
}

ARGS = {
    'article': article
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_activation Ran
ran; our contract draft was wrong, not the code
google-research/bert/modeling.py
code served (permissive licence) · get_code("5842ee67106321d6")
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) and returned function. 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 numpy as np
import six
import tensorflow as tf

def gelu(x):
    """Gaussian Error Linear Unit.

  This is a smoother version of the RELU.
  Original paper: https://arxiv.org/abs/1606.08415
  Args:
    x: float Tensor to perform activation.

  Returns:
    `x` with the GELU activation applied.
  """
    cdf = 0.5 * (1.0 + tf.tanh(np.sqrt(2 / np.pi) * (x + 0.044715 * tf.pow(x, 3))))
    return x * cdf

def get_activation(activation_string):
    """Maps a string to a Python function, e.g., "relu" => `tf.nn.relu`.

  Args:
    activation_string: String name of the activation function.

  Returns:
    A Python function corresponding to the activation function. If
    `activation_string` is None, empty, or "linear", this will return None.
    If `activation_string` is not a string, it will return `activation_string`.

  Raises:
    ValueError: The `activation_string` does not correspond to a known
      activation.
  """
    if not isinstance(activation_string, six.string_types):
        return activation_string
    if not activation_string:
        return None
    act = activation_string.lower()
    if act == 'linear':
        return None
    elif act == 'relu':
        return tf.nn.relu
    elif act == 'gelu':
        return gelu
    elif act == 'tanh':
        return tf.tanh
    else:
        raise ValueError('Unsupported activation: %s' % act)


ARGS = {
    'activation_string': 'relu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, six, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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_early_stopping_callback Ran
ran; our contract draft was wrong, not the code
LuJunru/NapSS/modeling/callbacks.py
pointer only (licence: MIT); the stored copy get_code serves, from manga-uofa/fdistill, is pointer only (licence: NONE) · get_code("295d9fdc5ce0b054")
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 manga-uofa/fdistill, 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.

get_pls Ran
ran on a synthesized input
LuJunru/NapSS/modeling/train_logr_cochrane.py
code served (permissive licence) · get_code("4a073f12f4c9fbed")
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 list, 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

torch.manual_seed(0)

# Case 1: article with pls_type == 'long', where pls is a list
article_long = {
    'pls_type': 'long',
    'pls': ['plain language summary text here']
}

# Case 2: article with pls_type != 'long', where pls is a list of dicts with 'text' keys
article_short = {
    'pls_type': 'short',
    'pls': [
        {'text': 'first part'},
        {'text': 'second part'},
        {'text': 'third part'}
    ]
}

ARGS = {
    'article': article_long
}
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 list, ndim 1, dtype family float — a list 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
input_fn_builder Ran
ran on a synthesized input
google-research/bert/extract_features.py
code served (permissive licence) · get_code("47a3c792cebb6603")
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 function. 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

class Feature:
    def __init__(self, unique_id, input_ids, input_mask, input_type_ids):
        self.unique_id = unique_id
        self.input_ids = input_ids
        self.input_mask = input_mask
        self.input_type_ids = input_type_ids

seq_length = 4
num_examples = 2

features = [
    Feature(
        unique_id=0,
        input_ids=[101, 2054, 2003, 102],
        input_mask=[1, 1, 1, 1],
        input_type_ids=[0, 0, 0, 0]
    ),
    Feature(
        unique_id=1,
        input_ids=[101, 1045, 2572, 102],
        input_mask=[1, 1, 1, 1],
        input_type_ids=[0, 0, 0, 0]
    )
]

ARGS = {
    'features': features,
    'seq_length': seq_length
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
LuJunru/NapSS/modeling/utils.py
code served (permissive licence) · get_code("e386d3a24af4d168")
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

torch.manual_seed(0)

# Create log probabilities tensor
# Shape: (batch_size=2, vocab_size=4)
# lprobs should be log probabilities, so values between -inf and 0
lprobs = torch.log(torch.softmax(torch.randn(2, 4), dim=-1))

# Create target indices tensor
# Shape: (batch_size=2,) - indices into the vocabulary
# Values should be in range [0, vocab_size) or ignore_index
target = torch.tensor([1, 2], dtype=torch.long)

# Epsilon for label smoothing (typically small, e.g., 0.1)
epsilon = 0.1

# Ignore index for padding tokens
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
lmap Ran
ran; our contract draft was wrong, not the code
LuJunru/NapSS/modeling/utils.py
code served (permissive licence) · get_code("7c43af131a6f39a6")
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 list, ndim 1, dtype family int; 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 numpy as np
from typing import Callable, List, Iterable

torch.manual_seed(0)

# Define a simple callable function
def square(x):
    """Simple function that squares its input"""
    return x ** 2

# Define an iterable (list of numbers)
numbers = [1, 2, 3, 4, 5]

# Construct ARGS dict
ARGS = {
    "f": square,
    "x": numbers,
}
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 list, ndim 1, dtype family int — a list 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
pls_length Ran
ran on a synthesized input
LuJunru/NapSS/prepare_data/process.py
code served (permissive licence) · get_code("de410425f99f8d57")
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
import numpy as np

# Based on the function pls_length, we need to provide an 'article' dictionary
# The function checks article['pls_type'] and then accesses article['pls']
# If pls_type is 'long', pls is a list and we call len() on it
# If pls_type is not 'long', pls is a list of dicts with 'text' key, and we sum the lengths

# Case 1: pls_type == 'long'
article_long = {
    'pls_type': 'long',
    'pls': ['item1', 'item2', 'item3']
}

# Case 2: pls_type != 'long' (e.g., 'short')
article_short = {
    'pls_type': 'short',
    'pls': [
        {'text': 'hello world'},
        {'text': 'foo bar baz'},
        {'text': 'x'}
    ]
}

# Using the 'long' case for the ARGS
ARGS = {
    'article': article_long
}
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 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
printable_text Ran
ran; our contract draft was wrong, not the code
google-research/bert/tokenization.py
code served (permissive licence) · get_code("0e5615f8994003cf")
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 str. 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 six

# The function takes a single parameter 'text' which can be:
# - str (works in both Python 2 and 3)
# - bytes (in Python 3, decoded to utf-8)
# - unicode (in Python 2, encoded to utf-8)

# Since we're running on Python 3, we'll test with a string
text_input = "Hello, World!"

ARGS = {
    "text": text_input
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
six — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
shift_tokens_right Ran
ran; our contract draft was wrong, not the code
LuJunru/NapSS/modeling/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from yeliu918/KG-BART, is pointer only (licence: NONE) · get_code("e00ccf7847d12b59")
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 yeliu918/KG-BART, 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.

add_newline_to_end_of_each_sentence Not yet run
unverified (harvested, no recorded run)
LuJunru/NapSS/modeling/sentence_splitter.py
code served (permissive licence) · get_code("c66ab1dac5e4762c")
How it ran

no invocation recorded.

file_based_input_fn_builder Not yet run
unverified (harvested, no recorded run)
google-research/bert/run_classifier.py
code served (permissive licence) · get_code("1b46c9ce24fc6db3")
How it ran

no invocation recorded.

get_assignment_map_from_checkpoint Not yet run
unverified (harvested, no recorded run)
google-research/bert/modeling.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from toggle1995/RIS-DMMI, is pointer only (licence: NONE) · get_code("50958618b65e514e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from toggle1995/RIS-DMMI, 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. No invocation recorded.

get_checkpoint_callback Not yet run
unverified (harvested, no recorded run)
LuJunru/NapSS/modeling/callbacks.py
code served (permissive licence) · get_code("01cc9caede179564")
How it ran

no invocation recorded.

get_doi Not yet run
unverified (harvested, no recorded run)
LuJunru/NapSS/prepare_data/scrape.py
code served (permissive licence) · get_code("4b39339b1136b5aa")
How it ran

no invocation recorded.

load_vocab Not yet run
unverified (harvested, no recorded run)
google-research/bert/tokenization.py
code served (permissive licence) · get_code("ff83ccc8b0b6462d")
How it ran

no invocation recorded.

res_para Not yet run
unverified (harvested, no recorded run)
LuJunru/NapSS/prepare_data/process.py
code served (permissive licence) · get_code("0dc1d3e997580e88")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 17 are also present in other papers whose code we hold (17 with at least one paper dated earlier, 1 the same month, 12 later) and 7 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
convert_to_unicode 36 other papers
26 dated earlier, 10 later
1609.08144 (2016-09)
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.04085 (2019-01)
Passage Re-ranking with BERT
and 33 more not named here
printable_text 33 other papers
25 dated earlier, 8 later
1609.08144 (2016-09)
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.04085 (2019-01)
Passage Re-ranking with BERT
and 30 more not named here
get_activation 32 other papers
27 dated earlier, 3 later, 2 same year, order not determinable · 1 only as an assembly brick
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.04085 (2019-01)
Passage Re-ranking with BERT
and 29 more not named here
gelu 26 other papers
21 dated earlier, 3 later, 2 same year, order not determinable · 4 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
and 23 more not named here
get_assignment_map_from_checkpoint 26 other papers
23 dated earlier, 3 later
1804.05392 (2018-04)
Higher-order Coreference Resolution with Coarse-to-fine Inference
1808.09781 (2018-08)
Self-Attentive Sequential Recommendation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 23 more not named here
load_vocab 16 other papers
15 dated earlier, 1 later
1609.08144 (2016-09)
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.08746 (2019-01)
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
and 13 more not named here
count_trainable_parameters 13 other papers
8 dated earlier, 4 later, 1 same year, order not determinable
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2010.05953 (2020-10)
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
and 10 more not named here
create_int_feature 13 other papers
11 dated earlier, 2 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.05474 (2019-06)
Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets
1908.08962 (2019-08)
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
and 10 more not named here
shift_tokens_right 11 other papers
9 dated earlier, 1 the same month, 1 same year, order not determinable
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2009.12005 (2020-09)
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
2009.12677 (2020-09)
KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning
and 8 more not named here
create_float_feature 9 other papers
8 dated earlier, 1 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1908.08962 (2019-08)
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
1909.06356 (2019-09)
Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering
and 6 more not named here
get_early_stopping_callback 9 other papers
5 dated earlier, 3 later, 1 same year, order not determinable
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2010.11856 (2020-10)
XOR QA: Cross-lingual Open-Retrieval Question Answering
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
and 6 more not named here
lmap 9 other papers
9 dated earlier
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
and 6 more not named here
file_based_input_fn_builder 7 other papers
6 dated earlier, 1 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1905.09217 (2019-05)
Deeper Text Understanding for IR with Contextual Neural Language Modeling
1906.09317 (2019-06)
Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction
and 4 more not named here
label_smoothed_nll_loss 7 other papers
7 dated earlier
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
and 4 more not named here
input_fn_builder 6 other papers
5 dated earlier, 1 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1908.08962 (2019-08)
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
1909.06356 (2019-09)
Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering
and 3 more not named here
add_newline_to_end_of_each_sentence 1 other paper
1 dated earlier
2105.11174 (2021-05)
Retrieval Enhanced Model for Commonsense Generation
get_checkpoint_callback 1 other paper
1 dated earlier
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation

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

Accessing medical literature is difficult for laypeople as the content is written for specialists and contains medical jargon. Automated text simplification methods offer a potential means to address this issue. In this work, we propose a summarize-then-simplify two-stage strategy, which we call NapSS, identifying the relevant content to simplify while ensuring that the original narrative flow is preserved. In this approach, we first generate reference summaries via sentence matching between the original and the simplified abstracts. These summaries are then used to train an extractive summarizer, learning the most relevant content to be simplified. Then, to ensure the narrative consistency of the simplified text, we synthesize auxiliary narrative prompts combining key phrases derived from the syntactical analyses of the original text. Our model achieves results significantly better than the seq2seq baseline on an English medical corpus, yielding 3%∼4% absolute improvements in terms of lexical similarity, and providing a further 1.1% improvement of SARI score when combined with the baseline. We also highlight shortcomings of existing evaluation methods, and introduce new metrics that take into account both lexical and high-level semantic similarity. A human evaluation conducted on a random sample of the test set further establishes the effectiveness of the proposed approach. Codes and models are released here: https://github.com/LuJunru/NapSS.

For agents

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

get_harvested_code_for_paper("2302.05574")
get_code_for_paper("2302.05574")
have("2302.05574")

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

curl https://syntology.ai/api/ran/2302.05574.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.05574.svg)](https://syntology.ai/paper/2302.05574)

Connect an agent — have() is free.