SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_16089 · AAAI · 2021

Automated Lay Language Summarization of Biomedical Scientific Reviews

Wei Qiu, Yizhong Wang, Trevor Cohen, Yue Guo

Open in the Atlas

Code that ran

13 of 15 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, 1 violated it and 7 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/aaai_16089.json · badge: /api/ran/aaai_16089.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
nlpyang/presumm canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
lipiji/neural-summ-cnndm-pytorch canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
abs_batch_size_fn Ran
ran on a synthesized input
nlpyang/presumm/src/models/data_loader.py
code served (permissive licence) · get_code("cb2c65cc6a650510")
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

torch.manual_seed(0)

# The function expects:
# - new: a list/tuple where new[0] is src and new[1] is tgt
# - count: an integer representing the batch count
# 
# The function uses:
# - len(tgt) to get the number of sentences in the target
# - Performs arithmetic operations on counts and sizes

# Create simple tensor data for src and tgt
# tgt needs to support len(), so it should be a list or tensor
src = torch.randn(2, 4)  # Small source tensor
tgt = [torch.randn(3, 4) for _ in range(5)]  # List of 5 target sequences (simulating sentences)

# new should be a tuple/list containing src and tgt
new = (src, tgt)

# count should be an integer representing batch position
count = 1

ARGS = {
    "new": new,
    "count": count
}
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
all_gather_list Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nlpyang/presumm/src/distributed.py
pointer only (licence: MIT); the stored copy get_code serves, from gb-kgp/MEDVOC, is pointer only (licence: NONE) · get_code("66575e439195e14f")
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 gb-kgp/MEDVOC, 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.

batched Ran
ran on a synthesized input
lipiji/neural-summ-cnndm-pytorch/data.py
code served (permissive licence) · get_code("a3ab4ea7a94f09fe")
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.

from random import shuffle

# Analyze the function:
# - x_size: int (size of data)
# - options: dict with keys 'is_predicting' (bool) and 'is_debugging' (bool)
# - consts: dict with keys 'testing_batch_size' (int) and 'batch_size' (int)

ARGS = {
    'x_size': 100,
    'options': {
        'is_predicting': False,
        'is_debugging': False,
    },
    'consts': {
        'batch_size': 32,
        'testing_batch_size': 16,
    },
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
ext_batch_size_fn Ran
ran on a synthesized input
nlpyang/presumm/src/models/data_loader.py
code served (permissive licence) · get_code("4edda4f9c7e44864")
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

torch.manual_seed(0)

# The function expects `new` to be a list/tuple with at least 5 elements
# It accesses new[0] and new[4]
# new[0] is used as `src` and len(src) is called on it, so it should be a sequence
# new[4] is used as `labels` but not actually used in the function body

# Create a sample batch item where:
# - new[0] (src) is a sequence (list of sentences or tokens)
# - new[4] (labels) can be any value since it's not used

src = [1, 2, 3, 4, 5]  # A sequence of 5 elements (representing sentences or tokens)
labels = torch.tensor([0, 1])  # Labels tensor (not used in function but accessed)

# new should be a list/tuple with at least 5 elements
new = [src, None, None, None, labels]

# count is the second parameter - an integer representing batch count
count = 1

ARGS = {
    "new": new,
    "count": count
}
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
get_data Ran
ran on a synthesized input
lipiji/neural-summ-cnndm-pytorch/data.py
code served (permissive licence) · get_code("fde03d15683ddde8")
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 BatchData. 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

# Build w2i (word to index) and i2w (index to word) mappings
w2i = {
    'hello': 0,
    'world': 1,
    'foo': 2,
    'bar': 3,
}
i2w = {v: k for k, v in w2i.items()}
i2w[999] = '<unk>'  # unknown word token

# Build modules dict
modules = {
    'w2i': w2i,
    'i2w': i2w,
    'lfw_emb': 999,  # index for unknown/low-frequency word embedding
}

# Build consts dict
consts = {
    'len_x': 10,  # max length of content
    'len_y': 5,   # max length of summary
}

# Build options dict
options = {
    'has_y': True,
    'is_predicting': False,
}

# Build flist: list of (contents, summarys) tuples
# Each content/summary is a tuple of (tokenized, original)
flist = [
    (
        (['hello', 'world', 'foo'], 'hello world foo'),
        (['hello', 'bar'], 'hello bar')
    ),
    (
        (['bar', 'foo', 'hello', 'world'], 'bar foo hello world'),
        (['world', 'foo'], 'world foo')
    ),
]

ARGS = {
    'xy_list': flist,
    'modules': modules,
    'consts': consts,
    'options': options,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BatchData — a BatchData output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchData 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
has_repeat Ran
ran; our contract draft was wrong, not the code
nlpyang/presumm/src/post_stats.py
pointer only (licence: MIT); the stored copy get_code serves, from gb-kgp/MEDVOC, is pointer only (licence: NONE) · get_code("7b7669755eae20fe")
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 gb-kgp/MEDVOC, 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.

is_master Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nlpyang/presumm/src/distributed.py
pointer only (licence: MIT); the stored copy get_code serves, from gb-kgp/MEDVOC, is pointer only (licence: NONE) · get_code("b80220994c939e73")
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 gb-kgp/MEDVOC, 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.

load_dict Ran
ran on a synthesized input
lipiji/neural-summ-cnndm-pytorch/prepare_data.py
code served (permissive licence) · get_code("f29015658c08a26b")
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 tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
temp_file = "test_dict.txt"
temp_path = os.path.join(temp_dir, temp_file)

# Write test data to the file
with open(temp_path, 'w') as f:
    f.write("apple 5\n")
    f.write("banana 3\n")
    f.write("cherry 7\n")

# Prepare arguments
d_path = temp_dir + os.sep
f_name = temp_file
dic = {}
dic_list = []

ARGS = {
    "d_path": d_path,
    "f_name": f_name,
    "dic": dic,
    "dic_list": dic_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
load_lines Ran
ran on a synthesized input
lipiji/neural-summ-cnndm-pytorch/prepare_data.py
code served (permissive licence) · get_code("55e1943957cbf258")
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
import tempfile
import os

class Config:
    def __init__(self):
        self.MIN_LEN_X = 2
        self.MAX_LEN_X = 10
        self.MIN_LEN_Y = 2
        self.MAX_LEN_Y = 8
        self.W_EOS = "<eos>"
        self.W_LS = "<summ>"
        self.W_RS = "</summ>"

config = Config()

# Create a temporary file with proper format
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_data.txt")

# Write test data in the format expected by load_lines
# Format: content<summ-content>abstract
# Where abstract contains <summ>sentence</summ> patterns
test_content = [
    "this is a test document with some words<summ-content><summ>summary one</summ><summ>summary two</summ>",
    "another document here with content<summ-content><summ>brief summary</summ>",
    "short<summ-content><summ>text</summ>",
]

with open(temp_file, 'w') as f:
    for line in test_content:
        f.write(line + '\n')

d_path = temp_dir + "/"
f_name = "test_data.txt"
configs = config

ARGS = {
    "d_path": d_path,
    "f_name": f_name,
    "configs": configs
}
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
load_model Ran
ran on a synthesized input
lipiji/neural-summ-cnndm-pytorch/utils_pg.py
code served (permissive licence) · get_code("56e39d938150e42d")
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
import tempfile
import os

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model and optimizer instances
model = SimpleModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a checkpoint and save it to a temporary file
checkpoint = {
    'model_state_dict': model.state_dict(),
    'optimizer_state_dict': optimizer.state_dict()
}

# Create a temporary file to store the checkpoint
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.pt')
temp_file_path = temp_file.name
temp_file.close()

torch.save(checkpoint, temp_file_path)

# Create fresh model and optimizer for loading
model_fresh = SimpleModel()
optimizer_fresh = torch.optim.SGD(model_fresh.parameters(), lr=0.01)

ARGS = {
    'f': temp_file_path,
    'model': model_fresh,
    'optimizer': optimizer_fresh
}
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
n_grams Ran
ran; our contract draft was wrong, not the code
nlpyang/presumm/src/post_stats.py
pointer only (licence: MIT); the stored copy get_code serves, from gb-kgp/MEDVOC, is pointer only (licence: NONE) · get_code("c3fcc4e906d8ecbd")
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 gb-kgp/MEDVOC, 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.

rouge_results_to_str Ran
ran; our contract draft was wrong, not the code
nlpyang/presumm/src/cal_rouge.py
pointer only (licence: MIT); the stored copy get_code serves, from gb-kgp/MEDVOC, is pointer only (licence: NONE) · get_code("14b39c4dc7a42e40")
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 gb-kgp/MEDVOC, 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.

str2bool Ran
ran, violated the contract we drafted
nlpyang/presumm/src/post_stats.py
code served (permissive licence) · get_code("f017532fc389cbfe")
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 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 argparse

def str2bool(v):
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# Setup code to construct valid arguments
ARGS = {
    'v': 'true'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — 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
get_xy_tuple Not yet run
unverified (harvested, no recorded run)
lipiji/neural-summ-cnndm-pytorch/prepare_data.py
code served (permissive licence) · get_code("9c4fb93467cb8acb")
How it ran

no invocation recorded.

sort_samples Not yet run
unverified (harvested, no recorded run)
lipiji/neural-summ-cnndm-pytorch/utils_pg.py
code served (permissive licence) · get_code("892f4b95b93afca1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 6 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
str2bool 82 other papers
42 dated earlier, 31 later, 9 same year, order not determinable
1510.03055 (2015-10)
A Diversity-Promoting Objective Function for Neural Conversation Models
1703.06490 (2017-03)
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks
1710.10467 (2017-10)
Generalized End-to-End Loss for Speaker Verification
and 79 more not named here
all_gather_list 5 other papers
2 dated earlier, 2 later, 1 same year, order not determinable
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
2109.04084 (2021-09)
Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
and 2 more not named here
is_master 5 other papers
2 dated earlier, 2 later, 1 same year, order not determinable
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
2109.04084 (2021-09)
Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
and 2 more not named here
rouge_results_to_str 5 other papers
4 dated earlier, 1 later
1905.13164 (2019-05)
Hierarchical Transformers for Multi-Document Summarization
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
1910.14142 (2019-10)
Discourse-Aware Neural Extractive Text Summarization
and 2 more not named here
has_repeat 3 other papers
2 dated earlier, 1 later
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
2405.04163 (2024-05)
MEDVOC: Vocabulary Adaptation for Fine-tuning Pre-trained Language Models on Medical Text Summarization
n_grams 3 other papers
2 dated earlier, 1 later
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
2405.04163 (2024-05)
MEDVOC: Vocabulary Adaptation for Fine-tuning Pre-trained Language Models on Medical Text Summarization
abs_batch_size_fn 2 other papers
2 dated earlier
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
ext_batch_size_fn 2 other papers
2 dated earlier
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization

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

Health literacy has emerged as a crucial factor in making appropriate health decisions and ensuring treatment outcomes. However, medical jargon and the complex structure of professional language in this domain make health information especially hard to interpret. Thus, there is an urgent unmet need for automated methods to enhance the accessibility of the biomedical literature to the general population. This problem can be framed as a type of translation problem between the language of healthcare professionals, and that of the general public. In this paper, we introduce the novel task of automated generation of lay language summaries of biomedical scientific reviews, and construct a dataset to support the development and evaluation of automated methods through which to enhance the accessibility of the biomedical literature. We conduct analyses of the various challenges in performing this task, including not only summarization of the key points but also explanation of background knowledge and simplification of professional language. We experiment with state-of-the-art summarization models as well as several data augmentation techniques, and evaluate their performance using both automated metrics and human assessment. Results indicate that automatically generated summaries produced using contemporary neural architectures can achieve promising quality and readability as compared with reference summaries developed for the lay public by experts (best ROUGE-L of 50.24 and Flesch-Kincaid readability score of 13.30). We also discuss the limitations of the current effort, providing insights and directions for future work.

For agents

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

get_harvested_code_for_paper("aaai_16089")
get_code_for_paper("aaai_16089")
have("aaai_16089")

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

curl https://syntology.ai/api/ran/aaai_16089.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_16089.svg)](https://syntology.ai/paper/aaai_16089)

Connect an agent — have() is free.