SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.09892 · EMNLP · 2022

Summarizing Community-based Question-Answer Pairs

Yoshi Suhara, Xiaolan Wang, Ting-Yao Hsu, Grammarly

arXiv · PDF · Open in the Atlas

Code that ran

7 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, 1 violated it and 3 have no contract verdict; 3 failures of our instrument; 1 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/2211.09892.json · badge: /api/ran/2211.09892.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/BertSum canonical (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
all_gather_list Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nlpyang/BertSum/src/distributed.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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.

gelu Ran
ran; our contract draft was wrong, not the code
nlpyang/BertSum/src/models/neural.py
code served (permissive licence) · get_code("8d23fbe2b99b840b")
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 Tensor, 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 torch
import math

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
init_logger Ran
ran on a synthesized input
nlpyang/BertSum/src/others/logging.py
code served (permissive licence) · get_code("e317b188410c9032")
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 RootLogger. 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 logging
import tempfile
import os

def init_logger(log_file=None, log_file_level=logging.NOTSET):
    log_format = logging.Formatter('[%(asctime)s %(levelname)s] %(message)s')
    logger = logging.getLogger()
    logger.setLevel(logging.INFO)
    console_handler = logging.StreamHandler()
    console_handler.setFormatter(log_format)
    logger.handlers = [console_handler]
    if log_file and log_file != '':
        file_handler = logging.FileHandler(log_file)
        file_handler.setLevel(log_file_level)
        file_handler.setFormatter(log_format)
        logger.addHandler(file_handler)
    return logger

# Create a temporary file for logging
temp_log_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.log').name

ARGS = {
    'log_file': temp_log_file,
    'log_file_level': logging.DEBUG
}
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 RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger 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
is_master Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nlpyang/BertSum/src/distributed.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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.

simple_batch_size_fn Ran
ran on a synthesized input
nlpyang/BertSum/src/models/data_loader.py
code served (permissive licence) · get_code("ab84694a81d67283")
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)

# Analyze the function:
# - Takes 'new' and 'count' as parameters
# - 'new' is indexed with [0] and [1], so it's a tuple/list with at least 2 elements
# - new[0] is assigned to 'src', which is used with len() so it should be a sequence
# - new[1] is assigned to 'labels' (not used in the function body)
# - 'count' is an integer used in comparison and multiplication

# Create a small batch item
# src should be a sequence (list of sentences or tokens)
src = ["token1", "token2", "token3"]  # A list representing source tokens
labels = torch.tensor([1, 0])  # Labels can be a tensor

# The 'new' parameter should be a tuple/list containing (src, labels)
new = (src, labels)

# 'count' should be an integer representing the position in the batch
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
str2bool Ran
ran, violated the contract we drafted
nlpyang/BertSum/src/preprocess.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
use_gpu Ran
ran on a synthesized input
nlpyang/BertSum/src/models/optimizers.py
code served (permissive licence) · get_code("9f20e41fbfe40651")
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

# Create a simple options object with gpu_ranks attribute
class Options:
    def __init__(self, gpu_ranks=None, gpu=None):
        if gpu_ranks is not None:
            self.gpu_ranks = gpu_ranks
        if gpu is not None:
            self.gpu = gpu

# Test case 1: opt with gpu_ranks list (non-empty)
opt1 = Options(gpu_ranks=[0, 1])

# Test case 2: opt with gpu attribute > -1
opt2 = Options(gpu=0)

# Test case 3: opt with both attributes
opt3 = Options(gpu_ranks=[0], gpu=0)

# Use the first option as the main argument
ARGS = {
    'opt': opt1
}
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
build_optim Not yet run
unverified (harvested, no recorded run)
nlpyang/BertSum/src/models/optimizers.py
code served (permissive licence) · get_code("89e1b4954fded05b")
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 8 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 1 the same month, 4 later) and 0 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
56 dated earlier, 1 the same month, 24 later, 1 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
gelu 51 other papers
34 dated earlier, 15 later, 2 same year, order not determinable · 8 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 48 more not named here
all_gather_list 5 other papers
4 dated earlier, 1 later
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
aaai_16089 (2021 (year only))
Automated Lay Language Summarization of Biomedical Scientific Reviews
and 2 more not named here
is_master 5 other papers
4 dated earlier, 1 later
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.14135 (2020-04)
BERT Fine-tuning For Arabic Text Summarization
aaai_16089 (2021 (year only))
Automated Lay Language Summarization of Biomedical Scientific Reviews
and 2 more not named here
use_gpu 3 other papers
3 dated earlier
1905.13164 (2019-05)
Hierarchical Transformers for Multi-Document Summarization
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.09424 (2020-04)
Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search
build_optim 2 other papers
2 dated earlier
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.09424 (2020-04)
Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search
init_logger 2 other papers
2 dated earlier
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders
2004.09424 (2020-04)
Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search
simple_batch_size_fn 1 other paper
1 dated earlier
1908.08345 (2019-08)
Text Summarization with Pretrained Encoders

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

Community-based Question Answering (CQA), which allows users to acquire their desired information, has increasingly become an essential component of online services in various domains such as E-commerce, travel, and dining. However, an overwhelming number of CQA pairs makes it difficult for users without particular intent to find useful information spread over CQA pairs. To help users quickly digest the key information, we propose the novel CQA summarization task that aims to create a concise summary from CQA pairs. To this end, we first design a multi-stage data annotation process and create a benchmark dataset, CO-QASUM, based on the Amazon QA corpus. We then compare a collection of extractive and abstractive summarization methods and establish a strong baseline approach DedupLED for the CQA summarization task. Our experiment further confirms two key challenges, sentencetype transfer and deduplication removal, towards the CQA summarization task. Our data and code are publicly available. 1 * Work done while at Megagon Labs. 1 https://github.com/megagonlabs/ qa-summarization Q: Is this actually a rigid board or more of a floppy mat? A: It is rigid.the main board is rigid,the two sides are semi. Q: Is this actually a rigid board or more of a floppy mat? A: The main area is very sturdy. Then there are two work area pads that are more flexible so when moving those I keep two hands on them. Q: how wide is each Side piece?" A: 16 inches wide (there are two).

For agents

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

get_harvested_code_for_paper("2211.09892")
get_code_for_paper("2211.09892")
have("2211.09892")

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

curl https://syntology.ai/api/ran/2211.09892.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.09892.svg)](https://syntology.ai/paper/2211.09892)

Connect an agent — have() is free.