SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.05897 · 2021

Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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 7 have no contract verdict; 2 failures of our instrument; 0 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/2109.05897.json · badge: /api/ran/2109.05897.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
abhi1nandy2/emnlp-2021-findings canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
FunctionStatusWhere it lives
flat_accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhi1nandy2/emnlp-2021-findings/fine_tuning_variants_scripts/AR_sentence_wise.py
code served (permissive licence) · get_code("f3e68336634b8642")
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 float64, 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 numpy as np

# flat_accuracy expects:
# - preds: array-like with shape (batch_size, num_classes) - will call np.argmax(axis=1)
# - labels: array-like with shape (batch_size,) - will be flattened

# Create small sample data
batch_size = 2
num_classes = 4

# preds: shape (2, 4) - logits/probabilities for 2 samples, 4 classes
preds = np.array([
    [0.1, 0.9, 0.05, 0.05],  # sample 0, argmax=1
    [0.2, 0.3, 0.4, 0.1]      # sample 1, argmax=2
])

# labels: shape (2,) - ground truth class indices
labels = np.array([1, 2])

ARGS = {
    "preds": preds,
    "labels": labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
float_to_str Ran
ran on a synthesized input
abhi1nandy2/emnlp-2021-findings/MTL_scripts/MTL_utils.py
code served (permissive licence) · get_code("162aed4b47317010")
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)

# The function float_to_str takes a single parameter 'num' and converts it to a float,
# then formats it as a string with 3 decimal places.
# We need to provide a numeric value that can be converted to float.

ARGS = {
    'num': 3.14159
}
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
format_time Ran
ran; our contract draft was wrong, not the code
abhi1nandy2/emnlp-2021-findings/fine_tuning_variants_scripts/AR_sentence_wise.py
code served (permissive licence) · get_code("e85f0cabb89be852")
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 datetime

def format_time(elapsed):
    """
    Takes a time in seconds and returns a string hh:mm:ss
    """
    elapsed_rounded = int(round(elapsed))
    return str(datetime.timedelta(seconds=elapsed_rounded))

ARGS = {
    "elapsed": 3661.5
}
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 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_em Ran
ran on a synthesized input
abhi1nandy2/emnlp-2021-findings/evaluation/metrics.py
code served (permissive licence) · get_code("508a22212da25b22")
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 float, 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

torch.manual_seed(0)

# Analyze the function:
# - all_hypothesis: needs to be indexable (len works) and each element needs .lower() method
# - all_references: needs to be indexable (len works) and each element needs .lower() method
# - The function compares strings element-wise
# - Returns a float (exact matches / total)

# Create lists of strings for testing
all_hypothesis = [
    "Hello World",
    "EXACT MATCH",
    "Different",
    "test string"
]

all_references = [
    "hello world",
    "exact match",
    "Different",
    "TEST STRING"
]

ARGS = {
    "all_hypothesis": all_hypothesis,
    "all_references": all_references
}
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 float, 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_sent_embedding Ran
ran on a synthesized input
abhi1nandy2/emnlp-2021-findings/evaluation/smd.py
code served (permissive licence) · get_code("763a8b233c0c46c1")
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 numpy as np

# Construct arguments for get_sent_embedding
# The function takes emb_list and converts it to a numpy array,
# then computes the mean across axis 0

# Create a small list of embeddings (e.g., 3 embeddings of dimension 4)
emb_list = [
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0],
    [9.0, 10.0, 11.0, 12.0]
]

ARGS = {
    "emb_list": emb_list
}
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 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
match_path_with_section Ran
ran on a synthesized input
abhi1nandy2/emnlp-2021-findings/MTL_scripts/MTL_utils.py
code served (permissive licence) · get_code("1eafbd36660bf39d")
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.

# Construct valid arguments for match_path_with_section

# Analyze the function:
# - q_section_path: a string with path separators ('>'), hyphens, question marks
# - corpus_dict: a dictionary where:
#   - keys are section identifiers
#   - values are dicts with keys: 'title', 'section_hierarchy', 'id'
#   - section_hierarchy is a string with '>' separator containing keys to corpus_dict

# Build a minimal corpus_dict structure
corpus_dict = {
    'sec_1': {
        'id': 'id_1',
        'title': 'Introduction',
        'section_hierarchy': 'sec_1'
    },
    'sec_2': {
        'id': 'id_2',
        'title': 'Basics',
        'section_hierarchy': 'sec_1>sec_2'
    },
    'sec_3': {
        'id': 'id_3',
        'title': 'Advanced Topics',
        'section_hierarchy': 'sec_1>sec_2>sec_3'
    },
    'sec_4': {
        'id': 'id_4',
        'title': 'Examples',
        'section_hierarchy': 'sec_1>sec_2>sec_4'
    }
}

# Create a query section path that should match
# The function looks for: section_name == iter_sec_content['title']
# and iter_sec_path[0:3] == q_section_path[0:3]
# q_section_path after processing becomes: ['Introduction', 'Basics', 'Advanced Topics']
q_section_path = 'Introduction > Basics > Advanced Topics'

ARGS = {
    'q_section_path': q_section_path,
    'corpus_dict': corpus_dict
}
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 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
prepare_results Ran
ran on a synthesized input
abhi1nandy2/emnlp-2021-findings/evaluation/metrics.py
code served (permissive licence) · get_code("6ee94dbbff2bd284")
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)

# The function prepare_results takes:
# - metric: a string label for the metric
# - p: precision value (float between 0 and 1)
# - r: recall value (float between 0 and 1)
# - f: f1 score value (float between 0 and 1)

ARGS = {
    'metric': 'accuracy',
    'p': 0.85,
    'r': 0.90,
    'f': 0.87
}
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
rem_sp Ran
ran on a synthesized input
abhi1nandy2/emnlp-2021-findings/EManual_data_extraction/extract_sections_from_html.py
code served (permissive licence) · get_code("7a617f732b781628")
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
import numpy as np

def rem_sp(text):
    """
    remove spaces and unicode escape chars
    """
    text = ' '.join(text.split())
    return text.encode('ascii', 'ignore').decode('unicode_escape')

# The function takes a single parameter 'text' which should be a string
# It removes extra spaces and unicode escape characters
ARGS = {
    'text': 'hello  world  \n  with   spaces'
}
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 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
remove_punct Ran
ran on a synthesized input
abhi1nandy2/emnlp-2021-findings/MTL_scripts/MTL_utils.py
code served (permissive licence) · get_code("27323a5a9bc199e9")
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 string

def remove_punct(s):
    s = s.replace(' :', ':').replace(' .', '.').replace(' .', '.').replace(''', '').replace("'", '').replace('Wi‑Fi', 'WiFi').split()
    s = [i for i in s if i != ' ']
    s = ' '.join(s)
    s = '. '.join(s.split('.'))
    s = ', '.join(s.split(','))
    temp_sent = s.replace(' :', ':').replace(' ,', ',').replace(' .', '.').replace(' .', '.').replace(''', '').replace("'", '').replace('Wi‑Fi', 'WiFi').split()
    temp_sent = [i for i in temp_sent if i != ' ']
    s = ' '.join(temp_sent)
    s = s.translate(str.maketrans('', '', string.punctuation))
    return s

ARGS = {
    's': "Hello world, this is a test. Wi‑Fi connection available: yes."
}
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 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

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 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
flat_accuracy 4 other papers
2 dated earlier, 2 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2002.10361 (2020-02)
Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition
2405.06459 (2024-05)
Are EEG-to-Text Models Working?
and 1 more not named here
format_time 4 other papers
4 later
2022.findings-naacl.188 (2022 (year only))
RCL: Relation Contrastive Learning for Zero-Shot Relation Extraction
2301.11796 (2023-01)
Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus
2402.11235 (2024-02)
ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs
and 1 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

Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. This can be primarily attributed to the absence of standard benchmark datasets. In this paper we meticulously create a large amount of data connected with E-manuals and develop suitable algorithm to exploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals and pretrain RoBERTa on this large corpus. We create various benchmark QA datasets which include question answer pairs curated by experts based upon two E-manuals, real user questions from Community Question Answering Forum pertaining to E-manuals etc. We introduce EMQAP (E-Manual Question Answering Pipeline) that answers questions pertaining to electronics devices. Built upon the pretrained RoBERTa, it harbors a supervised multi-task learning framework which efficiently performs the dual tasks of identifying the section in the E-manual where the answer can be found and the exact answer span within that section. For E-Manual annotated question-answer pairs, we show an improvement of about 40% in ROUGE-L F1 scores over the most competitive baseline. We perform a detailed ablation study and establish the versatility of EMQAP across different circumstances. The code and datasets are shared at https://github.com/abhi1nandy2/EMNLP-2021-Findings, and the corresponding project website is https://sites.google.com/view/emanualqa/home.

For agents

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

get_harvested_code_for_paper("2109.05897")
get_code_for_paper("2109.05897")
have("2109.05897")

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

curl https://syntology.ai/api/ran/2109.05897.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.05897.svg)](https://syntology.ai/paper/2109.05897)

Connect an agent — have() is free.