SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.16495 · EMNLP · 2022

Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering

Navonil Majumder, Poria Declare, Deepanway Declare, Declare Rada, Mihalcea Soujanya

arXiv · PDF · Open in the Atlas

Code that ran

2 of 7 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 1 has no contract verdict; 1 failure of our instrument; 5 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/2210.16495.json · badge: /api/ran/2210.16495.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
declare-lab/TEAM canonical (classifier label)
classifier basis not recorded on the link
2 ran · 5 no recorded run
FunctionStatusWhere it lives
configure_dataloaders Ran
ran on a synthesized input
declare-lab/TEAM/train_csqa2.py
code served (permissive licence) · get_code("ffc49c4218a2e155")
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 json
import random
import pandas as pd
import tempfile
import os
from torch.utils.data import Dataset, DataLoader

# Create temporary directory and mock data files
temp_dir = tempfile.mkdtemp()
os.makedirs(os.path.join(temp_dir, 'data', 'csqa2'), exist_ok=True)

# Create mock CSQA2 dataset files
train_file = os.path.join(temp_dir, 'data', 'csqa2', 'CSQA2_train.json')
dev_file = os.path.join(temp_dir, 'data', 'csqa2', 'CSQA2_dev.json')
test_file = os.path.join(temp_dir, 'data', 'csqa2', 'CSQA2_test.json')

# Write mock training data
with open(train_file, 'w') as f:
    f.write(json.dumps({'question': 'Is the sky blue?', 'answer': 'yes'}) + '\n')
    f.write(json.dumps({'question': 'Can dogs fly?', 'answer': 'no'}) + '\n')

# Write mock dev data
with open(dev_file, 'w') as f:
    f.write(json.dumps({'question': 'Do humans need water?', 'answer': 'yes'}) + '\n')
    f.write(json.dumps({'question': 'Is fire cold?', 'answer': 'no'}) + '\n')

# Write mock test data
with open(test_file, 'w') as f:
    f.write(json.dumps({'question': 'Is grass green?'}) + '\n')
    f.write(json.dumps({'question': 'Do fish swim in air?'}) + '\n')

# Change to temp directory so relative paths work
os.chdir(temp_dir)

ARGS = {
    'sep_token': '[SEP]',
    'train_batch_size': 2,
    'eval_batch_size': 2,
    'shuffle': False,
    'input_format': '0'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas, 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
configure_optimizer Ran
ran; our contract draft was wrong, not the code
declare-lab/TEAM/train_cicero.py
code served (permissive licence) · get_code("4dab6811065fbe1c")
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 AdamW. 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 torch.nn as nn
from torch.optim import AdamW

torch.manual_seed(0)

# Create a minimal model with named parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.ln = nn.LayerNorm(3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.ln(x)
        x = self.linear2(x)
        return x

# Create model instance
model = SimpleModel()

# Create args object with required attributes
class Args:
    def __init__(self):
        self.wd = 0.01  # weight decay
        self.lr = 1e-4  # learning rate
        self.adam_epsilon = 1e-8  # epsilon for Adam

args = Args()

ARGS = {
    'model': model,
    'args': args
}
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 AdamW — a AdamW output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a AdamW 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
configure_dataloaders Not yet run
unverified (harvested, no recorded run)
declare-lab/TEAM/train_cicero.py
code served (permissive licence) · get_code("25695845c448eef9")
How it ran

no invocation recorded.

configure_dataloaders Not yet run
unverified (harvested, no recorded run)
declare-lab/TEAM/train_cicero2.py
code served (permissive licence) · get_code("eedd86173a2d52d7")
How it ran

no invocation recorded.

configure_dataloaders Not yet run
unverified (harvested, no recorded run)
declare-lab/TEAM/train_cosmosqa.py
code served (permissive licence) · get_code("5d544b01234bdcee")
How it ran

no invocation recorded.

configure_dataloaders Not yet run
unverified (harvested, no recorded run)
declare-lab/TEAM/train_csqa.py
code served (permissive licence) · get_code("6b021e1d8b19988c")
How it ran

no invocation recorded.

configure_scheduler Not yet run
unverified (harvested, no recorded run)
declare-lab/TEAM/train_cicero.py
code served (permissive licence) · get_code("83ef42f1f5c80dc5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 5 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
configure_optimizer 2 other papers
2 later
2311.08355 (2023-11)
Mustango: Toward Controllable Text-to-Music Generation
2024.naacl-long.459 (2024 (year only))
Mustango: Toward Controllable Text-to-Music Generation
configure_scheduler 2 other papers
2 later
2311.08355 (2023-11)
Mustango: Toward Controllable Text-to-Music Generation
2024.naacl-long.459 (2024 (year only))
Mustango: Toward Controllable Text-to-Music 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

We propose a simple refactoring of multichoice question answering (MCQA) tasks as a series of binary classifications. The MCQA task is generally performed by scoring each (question, answer) pair normalized over all the pairs, and then selecting the answer from the pair that yield the highest score. For n answer choices, this is equivalent to an n-class classification setup where only one class (true answer) is correct. We instead show that classifying (question, true answer) as positive instances and (question, false answer) as negative instances is significantly more effective across various models and datasets. We show the efficacy of our proposed approach in different tasks -abductive reasoning, commonsense question answering, science question answering, and sentence completion. Our DeBERTa binary classification model reaches the top or close to the top performance on public leaderboards for these tasks. The source code of the proposed approach is available at https: //github.com/declare-lab/TEAM.

For agents

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

get_harvested_code_for_paper("2210.16495")
get_code_for_paper("2210.16495")
have("2210.16495")

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

curl https://syntology.ai/api/ran/2210.16495.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.16495.svg)](https://syntology.ai/paper/2210.16495)

Connect an agent — have() is free.