SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.02789 · 2018

Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Ashish Sabharwal, Peter Clark, Tushar Khot, Todor Mihaylov

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 have no contract verdict; 0 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/1809.02789.json · badge: /api/ran/1809.02789.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
allenai/arc-solvers canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
create_hypothesis Ran
ran on a synthesized input
allenai/arc-solvers/arc_solvers/processing/convert_to_entailment.py
code served (permissive licence) · get_code("f92024b299799ce7")
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 re

BLANK_STR = '___'

def create_hypothesis(fitb: str, choice: str) -> str:
    if '. ' + BLANK_STR in fitb or fitb.startswith(BLANK_STR):
        choice = choice[0].upper() + choice[1:]
    else:
        choice = choice.lower()
    if not fitb.endswith(BLANK_STR):
        choice = choice.rstrip('.')
    hypothesis = re.sub('__+', choice, fitb)
    return hypothesis

ARGS = {
    'fitb': 'The quick brown fox jumps over the ___ dog.',
    'choice': 'Lazy'
}
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_fitb_from_question Ran
ran on a synthesized input
allenai/arc-solvers/arc_solvers/processing/convert_to_entailment.py
code served (permissive licence) · get_code("274f33301270f386")
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 re

BLANK_STR = '___'

def replace_wh_word_with_blank(question_str: str):
    wh_word_offset_matches = []
    wh_words = ['which', 'what', 'where', 'when', 'how', 'who', 'why']
    for wh in wh_words:
        m = re.search(wh + '\\?[^\\.]*[\\. ]*$', question_str.lower())
        if m:
            wh_word_offset_matches = [(wh, m.start())]
            break
        else:
            m = re.search(wh + '[ ,][^\\.]*[\\. ]*$', question_str.lower())
            if m:
                wh_word_offset_matches.append((wh, m.start()))
    if len(wh_word_offset_matches):
        wh_word_offset_matches.sort(key=lambda x: x[1])
        wh_word_found = wh_word_offset_matches[0][0]
        wh_word_start_offset = wh_word_offset_matches[0][1]
        question_str = re.sub('\\?$', '.', question_str.strip())
        fitb_question = question_str[:wh_word_start_offset] + BLANK_STR + question_str[wh_word_start_offset + len(wh_word_found):]
        return fitb_question.replace(BLANK_STR + ' of the following', BLANK_STR)
    elif re.match('.*[^\\.\\?] *$', question_str):
        return question_str + ' ' + BLANK_STR
    else:
        return re.sub(' this[ \\?]', ' ___ ', question_str)

def get_fitb_from_question(question_text: str) -> str:
    fitb = replace_wh_word_with_blank(question_text)
    if not re.match('.*_+.*', fitb):
        print("Can't create hypothesis from: '{}'. Appending {} !".format(question_text, BLANK_STR))
        fitb = re.sub('[\\.\\? ]*$', '', question_text.strip()) + BLANK_STR
    return fitb

ARGS = {
    'question_text': 'What is the capital of France?'
}
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
score_choice_predictions Ran
ran on a synthesized input
allenai/arc-solvers/arc_solvers/processing/evaluate_predictions.py
code served (permissive licence) · get_code("660aff04fb937072")
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)

# Construct valid arguments for score_choice_predictions
# The function takes a list of floats representing choice predictions
# and returns the maximum value rounded to 4 decimal places

choice_predictions = [0.123456, 0.789012, 0.456789, 0.234567]

ARGS = {
    "choice_predictions": choice_predictions
}
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
create_hypothesis 1 other paper
1 later
1909.02151 (2019-09)
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning

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 present a new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject. The open book that comes with our questions is a set of 1326 elementary level science facts. Roughly 6000 questions probe an understanding of these facts and their application to novel situations. This requires combining an open book fact (e.g., metals conduct electricity) with broad common knowledge (e.g., a suit of armor is made of metal) obtained from other sources. While existing QA datasets over documents or knowledge bases, being generally self-contained, focus on linguistic understanding, OpenBookQA probes a deeper understanding of both the topic-in the context of common knowledge-and the language it is expressed in. Human performance on OpenBookQA is close to 92%, but many state-of-the-art pre-trained QA methods perform surprisingly poorly, worse than several simple neural baselines we develop. Our oracle experiments designed to circumvent the knowledge retrieval bottleneck demonstrate the value of both the open book and additional facts. We leave it as a challenge to solve the retrieval problem in this multi-hop setting and to close the large gap to human performance.

For agents

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

get_harvested_code_for_paper("1809.02789")
get_code_for_paper("1809.02789")
have("1809.02789")

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

curl https://syntology.ai/api/ran/1809.02789.json

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

[![Syntology run record](https://syntology.ai/api/ran/1809.02789.svg)](https://syntology.ai/paper/1809.02789)

Connect an agent — have() is free.