SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.00573 · 2021

MuSiQue: Multihop Questions via Single-hop Question Composition

arXiv · PDF · Open in the Atlas

Code that ran

12 of 16 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 11 have no contract verdict; 1 failure of our instrument; 4 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/2108.00573.json · badge: /api/ran/2108.00573.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
stonybrooknlp/musique canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
mangopy/direct-rag-learning community (classifier label)
classifier basis not recorded on the link
11 ran · 4 no recorded run
FunctionStatusWhere it lives
cal_ppl Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/prepare/entropy.py
code served (permissive licence) · get_code("ebfd9b0ec5f4b3ef")
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 Tensor, ndim 1, dtype family float, shape (2,) 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
from torch import nn

torch.manual_seed(0)

class MockConfig:
    def __init__(self):
        self.vocab_size = 5

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.config = MockConfig()
        self.embedding = nn.Embedding(5, 8)
        self.linear = nn.Linear(8, 5)
    
    def forward(self, input_ids, labels=None):
        # input_ids shape: (batch_size, seq_len)
        x = self.embedding(input_ids)  # (batch_size, seq_len, 8)
        logits = self.linear(x)  # (batch_size, seq_len, vocab_size)
        return {'logits': logits}

model = MockModel()

batch_size = 2
seq_len = 4

input_ids = torch.randint(0, 5, (batch_size, seq_len))

labels = torch.randint(0, 5, (batch_size, seq_len))
labels[0, -1] = -100
labels[1, 2] = -100

ARGS = {
    'model': model,
    'input_ids': input_ids,
    'labels': labels
}
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 Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) 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
causal_cross_entropy Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/prepare/entropy.py
code served (permissive licence) · get_code("fac0d9d6ff56e2b2")
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 Tensor, ndim 1, dtype family float, shape (2,) 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
from torch import nn, tensor

torch.manual_seed(0)

# Define a minimal model that satisfies the function's requirements
class MinimalLanguageModel(nn.Module):
    def __init__(self, vocab_size=10, hidden_size=4):
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, hidden_size)
        self.lm_head = nn.Linear(hidden_size, vocab_size)
    
    def forward(self, input_ids, labels=None):
        # input_ids shape: (batch_size, seq_len)
        # returns dict with 'logits' key
        x = self.embedding(input_ids)  # (batch_size, seq_len, hidden_size)
        logits = self.lm_head(x)  # (batch_size, seq_len, vocab_size)
        return {'logits': logits}

# Create model instance
model = MinimalLanguageModel(vocab_size=10, hidden_size=4)

# Create input_ids tensor: (batch_size=2, seq_len=5)
input_ids = torch.tensor([[1, 2, 3, 4, 5],
                          [2, 3, 4, 5, 1]], dtype=torch.long)

# Create labels tensor: same shape as input_ids, with -100 for ignore_index positions
labels = torch.tensor([[2, 3, 4, 5, 1],
                       [3, 4, 5, 1, 2]], dtype=torch.long)

ARGS = {
    'model': model,
    'input_ids': input_ids,
    'labels': labels
}
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 Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) 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
collect_docs Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/evaluate.py
code served (permissive licence) · get_code("9369e71b95149aa5")
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

torch.manual_seed(0)

example = {
    'positive': ['doc_pos_1', 'doc_pos_2', 'doc_pos_3'],
    'retrieval': ['doc_ret_1', 'doc_ret_2', 'doc_ret_3', 'doc_ret_4', 'doc_ret_5', 'doc_ret_6', 'doc_ret_7', 'doc_ret_8', 'doc_ret_9', 'doc_ret_10', 'doc_ret_11', 'doc_ret_12', 'doc_ret_13', 'doc_ret_14', 'doc_ret_15', 'doc_ret_16', 'doc_ret_17']
}

ARGS = {
    'example': example,
    'k_positive': 3,
    'k_retrieval': 17
}
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
eval_em Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/utilize/metrics.py
code served (permissive licence) · get_code("0b2979a7d1760cb1")
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 dict. 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

def rounder(num):
    return round(num, 3)

def normalize_answer(s):
    """Lower text and remove punctuation, articles and extra whitespace."""
    re_punc = re.compile('[!"#$%&()*+,-./:;<=>?@\\[\\]\\\\^`{|}~_\\\']')

    def remove_articles(text):
        return re.sub('\\b(a|an|the)\\b', ' ', text)

    def white_space_fix(text):
        return ' '.join(text.split())

    def remove_punc(text):
        return re_punc.sub(' ', text)

    def lower(text):
        return text.lower()
    return white_space_fix(remove_articles(remove_punc(lower(s))))

def eval_em(predictions, raw):
    scores = []
    for pred, example in zip(predictions, raw):
        pred = normalize_answer(pred)
        if any([normalize_answer(ans) == pred for ans in example]):
            scores.append(1)
        else:
            scores.append(0)
    return {'EM': rounder(sum(scores) * 100 / len(scores))}

# Setup code
predictions = [
    "The capital of France",
    "Albert Einstein"
]

raw = [
    ["the capital of france", "paris is the capital"],
    ["albert einstein", "Einstein was a physicist"]
]

ARGS = {
    "predictions": predictions,
    "raw": raw
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
generation_instruction Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/instruction.py
code served (permissive licence) · get_code("bec7c35aef9d72d5")
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 copy
from typing import List

torch.manual_seed(0)

ARGS = {
    'question': 'What is the capital of France?',
    'docs': [
        'Paris is the capital and largest city of France, located in the north-central part of the country.',
        'France is a country in Western Europe with several overseas regions and territories.',
        'The Eiffel Tower is an iconic monument located in Paris.'
    ]
}
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
get_command Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/prepare/sampling.py
code served (permissive licence) · get_code("a54293fda5579b8c")
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 logging
import torch
import tempfile
import os

# Configure logging
logging.basicConfig(level=logging.INFO)

# Create temporary directory for files
temp_dir = tempfile.gettempdir()

# Define parameters for get_command function
execute_file = os.path.join(temp_dir, "train_script.py")
command_args = {
    "batch_size": 32,
    "learning_rate": 0.001,
    "epochs": 10,
    "model": "resnet50",
    "dataset": "cifar10"
}
device = [0, 1]
log_file = os.path.join(temp_dir, "training.log")

ARGS = {
    "execute_file": execute_file,
    "command_args": command_args,
    "device": device,
    "log_file": log_file
}
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
normalize_answer Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/utilize/metrics.py
code served (permissive licence) · get_code("97cb57dd2386abcb")
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

def normalize_answer(s):
    """Lower text and remove punctuation, articles and extra whitespace."""
    re_punc = re.compile('[!"#$%&()*+,-./:;<=>?@\\[\\]\\\\^`{|}~_\\\']')

    def remove_articles(text):
        return re.sub('\\b(a|an|the)\\b', ' ', text)

    def white_space_fix(text):
        return ' '.join(text.split())

    def remove_punc(text):
        return re_punc.sub(' ', text)

    def lower(text):
        return text.lower()
    return white_space_fix(remove_articles(remove_punc(lower(s))))

ARGS = {
    "s": "The Quick, Brown Fox! Jumps over a lazy dog."
}
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
preprocess_supervised_dataset Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/prepare/entropy.py
code served (permissive licence) · get_code("9b674a8aeb03a2f2")
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 dict. 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
from typing import Dict, List, Any

torch.manual_seed(0)

class StandInTokenizer:
    def __init__(self):
        self.vocab_size = 100
    
    def apply_chat_template(self, conversation: List[Dict[str, str]]) -> List[int]:
        """
        Simulate a chat template tokenizer.
        Returns token IDs based on the conversation content.
        """
        total_length = 0
        for msg in conversation:
            content = msg.get('content', '')
            total_length += len(content.split()) + 2
        
        token_ids = list(range(total_length))
        return token_ids

examples = {
    'prompt': [
        'What is machine learning?',
        'Explain deep learning.'
    ],
    'response': [
        'Machine learning is a subset of AI.',
        'Deep learning uses neural networks.'
    ]
}

tokenizer = StandInTokenizer()

ARGS = {
    'examples': examples,
    'tokenizer': tokenizer
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
rank_instruction Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/instruction.py
code served (permissive licence) · get_code("203ee66a16f129c1")
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 copy

ARGS = {
    "question": "What are the benefits of machine learning?",
    "docs": [
        "Machine learning is a subset of artificial intelligence that enables systems to learn from data without being explicitly programmed.",
        "Deep learning models can process large amounts of unstructured data efficiently.",
        "Neural networks are inspired by biological neural systems and can approximate complex functions.",
        "Supervised learning requires labeled training data to train predictive models."
    ]
}
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
read_jsonl Ran
ran; our contract draft was wrong, not the code
stonybrooknlp/musique/evaluate_v1.0.py
pointer only (licence: CC-BY-4.0) · get_code("a0c3c47032ca66fd")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stonybrooknlp/musique, is not in the permissive set Syntology serves inline. 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.

rounder Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/utilize/metrics.py
code served (permissive licence) · get_code("1ac4537f9c4bf017")
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

torch.manual_seed(0)

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 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
shell_command Ran
ran on a synthesized input
mangopy/direct-rag-learning/src/evaluate.py
code served (permissive licence) · get_code("456d16436e8dcb49")
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 Popen. 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 subprocess

ARGS = {
    'command': 'echo "test command"',
    'directory': './'
}
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 Popen — a Popen output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Popen 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
document_retrieval Not yet run
unverified (harvested, no recorded run)
mangopy/direct-rag-learning/src/prepare/prepare.py
code served (permissive licence) · get_code("4a62a7015c03e433")
How it ran

no invocation recorded.

gather_data Not yet run
unverified (harvested, no recorded run)
mangopy/direct-rag-learning/src/prepare/prepare.py
code served (permissive licence) · get_code("4e8dbe891b051948")
How it ran

no invocation recorded.

launch Not yet run
unverified (harvested, no recorded run)
mangopy/direct-rag-learning/src/evaluate.py
code served (permissive licence) · get_code("bb3452c00b70772e")
How it ran

no invocation recorded.

prepare_warmup_data_for_generation Not yet run
unverified (harvested, no recorded run)
mangopy/direct-rag-learning/src/prepare/prepare.py
code served (permissive licence) · get_code("ae22245c5794b39a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 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 14 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
causal_cross_entropy 1 other paper
1 later
2505.20128 (2025-05)
Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers
rounder 1 other paper
1 later
2505.20128 (2025-05)
Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers

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

Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by construction, \emph{requires} proper multihop reasoning? To this end, we introduce a bottom-up approach that systematically selects composable pairs of single-hop questions that are connected, i.e., where one reasoning step critically relies on information from another. This bottom-up methodology lets us explore a vast space of questions and add stringent filters as well as other mechanisms targeting connected reasoning. It provides fine-grained control over the construction process and the properties of the resulting $k$-hop questions. We use this methodology to create MuSiQue-Ans, a new multihop QA dataset with 25K 2-4 hop questions. Relative to existing datasets, MuSiQue-Ans is more difficult overall (3x increase in human-machine gap), and harder to cheat via disconnected reasoning (e.g., a single-hop model has a 30 point drop in F1). We further add unanswerable contrast questions to produce a more stringent dataset, MuSiQue-Full. We hope our datasets will help the NLP community develop models that perform genuine multihop reasoning.

For agents

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

get_harvested_code_for_paper("2108.00573")
get_code_for_paper("2108.00573")
have("2108.00573")

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

curl https://syntology.ai/api/ran/2108.00573.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.00573.svg)](https://syntology.ai/paper/2108.00573)

Connect an agent — have() is free.