SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1606.04582 · 2016

Query-Reduction Networks for Question Answering

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 5 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/1606.04582.json · badge: /api/ran/1606.04582.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
uwnlp/qrn canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
apply Ran
ran on a synthesized input
uwnlp/qrn/qa2hypo.py
code served (permissive licence) · get_code("614cd4ff5ed0b119")
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

# The function uses:
# - regex.match(question) -> needs a compiled regex pattern
# - result.groups() -> match object that returns groups
# - string.format(*result.groups(), answer=answer) -> format string with positional and keyword args
# - .capitalize() -> string method

# Create a simple regex pattern that captures groups
regex = re.compile(r'what is (\w+)\s+(\w+)')

# Create a format string that uses positional args and answer keyword arg
string = "The {} {} is {answer}"

# Create a question that matches the regex and produces groups
question = "what is the answer"

# Create an answer string
answer = "yes"

ARGS = {
    "regex": regex,
    "string": string,
    "question": question,
    "answer": answer
}
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
bool_ Ran
ran on a synthesized input
uwnlp/qrn/prepro-dialog.py
code served (permissive licence) · get_code("7e833c4f48283721")
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

def bool_(string):
    if string == 'True':
        return True
    elif string == 'False':
        return False
    else:
        raise Exception('Cannot cast %r to bool value.' % string)

ARGS = {
    'string': 'True'
}
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 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
bool_ Ran
ran on a synthesized input
uwnlp/qrn/babi/visualize_result.py
code served (permissive licence) · get_code("d7bcd84367c16537")
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

def setup():
    string_true = 'True'
    
    return {
        'string': string_true
    }

ARGS = setup()
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 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
qa2hypo Ran
ran on a synthesized input
uwnlp/qrn/qa2hypo.py
code served (permissive licence) · get_code("0db092a8268706d8")
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

# Define ARGS dictionary with valid arguments for qa2hypo function
ARGS = {
    "question": "Where is the cat?",
    "answer": "kitchen"
}
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
read_data Ran
ran on a synthesized input
uwnlp/qrn/babi/read_data.py
code served (permissive licence) · get_code("35e1b8042092a3f0")
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 DataSet. 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 json
import logging
import os
import numpy as np
import tempfile

# Create temporary directories and files for the test
temp_dir = tempfile.mkdtemp()

# Create the necessary directory structure
lang = "en"
task = "01"
mid = lang
task_dir = os.path.join(temp_dir, mid, task.zfill(2))
os.makedirs(task_dir, exist_ok=True)

# Create mode2idxs.json
mode2idxs_dict = {
    "train": [0, 1, 2, 3, 4],
    "val": [5, 6],
    "test": [7, 8, 9]
}
mode2idxs_path = os.path.join(task_dir, 'mode2idxs.json')
with open(mode2idxs_path, 'w') as f:
    json.dump(mode2idxs_dict, f)

# Create data.json with sample data
# The data structure should be a list of lists where each inner list 
# contains values indexed by the indices in mode2idxs
data = [
    [f"text_{i}" for i in range(10)],  # text data
    [f"label_{i}" for i in range(10)]   # label data
]
data_path = os.path.join(task_dir, 'data.json')
with open(data_path, 'w') as f:
    json.dump(data, f)

# Create a params object with required attributes
class Params:
    def __init__(self):
        self.lang = lang
        self.large = False
        self.data_dir = temp_dir
        self.batch_size = 2

params = Params()

ARGS = {
    'params': params,
    'mode': 'train',
    'task': '1'
}
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 DataSet — a DataSet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataSet 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

In this paper, we study the problem of question answering when reasoning over multiple facts is required. We propose Query-Reduction Network (QRN), a variant of Recurrent Neural Network (RNN) that effectively handles both short-term (local) and long-term (global) sequential dependencies to reason over multiple facts. QRN considers the context sentences as a sequence of state-changing triggers, and reduces the original query to a more informed query as it observes each trigger (context sentence) through time. Our experiments show that QRN produces the state-of-the-art results in bAbI QA and dialog tasks, and in a real goal-oriented dialog dataset. In addition, QRN formulation allows parallelization on RNN's time axis, saving an order of magnitude in time complexity for training and inference.

For agents

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

get_harvested_code_for_paper("1606.04582")
get_code_for_paper("1606.04582")
have("1606.04582")

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

curl https://syntology.ai/api/ran/1606.04582.json

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

[![Syntology run record](https://syntology.ai/api/ran/1606.04582.svg)](https://syntology.ai/paper/1606.04582)

Connect an agent — have() is free.