SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1603.01547 · 2016

Text Understanding with the Attention Sum Reader Network

arXiv · PDF · Open in the Atlas

Code that ran

2 of 10 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 8 no recorded run), measured 2026-11-21; 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/1603.01547.json · badge: /api/ran/1603.01547.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
libertatis/mrc-cbt community (classifier label)
classifier basis not recorded on the link
2 ran · 8 no recorded run
FunctionStatusWhere it lives
get_record_parser Ran
ran on a synthesized input
libertatis/mrc-cbt/util.py
code served (permissive licence) · get_code("84fa04c20351d159")
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 function. 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 tensorflow as tf

class Config:
    def __init__(self):
        self.para_limit = 400
        self.test_para_limit = 300
        self.ques_limit = 50
        self.test_ques_limit = 40
        self.char_limit = 16
        self.num_cans = 4

config = Config()

ARGS = {
    "config": config,
    "is_test": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
glu Ran
ran, honoured the contract we drafted
libertatis/mrc-cbt/layers.py
code served (permissive licence) · get_code("618e1a43f3790bc0")
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 EagerTensor, ndim 3, dtype family float, shape (2, 3, 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
tf.random.set_seed(0)

# Create a small test tensor
# Shape: [batch_size=2, seq_len=3, 2*hidden_size=4]
# The function splits on axis=-1 into two parts of size 2 each
x = tf.constant(np.random.randn(2, 3, 4).astype(np.float32))

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, shape (2, 3, 2) — shape (2, 3, 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
cbt_text2json Not yet run
unverified (harvested, no recorded run)
libertatis/mrc-cbt/cbt_text2json.py
code served (permissive licence) · get_code("1cbcbc7973ab4b10")
How it ran

no invocation recorded.

convert_to_features Not yet run
unverified (harvested, no recorded run)
libertatis/mrc-cbt/prepro.py
code served (permissive licence) · get_code("a257835a6f083f17")
How it ran

no invocation recorded.

default_tokenizer Not yet run
unverified (harvested, no recorded run)
libertatis/mrc-cbt/cbt_text2json.py
code served (permissive licence) · get_code("4311e2158e8c5261")
How it ran

no invocation recorded.

default_tokenizer Not yet run
unverified (harvested, no recorded run)
libertatis/mrc-cbt/prepro.py
code served (permissive licence) · get_code("17de19718f9723ae")
How it ran

no invocation recorded.

get_batch_dataset Not yet run
unverified (harvested, no recorded run)
libertatis/mrc-cbt/util.py
code served (permissive licence) · get_code("29a6e45846396956")
How it ran

no invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
libertatis/mrc-cbt/util.py
code served (permissive licence) · get_code("1ea08aaae7fd9f80")
How it ran

no invocation recorded.

layer_norm_compute_python Not yet run
unverified (harvested, no recorded run)
libertatis/mrc-cbt/layers.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from zhangyaoyuan/GAN-Simplification, is pointer only (licence: NONE) · get_code("80444e734e109863")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from zhangyaoyuan/GAN-Simplification, and GitHub detected no licence in that repository when it was checked. 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. No invocation recorded.

noam_norm Not yet run
unverified (harvested, no recorded run)
libertatis/mrc-cbt/layers.py
code served (permissive licence) · get_code("98c3ae22156c7728")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 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
glu 2 other papers
1 dated earlier, 1 later
1508.06615 (2015-08)
Character-Aware Neural Language Models
1909.06356 (2019-09)
Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering
noam_norm 2 other papers
1 dated earlier, 1 later
1508.06615 (2015-08)
Character-Aware Neural Language Models
1909.06356 (2019-09)
Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering
get_dataset 1 other paper
1 dated earlier
1508.06615 (2015-08)
Character-Aware Neural Language Models
layer_norm_compute_python 1 other paper
1 later
1607.06450 (2016-07)
Layer Normalization

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Several large cloze-style context-question-answer datasets have been introduced recently: the CNN and Daily Mail news data and the Children's Book Test. Thanks to the size of these datasets, the associated text comprehension task is well suited for deep-learning techniques that currently seem to outperform all alternative approaches. We present a new, simple model that uses attention to directly pick the answer from the context as opposed to computing the answer using a blended representation of words in the document as is usual in similar models. This makes the model particularly suitable for question-answering problems where the answer is a single word from the document. Ensemble of our models sets new state of the art on all evaluated datasets.

For agents

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

get_harvested_code_for_paper("1603.01547")
get_code_for_paper("1603.01547")
have("1603.01547")

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

curl https://syntology.ai/api/ran/1603.01547.json

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

[![Syntology run record](https://syntology.ai/api/ran/1603.01547.svg)](https://syntology.ai/paper/1603.01547)

Connect an agent — have() is free.