SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1506.03134 · 2015

Pointer Networks

arXiv · PDF · Open in the Atlas

Code that ran

18 of 23 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; 3 honoured the contract we drafted, 1 violated it and 9 have no contract verdict; 5 failures 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/1506.03134.json · badge: /api/ran/1506.03134.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
copy not recorded community
not in the paper's declared repositories
7 ran · 0 no recorded run
devsisters/pointer-network-tensorflow community (classifier label)
classifier basis not recorded on the link
5 ran · 5 no recorded run
NTT123/pointer-networks community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
thomlake/pytorch-attention community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
PreProcessOutput Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from JoseVillagranE/Pointer-Networks
pointer only; the stored copy get_code serves, from JoseVillagranE/Pointer-Networks, is pointer only (licence: NONE) · get_code("b337a9636b389167")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

PreProcessOutput_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from JoseVillagranE/Pointer-Networks
pointer only; the stored copy get_code serves, from JoseVillagranE/Pointer-Networks, is pointer only (licence: NONE) · get_code("d88d8c4f9d624404")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

Reward Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from JoseVillagranE/Pointer-Networks
pointer only; the stored copy get_code serves, from JoseVillagranE/Pointer-Networks, is pointer only (licence: NONE) · get_code("7c3324bc44451062")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

add_argument_group Ran
ran; our contract draft was wrong, not the code
devsisters/pointer-network-tensorflow/config.py
code served (permissive licence) · get_code("6d80592fd6d47b2d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned _ArgumentGroup. 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 argparse

arg_lists = []
parser = argparse.ArgumentParser()

def add_argument_group(name):
    arg = parser.add_argument_group(name)
    arg_lists.append(arg)
    return arg

ARGS = {
    'name': 'test_group'
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 _ArgumentGroup — a _ArgumentGroup output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a _ArgumentGroup 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
batch Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from Guillem96/pointer-nn-pytorch
pointer only; the stored copy get_code serves, from Guillem96/pointer-nn-pytorch, is pointer only (licence: GPL-3.0) · get_code("796b2511367209ba")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

compute_convex_hull Ran
ran on a synthesized input
NTT123/pointer-networks/utils.py
code served (permissive licence) · get_code("808b77f0d68bfa3b")
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 int; 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.

from typing import List, NamedTuple

class Point(NamedTuple):
    x: float
    y: float

# Create a small set of points for testing the convex hull algorithm
points = [
    Point(0.0, 0.0),
    Point(1.0, 1.0),
    Point(2.0, 0.0),
    Point(1.0, 2.0),
    Point(0.5, 0.5),
]

ARGS = {
    "points": points
}
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 list, ndim 1, dtype family int — 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
dot Ran
ran on a synthesized input
thomlake/pytorch-attention/attention/attention.py
code served (permissive licence) · get_code("9cd6b612674a71c5")
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 3, dtype family float, shape (2, 3, 5) 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)

# Create sample tensors matching the function signature
# a: (B, M, D) - batch size 2, M=3, D=4
# b: (B, N, D) - batch size 2, N=5, D=4
a = torch.randn(2, 3, 4)
b = torch.randn(2, 5, 4)

ARGS = {
    "a": a,
    "b": b,
}
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 3, dtype family float, shape (2, 3, 5) — shape (2, 3, 5) 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
fill_context_mask Ran
ran on a synthesized input
thomlake/pytorch-attention/attention/attention.py
code served (permissive licence) · get_code("01ecdf1ea44311c2")
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 3, dtype family float, shape (2, 3, 4) 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)

# Create a mask tensor of size (B, N, D)
# B=2 (batch), N=3 (sequence/attention heads), D=4 (context dimension)
mask = torch.zeros(2, 3, 4)

# List of context sizes for each item in batch
# First item has size 2, second item has size 3
# This means positions beyond these sizes will be masked
sizes = [2, 3]

# Value to use for masked positions
v_mask = float('-inf')

# Value to use for unmasked positions
v_unmask = 0.0

ARGS = {
    "mask": mask,
    "sizes": sizes,
    "v_mask": v_mask,
    "v_unmask": v_unmask,
}
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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 4) 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
generate_one_example Ran
ran on a synthesized input
devsisters/pointer-network-tensorflow/data_loader.py
code served (permissive licence) · get_code("144491703e61223e")
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. 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 numpy as np

# Set random seed for reproducibility
rng = np.random.RandomState(42)

# Define arguments for generate_one_example
n_nodes = 5
ARGS = {
    "n_nodes": n_nodes,
    "rng": rng
}
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 tuple — a tuple output has no array shape of its own; none is 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_left_most_point Ran
ran on a synthesized input
NTT123/pointer-networks/utils.py
code served (permissive licence) · get_code("8ff08ad475614f0a")
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 int, ndim 0, dtype family int, 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.

from typing import List, NamedTuple

class Point(NamedTuple):
    x: float
    y: float

def get_left_most_point(points: List[Point]) -> int:
    x, _ = zip(*points)
    return x.index(min(x))

# Create a list of Point objects
points = [
    Point(x=5.0, y=10.0),
    Point(x=2.0, y=15.0),
    Point(x=8.0, y=3.0),
    Point(x=1.0, y=7.0),
]

ARGS = {
    "points": points
}
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 int, ndim 0, dtype family int, 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
length Ran
ran on a synthesized input
devsisters/pointer-network-tensorflow/data_loader.py
code served (permissive licence) · get_code("f9e1ca751b8d078c")
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 float64, ndim 0, 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 numpy as np

# The function length(x, y) computes the Euclidean distance between two points
# It converts both x and y to numpy arrays and computes the norm of their difference
# x and y should be array-like objects (lists, tuples, numpy arrays, etc.)

# Create two distinct points in a 4-dimensional space
x = [1.0, 2.0, 3.0, 4.0]
y = [5.0, 6.0, 7.0, 8.0]

ARGS = {
    "x": x,
    "y": y
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
mask3d Ran
ran on a synthesized input
thomlake/pytorch-attention/attention/attention.py
code served (permissive licence) · get_code("fc2318f83f2edd7e")
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 3, dtype family float, shape (2, 4, 3) 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.autograd import Variable

torch.manual_seed(0)

# Construct a small 3D tensor (B=2, N=4, D=3)
value = torch.randn(2, 4, 3)

# Construct sizes list - indicating valid entries for each batch item
# First batch item has 2 valid entries, second has 3 valid entries
sizes = [2, 3]

ARGS = {
    "value": value,
    "sizes": sizes
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) 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
on_left_side Ran
ran on a synthesized input
NTT123/pointer-networks/utils.py
code served (permissive licence) · get_code("0719b12a34b7a290")
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

torch.manual_seed(0)

# Construct arguments for on_left_side(c, a, b)
# The function expects c, a, b to be points that can be unpacked with zip(*[c, a, b])
# This means each should be a sequence of (x, y) coordinates

# Create three 2D points as tuples
c = (1, 2)  # point C at (1, 2)
a = (0, 0)  # point A at (0, 0)
b = (4, 0)  # point B at (4, 0)

ARGS = {
    "c": c,
    "a": a,
    "b": b,
}
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
sample Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from Guillem96/pointer-nn-pytorch
pointer only; the stored copy get_code serves, from Guillem96/pointer-nn-pytorch, is pointer only (licence: GPL-3.0) · get_code("8b887331144b7967")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

sequence_mask Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from JoseVillagranE/Pointer-Networks
pointer only; the stored copy get_code serves, from JoseVillagranE/Pointer-Networks, is pointer only (licence: NONE) · get_code("0c43e7290e581e42")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

solve_tsp_dynamic Ran
ran on a synthesized input
devsisters/pointer-network-tensorflow/data_loader.py
code served (permissive licence) · get_code("cd74738f6e87dded")
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 ndarray, ndim 1, dtype family int, shape (4,) 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 numpy as np

# The function solve_tsp_dynamic solves the Traveling Salesman Problem using dynamic programming.
# It takes a single parameter 'points' which should be a list/array of coordinate tuples.
# The function expects points to be convertible to numpy arrays and computes distances between them.

# Create a small set of 2D points for testing
points = [
    (0.0, 0.0),
    (1.0, 0.0),
    (1.0, 1.0),
    (0.0, 1.0)
]

ARGS = {
    "points": points
}
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 ndarray, ndim 1, dtype family int, shape (4,) — shape (4,) 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
str2bool Ran
ran, violated the contract we drafted
devsisters/pointer-network-tensorflow/config.py
pointer only (licence: MIT); the stored copy get_code serves, from haoran0301/amenunet, is pointer only (licence: NONE) · get_code("248284f69adfeaad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from haoran0301/amenunet, 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. A run is recorded.

tensor_sort Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from JoseVillagranE/Pointer-Networks
pointer only; the stored copy get_code serves, from JoseVillagranE/Pointer-Networks, is pointer only (licence: NONE) · get_code("926944485fdd4f48")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

decoder_rnn Not yet run
unverified (harvested, no recorded run)
devsisters/pointer-network-tensorflow/layers.py
code served (permissive licence) · get_code("1d70016e058df0c1")
How it ran

no invocation recorded.

download_file_from_google_drive Not yet run
unverified (harvested, no recorded run)
devsisters/pointer-network-tensorflow/download.py
code served (permissive licence) · get_code("20f31737837ced8e")
How it ran

no invocation recorded.

get_confirm_token Not yet run
unverified (harvested, no recorded run)
devsisters/pointer-network-tensorflow/download.py
pointer only (licence: MIT); the stored copy get_code serves, from med-air/FedBN, is pointer only (licence: NONE) · get_code("135b3dc835ffe6ad")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from med-air/FedBN, 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.

index_matrix_to_pairs Not yet run
unverified (harvested, no recorded run)
devsisters/pointer-network-tensorflow/layers.py
code served (permissive licence) · get_code("91e306bf0f9b04bc")
How it ran

no invocation recorded.

trainable_initial_state Not yet run
unverified (harvested, no recorded run)
devsisters/pointer-network-tensorflow/layers.py
code served (permissive licence) · get_code("4719eb1221618d56")
How it ran

no invocation recorded.

Also present in other papers' code

Of 23 samples lifted from this paper's linked repositories, 23 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 11 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 9 later) and 12 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
get_confirm_token 38 other papers
2 dated earlier, 36 later
1409.8230 (2014-09)
RENOIR - A Dataset for Real Low-Light Image Noise Reduction
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1607.06520 (2016-07)
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
and 35 more not named here
str2bool 33 other papers
1 dated earlier, 32 later
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
1612.06321 (2016-12)
Large-Scale Image Retrieval with Attentive Deep Local Features
and 30 more not named here
add_argument_group 27 other papers
1 dated earlier, 26 later
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1611.01578 (2016-11)
Neural Architecture Search with Reinforcement Learning
and 24 more not named here
batch 2 other papers
2 dated earlier
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
download_file_from_google_drive 2 other papers
2 later
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
1805.07010 (2018-05)
Learning Permutations with Sinkhorn Policy Gradient
sample 2 other papers
2 dated earlier
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1409.3215 (2014-09)
Sequence to Sequence Learning with Neural Networks
PreProcessOutput 1 other paper
1 later
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
PreProcessOutput_batch 1 other paper
1 later
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
Reward 1 other paper
1 later
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
sequence_mask 1 other paper
1 later
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning
tensor_sort 1 other paper
1 later
1611.09940 (2016-11)
Neural Combinatorial Optimization with Reinforcement Learning

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 introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines, because the number of target classes in each step of the output depends on the length of the input, which is variable. Problems such as sorting variable sized sequences, and various combinatorial optimization problems belong to this class. Our model solves the problem of variable size output dictionaries using a recently proposed mechanism of neural attention. It differs from the previous attention attempts in that, instead of using attention to blend hidden units of an encoder to a context vector at each decoder step, it uses attention as a pointer to select a member of the input sequence as the output. We call this architecture a Pointer Net (Ptr-Net). We show Ptr-Nets can be used to learn approximate solutions to three challenging geometric problems -- finding planar convex hulls, computing Delaunay triangulations, and the planar Travelling Salesman Problem -- using training examples alone. Ptr-Nets not only improve over sequence-to-sequence with input attention, but also allow us to generalize to variable size output dictionaries. We show that the learnt models generalize beyond the maximum lengths they were trained on. We hope our results on these tasks will encourage a broader exploration of neural learning for discrete problems.

For agents

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

get_harvested_code_for_paper("1506.03134")
get_code_for_paper("1506.03134")
have("1506.03134")

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

curl https://syntology.ai/api/ran/1506.03134.json

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

[![Syntology run record](https://syntology.ai/api/ran/1506.03134.svg)](https://syntology.ai/paper/1506.03134)

Connect an agent — have() is free.