SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1602.06023 · 2016

Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 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/1602.06023.json · badge: /api/ran/1602.06023.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
kashgupta/textsummarization extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
meghu2791/DeepLearningModels reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
attention_mul Ran
ran, honoured the contract we drafted
meghu2791/DeepLearningModels/model.py
code served (permissive licence) · get_code("96aec95e5c30b374")
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 2, dtype family float, shape (1, 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)

# The function expects:
# - rnn_outputs: a tensor that supports size(0) and indexing [i]
# - att_weights: a tensor that supports size(0) and indexing [i]
# Both should have compatible shapes for element-wise multiplication

batch_size = 2
seq_len = 3
hidden_dim = 4

# rnn_outputs: shape (seq_len, hidden_dim)
rnn_outputs = torch.randn(seq_len, hidden_dim)

# att_weights: shape (seq_len, hidden_dim) for broadcasting with rnn_outputs
att_weights = torch.randn(seq_len, hidden_dim)

ARGS = {
    "rnn_outputs": rnn_outputs,
    "att_weights": att_weights,
}
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 2, dtype family float, shape (1, 4) — shape (1, 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
create_ngrams Ran
ran; our contract draft was wrong, not the code
kashgupta/textsummarization/Extension-2/Extension_Part_1.py
code served (permissive licence) · get_code("0dbfbcc464c29d4e")
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 2, 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
import numpy as np

# Analyze the function:
# - text_list: a list that supports len() and slicing with [i:j]
# - n: an integer, defaults to 2

# The function creates n-grams from text_list
# It needs: len(text_list), slicing operations, append to list

# Create a simple text_list - a list of strings or tokens
text_list = ["hello", "world", "this", "is", "a", "test"]

# Create ARGS dict with all parameters
ARGS = {
    "text_list": text_list,
    "n": 2
}
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 list, ndim 2, 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
decode Ran
ran; our contract draft was wrong, not the code
meghu2791/DeepLearningModels/model.py
code served (permissive licence) · get_code("0c557b9d91697584")
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 torch
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create a dummy model (not actually used in the function body)
class DummyModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(10, 10)
    
    def forward(self, x):
        return self.linear(x)

model = DummyModel()

# Create logits tensor: shape (batch_size=2, seq_len=3, vocab_size=4)
# This will be reshaped to (-1, vocab_size) = (6, 4) in the function
logits = torch.randn(2, 3, 4)

# vocab_size parameter
vocab_size = 4

ARGS = {
    "model": model,
    "logits": logits,
    "vocab_size": vocab_size,
}
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 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
intersection Ran
ran, violated the contract we drafted
kashgupta/textsummarization/Extension-2/Extension_Part_1.py
code served (permissive licence) · get_code("2056211e6a0e4539")
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.

import torch
import numpy as np

torch.manual_seed(0)

# The function takes two lists and finds the intersection
# It checks if values from system_lst are in ref_lst
# The values should be comparable (support 'in' operator)

system_lst = [1, 2, 3, 4, 5]
ref_lst = [3, 4, 5, 6, 7]

ARGS = {
    "system_lst": system_lst,
    "ref_lst": ref_lst,
}
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 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
rouge_metrics Ran
ran, honoured the contract we drafted
kashgupta/textsummarization/Extension-2/Extension_Part_1.py
code served (permissive licence) · get_code("3bcc17ac26724ff5")
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, 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
import numpy as np

torch.manual_seed(0)

# The function takes two lists of values and compares them
# Based on the function body, it needs:
# - system_list: a list of comparable values (strings, ints, etc.)
# - reference_list: a list of comparable values (strings, ints, etc.)

system_list = ["the", "quick", "brown", "fox"]
reference_list = ["the", "brown", "fox", "jumps"]

ARGS = {
    "system_list": system_list,
    "reference_list": reference_list,
}
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 tuple, ndim 1, dtype family float — a tuple 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
train_data Not yet run
unverified (harvested, no recorded run)
meghu2791/DeepLearningModels/model.py
code served (permissive licence) · get_code("f63c9732ae7b92ed")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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 work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-to-word structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new dataset consisting of multi-sentence summaries, and establish performance benchmarks for further research.

For agents

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

get_harvested_code_for_paper("1602.06023")
get_code_for_paper("1602.06023")
have("1602.06023")

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

curl https://syntology.ai/api/ran/1602.06023.json

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

[![Syntology run record](https://syntology.ai/api/ran/1602.06023.svg)](https://syntology.ai/paper/1602.06023)

Connect an agent — have() is free.