SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.08400 · NAACL · 2021

Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs

Jiaao Chen, Diyi Yang

arXiv · PDF · Open in the Atlas

Code that ran

14 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; 4 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 8 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2104.08400.json · badge: /api/ran/2104.08400.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
GT-SALT/Structure-Aware-BART canonical (classifier label)
classifier basis: census
14 ran · 2 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
GT-SALT/Structure-Aware-BART/transformers/src/transformers/activations.py
code served (permissive licence) · get_code("0f786c407fb1ee4c")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:33:52Z). 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 swish takes a single parameter 'x' which is used with:
# - torch.sigmoid(x) - requires a tensor
# - x * ... - requires a tensor that supports multiplication
# So x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (2, 4) — shape (2, 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
count_trainable_parameters Ran
ran, honoured the contract we drafted
GT-SALT/Structure-Aware-BART/src/callbacks.py
pointer only (licence: MIT); the stored copy get_code serves, from manga-uofa/fdistill, is pointer only (licence: NONE) · get_code("a3826392847cbef3")
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 manga-uofa/fdistill, 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.

encode_line Ran
ran; our contract draft was wrong, not the code
GT-SALT/Structure-Aware-BART/src/utils.py
code served (permissive licence) · get_code("668b8e99ed0c27e5")
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
from transformers import BartTokenizer

torch.manual_seed(0)

# Create a minimal BartTokenizer instance
# BartTokenizer requires a vocab file, so we'll create a mock tokenizer
class MockTokenizer:
    def __init__(self, is_bart=False):
        self.is_bart = is_bart
    
    def __call__(self, texts, max_length=None, padding=None, truncation=False, return_tensors=None, add_prefix_space=False):
        # Return a mock tokenized output with input_ids
        batch_size = len(texts) if isinstance(texts, list) else 1
        return {
            'input_ids': torch.randint(0, 1000, (batch_size, max_length or 10))
        }

class MockBartTokenizer(MockTokenizer):
    def __init__(self):
        super().__init__(is_bart=True)

# Create tokenizer - use mock since we can't download real BartTokenizer
tokenizer = MockBartTokenizer()

# Define all arguments
ARGS = {
    'tokenizer': tokenizer,
    'line': 'This is a test sentence.',
    'max_length': 10,
    'pad_to_max_length': True,
    'return_tensors': 'pt'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — 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
gelu Ran
ran, honoured the contract we drafted
GT-SALT/Structure-Aware-BART/transformers/src/transformers/activations_tf.py
pointer only (licence: MIT); the stored copy get_code serves, from ypw0102/gdr, is pointer only (licence: NONE) · get_code("14a1c81ea568d152")
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 ypw0102/gdr, 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.

gelu_fast Ran
ran; our contract draft was wrong, not the code
GT-SALT/Structure-Aware-BART/transformers/src/transformers/activations.py
code served (permissive licence) · get_code("a4475703ff58ecf9")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 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)

# gelu_fast takes a single parameter 'x' which is used in arithmetic operations
# It should be a tensor that supports multiplication, addition, and tanh operations
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (2, 4) — shape (2, 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
gelu_new Ran
ran; our contract draft was wrong, not the code
GT-SALT/Structure-Aware-BART/transformers/src/transformers/activations.py
pointer only (licence: MIT); the stored copy get_code serves, from ypw0102/gdr, is pointer only (licence: NONE) · get_code("aef07bb1e2787431")
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 ypw0102/gdr, 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.

gelu_new Ran
ran, honoured the contract we drafted
GT-SALT/Structure-Aware-BART/transformers/src/transformers/activations_tf.py
pointer only (licence: MIT); the stored copy get_code serves, from ypw0102/gdr, is pointer only (licence: NONE) · get_code("13718ddda6b66f8e")
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 ypw0102/gdr, 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.

get_early_stopping_callback Ran
ran; our contract draft was wrong, not the code
GT-SALT/Structure-Aware-BART/src/callbacks.py
pointer only (licence: MIT); the stored copy get_code serves, from manga-uofa/fdistill, is pointer only (licence: NONE) · get_code("295d9fdc5ce0b054")
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 manga-uofa/fdistill, 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.

invert_mask Ran
ran, violated the contract we drafted
GT-SALT/Structure-Aware-BART/transformers/src/transformers/modeling_bart.py
pointer only (licence: MIT); the stored copy get_code serves, from yeliu918/KG-BART, is pointer only (licence: NONE) · get_code("874a42377fa0659f")
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 yeliu918/KG-BART, 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.

label_smoothed_nll_loss Ran
ran on a synthesized input
GT-SALT/Structure-Aware-BART/src/utils.py
code served (permissive licence) · get_code("e386d3a24af4d168")
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

torch.manual_seed(0)

# Create log probabilities tensor
# Shape: (batch_size=2, vocab_size=4)
# lprobs should be log probabilities, so values between -inf and 0
lprobs = torch.log(torch.softmax(torch.randn(2, 4), dim=-1))

# Create target indices tensor
# Shape: (batch_size=2,) - indices into the vocabulary
# Values should be in range [0, vocab_size) or ignore_index
target = torch.tensor([1, 2], dtype=torch.long)

# Epsilon for label smoothing (typically small, e.g., 0.1)
epsilon = 0.1

# Ignore index for padding tokens
ignore_index = -100

ARGS = {
    "lprobs": lprobs,
    "target": target,
    "epsilon": epsilon,
    "ignore_index": ignore_index,
}
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, 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
lmap Ran
ran; our contract draft was wrong, not the code
GT-SALT/Structure-Aware-BART/src/utils.py
code served (permissive licence) · get_code("b508796abb35571f")
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
from typing import Callable, List, Iterable

torch.manual_seed(0)

# Define a simple callable function
def square(x):
    return x ** 2

# Define an iterable (list of integers)
iterable = [1, 2, 3, 4, 5]

# Construct ARGS dict with all parameters
ARGS = {
    "f": square,
    "x": iterable
}
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 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
make_padding_mask Ran
ran; our contract draft was wrong, not the code
GT-SALT/Structure-Aware-BART/transformers/src/transformers/modeling_bart.py
pointer only (licence: MIT); the stored copy get_code serves, from yeliu918/KG-BART, is pointer only (licence: NONE) · get_code("f20c9b1aead27fea")
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 yeliu918/KG-BART, 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.

mish Ran
ran, honoured the contract we drafted
GT-SALT/Structure-Aware-BART/transformers/src/transformers/activations_tf.py
pointer only (licence: MIT); the stored copy get_code serves, from VITA-Group/READ-ME, is pointer only (licence: NONE) · get_code("cc8c8c3ebf0c343f")
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 VITA-Group/READ-ME, 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.

shift_tokens_right Ran
ran; our contract draft was wrong, not the code
GT-SALT/Structure-Aware-BART/transformers/src/transformers/modeling_bart.py
pointer only (licence: MIT); the stored copy get_code serves, from yeliu918/KG-BART, is pointer only (licence: NONE) · get_code("e00ccf7847d12b59")
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 yeliu918/KG-BART, 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.

get_checkpoint_callback Not yet run
unverified (harvested, no recorded run)
GT-SALT/Structure-Aware-BART/src/callbacks.py
code served (permissive licence) · get_code("d6fdbced63d1ed12")
How it ran

no invocation recorded.

load_xsum_checkpoint Not yet run
unverified (harvested, no recorded run)
GT-SALT/Structure-Aware-BART/transformers/src/transformers/convert_bart_original_pytorch_checkpoint_to_pytorch.py
code served (permissive licence) · get_code("20e1eb8c4dd8d2d1")
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, 14 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 5 the same month, 14 later) and 2 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
swish 206 other papers
63 dated earlier, 3 the same month, 137 later, 3 same year, order not determinable · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
mish 25 other papers
1 dated earlier, 24 later
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2106.00420 (2021-06)
Dialogue-oriented Pre-training
2107.00910 (2021-07)
Learned Token Pruning for Transformers
and 22 more not named here
gelu_new 24 other papers
1 dated earlier, 1 the same month, 22 later
2004.10964 (2020-04)
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
2104.08066 (2021-04)
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
2106.00420 (2021-06)
Dialogue-oriented Pre-training
and 21 more not named here
gelu_fast 22 other papers
1 dated earlier, 1 the same month, 20 later
2010.03957 (2020-10)
Transformers for Modeling Physical Systems
2104.08066 (2021-04)
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models
2106.00420 (2021-06)
Dialogue-oriented Pre-training
and 19 more not named here
count_trainable_parameters 13 other papers
4 dated earlier, 9 later
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2010.05953 (2020-10)
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
and 10 more not named here
shift_tokens_right 11 other papers
3 dated earlier, 6 later, 2 same year, order not determinable
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2009.12005 (2020-09)
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
2009.12677 (2020-09)
KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning
and 8 more not named here
invert_mask 10 other papers
3 dated earlier, 5 later, 2 same year, order not determinable
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2009.12005 (2020-09)
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
2009.12677 (2020-09)
KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning
and 7 more not named here
get_early_stopping_callback 9 other papers
2 dated earlier, 7 later
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2010.11856 (2020-10)
XOR QA: Cross-lingual Open-Retrieval Question Answering
2105.11174 (2021-05)
Retrieval Enhanced Model for Commonsense Generation
and 6 more not named here
lmap 9 other papers
1 dated earlier, 1 the same month, 7 later
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
2105.04779 (2021-05)
EL-Attention: Memory Efficient Lossless Attention for Generation
and 6 more not named here
make_padding_mask 9 other papers
3 dated earlier, 4 later, 2 same year, order not determinable
1910.13461 (2019-10)
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
2009.12005 (2020-09)
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
2009.12677 (2020-09)
KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning
and 6 more not named here
label_smoothed_nll_loss 7 other papers
1 dated earlier, 1 the same month, 5 later
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
2105.04779 (2021-05)
EL-Attention: Memory Efficient Lossless Attention for Generation
and 4 more not named here
gelu 3 other papers
3 later
2106.00420 (2021-06)
Dialogue-oriented Pre-training
2401.10487 (2024-01)
Generative Dense Retrieval: Memory Can Be a Burden
2406.10960 (2024-06)
ESCoT: Towards Interpretable Emotional Support Dialogue Systems
gelu_new 3 other papers
3 later
2106.00420 (2021-06)
Dialogue-oriented Pre-training
2401.10487 (2024-01)
Generative Dense Retrieval: Memory Can Be a Burden
2406.10960 (2024-06)
ESCoT: Towards Interpretable Emotional Support Dialogue Systems
encode_line 1 other paper
1 later
2105.04779 (2021-05)
EL-Attention: Memory Efficient Lossless Attention for Generation

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

Abstractive conversation summarization has received much attention recently. However, these generated summaries often suffer from insufficient, redundant, or incorrect content, largely due to the unstructured and complex characteristics of human-human interactions. To this end, we propose to explicitly model the rich structures in conversations for more precise and accurate conversation summarization, by first incorporating discourse relations between utterances and action triples ("WHO-DOING-WHAT") in utterances through structured graphs to better encode conversations, and then designing a multi-granularity decoder to generate summaries by combining all levels of information. Experiments show that our proposed models outperform state-of-theart methods and generalize well in other domains in terms of both automatic evaluations and human judgments. We have publicly released our code at https://github.com/ GT-SALT/Structure-Aware-BART.

For agents

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

get_harvested_code_for_paper("2104.08400")
get_code_for_paper("2104.08400")
have("2104.08400")

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

curl https://syntology.ai/api/ran/2104.08400.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.08400.svg)](https://syntology.ai/paper/2104.08400)

Connect an agent — have() is free.