SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.03548 · EMNLP · 2023

GEMINI: Controlling The Sentence-Level Summary Style in Abstractive Text Summarization

Yue Zhang, Guangsheng Bao, Zebin Ou, Aaron Hernandez

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 4 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2304.03548.json · badge: /api/ran/2304.03548.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
baoguangsheng/gemini canonical (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
Embedding Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
baoguangsheng/gemini/fairseq/models/transformer_gemini.py
pointer only (licence: MIT); the stored copy get_code serves, from instance-wise-ordered-transformer/iot, is pointer only (licence: NOASSERTION) · get_code("96cbb5e9ca5b6be0")
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 instance-wise-ordered-transformer/iot, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

Linear Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
baoguangsheng/gemini/fairseq/models/transformer_gemini.py
pointer only (licence: MIT); the stored copy get_code serves, from instance-wise-ordered-transformer/iot, is pointer only (licence: NOASSERTION) · get_code("8cd8cb0d1e9e63e4")
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 instance-wise-ordered-transformer/iot, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

distributed_init Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
baoguangsheng/gemini/fairseq/distributed_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from agi-content-generation/EKD, is pointer only (licence: NOASSERTION) · get_code("2e69129bbcf930e7")
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 agi-content-generation/EKD, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

is_master Ran
ran, violated the contract we drafted
baoguangsheng/gemini/fairseq/distributed_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from agi-content-generation/EKD, is pointer only (licence: NOASSERTION) · get_code("90b79fe15491de83")
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 agi-content-generation/EKD, and GitHub could not classify the licence of that repository (NOASSERTION). 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
baoguangsheng/gemini/fairseq/criterions/label_smoothed_cross_entropy_gemini.py
code served (permissive licence) · get_code("3986ca46566273de")
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 we use log_softmax
lprobs = torch.log_softmax(torch.randn(2, 4), dim=-1)

# Create target tensor: shape (batch_size=2,)
target = torch.tensor([0, 2], dtype=torch.long)

# Label smoothing epsilon
epsilon = 0.1

# Token range (inclusive) for itok filtering
itok_range = [0, 1]

# Index to ignore (padding index)
ignore_index = None

# Whether to reduce the loss
reduce = True

ARGS = {
    "lprobs": lprobs,
    "target": target,
    "epsilon": epsilon,
    "itok_range": itok_range,
    "ignore_index": ignore_index,
    "reduce": reduce,
}
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
safe_readline Ran
ran; our contract draft was wrong, not the code
baoguangsheng/gemini/fairseq/binarizer.py
pointer only (licence: MIT); the stored copy get_code serves, from agi-content-generation/EKD, is pointer only (licence: NOASSERTION) · get_code("82bdf940665aeeb4")
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 agi-content-generation/EKD, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

all_reduce Not yet run
unverified (harvested, no recorded run)
baoguangsheng/gemini/fairseq/distributed_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from agi-content-generation/EKD, is pointer only (licence: NOASSERTION) · get_code("199e96db5edd0edd")
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 agi-content-generation/EKD, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 6 later) and 1 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
safe_readline 66 other papers
54 dated earlier, 10 later, 2 same year, order not determinable
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
1802.06901 (2018-02)
Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
1904.01038 (2019-04)
FAIRSEQ: A Fast, Extensible Toolkit for Sequence Modeling
and 63 more not named here
Linear 58 other papers
40 dated earlier, 18 later · 5 only as an assembly brick
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1706.03762 (2017-06)
Attention Is All You Need
1904.01681 (2019-04)
Augmented Neural ODEs
and 55 more not named here
Embedding 29 other papers
23 dated earlier, 6 later
1904.01681 (2019-04)
Augmented Neural ODEs
1906.12183 (2019-06)
Neural ODEs as the Deep Limit of ResNets with constant weights
2002.03184 (2020-02)
Time-aware Large Kernel Convolutions
and 26 more not named here
is_master 18 other papers
14 dated earlier, 4 later
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
1902.01388 (2019-02)
Re-examination of the Role of Latent Variables in Sequence Modeling
2004.14524 (2020-04)
Simulated Multiple Reference Training Improves Low-Resource Machine Translation
and 15 more not named here
all_reduce 16 other papers
11 dated earlier, 5 later
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
2021.findings-emnlp.366 (2021 (year only))
Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables
2104.08771 (2021-04)
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation
and 13 more not named here
distributed_init 6 other papers
5 dated earlier, 1 later
1610.02424 (2016-10)
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
2021.findings-emnlp.366 (2021 (year only))
Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables
2104.08771 (2021-04)
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation
and 3 more not named here

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

Human experts write summaries using different techniques, including extracting a sentence from the document and rewriting it, or fusing various information from the document to abstract it. These techniques are flexible and thus difficult to be imitated by any single method. To address this issue, we propose an adaptive model, GEMINI, that integrates a rewriter and a generator to mimic the sentence rewriting and abstracting techniques, respectively. GEMINI adaptively chooses to rewrite a specific document sentence or generate a summary sentence from scratch. Experiments demonstrate that our adaptive approach outperforms the pure abstractive and rewriting baselines on three benchmark datasets, achieving the best results on WikiHow. Interestingly, empirical results show that the human summary styles of summary sentences are consistently predictable given their context. We release our code and model at https: //github.com/baoguangsheng/gemini.

For agents

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

get_harvested_code_for_paper("2304.03548")
get_code_for_paper("2304.03548")
have("2304.03548")

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

curl https://syntology.ai/api/ran/2304.03548.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.03548.svg)](https://syntology.ai/paper/2304.03548)

Connect an agent — have() is free.