SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.10487 · 2024

Generative Dense Retrieval: Memory Can Be a Burden

arXiv · PDF · Open in the Atlas

Code that ran

16 of 19 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; 6 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 3 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 2026-11-22; 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/2401.10487.json · badge: /api/ran/2401.10487.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
ypw0102/gdr canonical (classifier label)
classifier basis: census
16 ran · 3 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/transformers/activations.py
pointer only (licence: NONE) · get_code("0f786c407fb1ee4c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

E_CL Ran
ran, honoured the contract we drafted
ypw0102/gdr/GDR_model/main_helper_loss.py
pointer only (licence: NONE) · get_code("f9be524a39f343b5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

E_Reg_loss Ran
ran, honoured the contract we drafted
ypw0102/gdr/GDR_model/main_helper_loss.py
pointer only (licence: NONE) · get_code("f4d5ea96900f4114")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

doc_reweight_loss Ran
ran, honoured the contract we drafted
ypw0102/gdr/GDR_model/main_helper_loss.py
pointer only (licence: NONE) · get_code("c90481d879d6e74f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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 Ran
ran, honoured the contract we drafted
ypw0102/gdr/GDR_model/transformers/activations_tf.py
pointer only (licence: NONE) · get_code("14a1c81ea568d152")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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
ypw0102/gdr/GDR_model/transformers/activations.py
pointer only (licence: NONE) · get_code("a4475703ff58ecf9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/transformers/activations.py
pointer only (licence: NONE) · get_code("aef07bb1e2787431")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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
ypw0102/gdr/GDR_model/transformers/activations_tf.py
pointer only (licence: NONE) · get_code("13718ddda6b66f8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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_ckpt Ran
ran; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/main_utils.py
pointer only (licence: NONE) · get_code("923d19a187027958")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

grad_status Ran
ran; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/main_utils.py
pointer only (licence: NONE) · get_code("4ed3a54ebfd50cc5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

lmap Ran
ran; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/main_utils.py
pointer only (licence: NONE) · get_code("64e8746cf3f62e8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

load_candidate_from_stream Ran
ran; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/main_metrics.py
pointer only (licence: NONE) · get_code("a4d8ea61b62189e8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

load_reference Ran
ran; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/main_metrics.py
pointer only (licence: NONE) · get_code("b75e94e5d0c04ad5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

load_reference_from_stream Ran
ran; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/main_metrics.py
pointer only (licence: NONE) · get_code("e99a1fef3b9d445c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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
ypw0102/gdr/GDR_model/transformers/activations_tf.py
pointer only (licence: NONE); 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: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

simple_tok Ran
ran; our contract draft was wrong, not the code
ypw0102/gdr/GDR_model/bm25_preprocess.py
pointer only (licence: NONE) · get_code("1713558286ecf0e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

build_or_load_embedding_tree Not yet run
unverified (harvested, no recorded run)
ypw0102/gdr/GDR_model/main_models.py
pointer only (licence: NONE) · get_code("e79bfbea5d698632")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

load_embedding Not yet run
unverified (harvested, no recorded run)
ypw0102/gdr/GDR_model/main_models.py
pointer only (licence: NONE) · get_code("da402819a398f4a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

tree_embedding_calculate Not yet run
unverified (harvested, no recorded run)
ypw0102/gdr/GDR_model/main_models.py
pointer only (licence: NONE) · get_code("097315a106ec7d48")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ypw0102/gdr 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.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 1 the same month, 6 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
swish 206 other papers
171 dated earlier, 4 the same month, 27 later, 4 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
16 dated earlier, 8 later, 1 same year, order not determinable
2007.07779 (2020-07)
AdapterHub: A Framework for Adapting Transformers
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2106.00420 (2021-06)
Dialogue-oriented Pre-training
and 22 more not named here
gelu_new 24 other papers
19 dated earlier, 5 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
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
and 21 more not named here
gelu_fast 22 other papers
17 dated earlier, 5 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
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
and 19 more not named here
gelu 3 other papers
2 dated earlier, 1 later
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2106.00420 (2021-06)
Dialogue-oriented Pre-training
2406.10960 (2024-06)
ESCoT: Towards Interpretable Emotional Support Dialogue Systems
gelu_new 3 other papers
2 dated earlier, 1 later
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2106.00420 (2021-06)
Dialogue-oriented Pre-training
2406.10960 (2024-06)
ESCoT: Towards Interpretable Emotional Support Dialogue Systems
lmap 2 other papers
2 dated earlier
2108.02866 (2021-08)
Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering
2109.04096 (2021-09)
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR implicitly achieves deep interaction between query and document. However, such a memorizing mechanism faces three drawbacks: (1) Poor memory accuracy for fine-grained features of documents; (2) Memory confusion gets worse as the corpus size increases; (3) Huge memory update costs for new documents. To alleviate these problems, we propose the Generative Dense Retrieval (GDR) paradigm. Specifically, GDR first uses the limited memory volume to achieve inter-cluster matching from query to relevant document clusters. Memorizing-free matching mechanism from Dense Retrieval (DR) is then introduced to conduct fine-grained intra-cluster matching from clusters to relevant documents. The coarse-to-fine process maximizes the advantages of GR's deep interaction and DR's scalability. Besides, we design a cluster identifier constructing strategy to facilitate corpus memory and a cluster-adaptive negative sampling strategy to enhance the intra-cluster mapping ability. Empirical results show that GDR obtains an average of 3.0 R@100 improvement on NQ dataset under multiple settings and has better scalability.

For agents

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

get_harvested_code_for_paper("2401.10487")
get_code_for_paper("2401.10487")
have("2401.10487")

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

curl https://syntology.ai/api/ran/2401.10487.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.10487.svg)](https://syntology.ai/paper/2401.10487)

Connect an agent — have() is free.