SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.12652 · 2023

REPLUG: Retrieval-Augmented Black-Box Language Models

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 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; 0 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 0 failures of our instrument; 3 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/2301.12652.json · badge: /api/ran/2301.12652.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
intellabs/fastrag community (classifier label)
classifier basis not recorded on the link
10 ran · 3 no recorded run
FunctionStatusWhere it lives
add_timing_to_pipeline Ran
ran on a synthesized input
intellabs/fastrag/fastrag/utils.py
pointer only (licence: Apache-2.0) · get_code("f3305aacfc98aaff")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

adjust_batch Ran
ran on a synthesized input
intellabs/fastrag/fastrag/generators/gaudi_utils.py
pointer only (licence: Apache-2.0) · get_code("22702323a133d7aa")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

clean_for_prompt Ran
ran on a synthesized input
intellabs/fastrag/fastrag/agents/utils.py
pointer only (licence: Apache-2.0) · get_code("a063dd45ba80cda9")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

fastrag_timing Ran
ran on a synthesized input
intellabs/fastrag/fastrag/utils.py
pointer only (licence: Apache-2.0) · get_code("3bd441205b45bf06")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_padded_tensor Ran
ran on a synthesized input
intellabs/fastrag/fastrag/generators/fid_utils.py
pointer only (licence: Apache-2.0) · get_code("392eb8978ee423ad")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_timing_from_pipeline Ran
ran on a synthesized input
intellabs/fastrag/fastrag/utils.py
pointer only (licence: Apache-2.0) · get_code("629184378b16dad0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

load_text Ran
ran on a synthesized input
intellabs/fastrag/fastrag/agents/utils.py
pointer only (licence: Apache-2.0) · get_code("e7bb63793c50dd54")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

setup_device Ran
ran on a synthesized input
intellabs/fastrag/fastrag/generators/gaudi_utils.py
pointer only (licence: Apache-2.0) · get_code("3c215e4cbc96b8b6")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

setup_parser Ran
ran on a synthesized input
intellabs/fastrag/fastrag/generators/gaudi.py
pointer only (licence: Apache-2.0) · get_code("3a98b7557c38ef50")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

wiki_odqa_tasks_encoder Ran
ran on a synthesized input
intellabs/fastrag/fastrag/data_loaders.py
pointer only (licence: Apache-2.0) · get_code("71454965f4141e50")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_torch_compiled_model Not yet run
unverified (harvested, no recorded run)
intellabs/fastrag/fastrag/generators/gaudi_utils.py
pointer only (licence: Apache-2.0) · get_code("9a8ef57d5aeeee0d")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

passages_to_tensors Not yet run
unverified (harvested, no recorded run)
intellabs/fastrag/fastrag/generators/fid_utils.py
pointer only (licence: Apache-2.0) · get_code("b7cb9a8067883d41")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

tokenization_result_to_tensor Not yet run
unverified (harvested, no recorded run)
intellabs/fastrag/fastrag/generators/fid_utils.py
pointer only (licence: Apache-2.0) · get_code("24505d354160b0da")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, intellabs/fastrag, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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

We introduce REPLUG, a retrieval-augmented language modeling framework that treats the language model (LM) as a black box and augments it with a tuneable retrieval model. Unlike prior retrieval-augmented LMs that train language models with special cross attention mechanisms to encode the retrieved text, REPLUG simply prepends retrieved documents to the input for the frozen black-box LM. This simple design can be easily applied to any existing retrieval and language models. Furthermore, we show that the LM can be used to supervise the retrieval model, which can then find documents that help the LM make better predictions. Our experiments demonstrate that REPLUG with the tuned retriever significantly improves the performance of GPT-3 (175B) on language modeling by 6.3%, as well as the performance of Codex on five-shot MMLU by 5.1%.

For agents

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

get_harvested_code_for_paper("2301.12652")
get_code_for_paper("2301.12652")
have("2301.12652")

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

curl https://syntology.ai/api/ran/2301.12652.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.12652.svg)](https://syntology.ai/paper/2301.12652)

Connect an agent — have() is free.