SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.09318 · NeurIPS · 2022

DataMUX: Data Multiplexing for Neural Networks

Karthik Narasimhan, Vishvak Murahari, Carlos Jimenez, Runzhe Yang

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 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/2202.09318.json · badge: /api/ran/2202.09318.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
princeton-nlp/datamux marked official in Papers with Code
Papers with Code archive
8 ran · 1 no recorded run
FunctionStatusWhere it lives
RetrievalHeadIndexDemultiplexing Ran
ran on a synthesized input
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("4573eece1b643ae9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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.

RetrievalHeadMLPDemultiplexing Ran
ran on a synthesized input
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("1f9ba0adc7fd6702")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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.

RobertaIndexDemultiplexerSequenceClassification Ran
ran on a synthesized input
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("546ff05a58f372a4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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.

RobertaMLPDemultiplexerSequenceClassification Ran
ran on a synthesized input · constructed an object; no result was computed
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("807966683fd8b592")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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.

RobertaMLPDemuxModule Ran
ran on a synthesized input · constructed an object; no result was computed
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("cfe0543d2ad4dc5f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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.

SequenceClassifierOutputMuxed Ran
ran on a synthesized input · constructed an object; no result was computed
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("165182edd4643caa")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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.

binary_encoding Ran
ran, honoured the contract we drafted
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("181f1d62d685220a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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.

random_encoding Ran
ran, honoured the contract we drafted
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("8e9f043a6aacef9a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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.

RobertaSequenceClassificationMuxed Not yet run
unverified (harvested, no recorded run)
princeton-nlp/datamux/models/multiplexing.py
pointer only (licence: NOASSERTION) · get_code("8a784cafcc4e2bf4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, princeton-nlp/datamux (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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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 paper, we introduce data multiplexing (DataMUX), a technique that enables deep neural networks to process multiple inputs simultaneously using a single compact representation. DataMUX demonstrates that neural networks are capable of generating accurate predictions over mixtures of inputs, resulting in increased inference throughput with minimal extra memory requirements. Our approach uses two key components -1) a multiplexing layer that performs a fixed linear transformation to each input before combining them to create a 'mixed' representation of the same size as a single input, which is then processed by the base network, and 2) a demultiplexing layer that converts the base network's output back into independent representations before producing predictions for each input. We show the viability of DataMUX for different architectures (Transformers, and to a much lesser extent MLPs and CNNs) across six different tasks spanning sentence classification, named entity recognition and image classification. For instance, DataMUX for Transformers can multiplex up to 20x/40x inputs, achieving up to 11x/18x increase in inference throughput with absolute performance drops of < 2% and < 4% respectively compared to a vanilla Transformer on MNLI, a natural language inference task. We also provide a theoretical construction for multiplexing in self-attention networks and analyze the effect of various design elements in DataMUX. 1

For agents

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

get_harvested_code_for_paper("2202.09318")
get_code_for_paper("2202.09318")
have("2202.09318")

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

curl https://syntology.ai/api/ran/2202.09318.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.09318.svg)](https://syntology.ai/paper/2202.09318)

Connect an agent — have() is free.