SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.05735 · 2026

MRL Rep. Dense Truncated

Mit, Stefanie Jegelka, Yifei Wang, Chenyu You, Bo Chen, Yifan Wang, Aosong Feng, Tiansheng Wen, Lixuan Guo, Rep Csr, Sparse

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2602.05735.json · badge: /api/ran/2602.05735.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
Y-Research-SBU/CSRv2 community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
CSR Ran
ran on a synthesized input · constructed an object; no result was computed
Y-Research-SBU/CSRv2/text/model_zoo.py
code served (permissive licence) · get_code("fcf9f4cbee54151c")
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 an instance of its own class, CSR: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "n_latents": 8,
    "topk": 3,
    "auxk": 2,
    "normalize": True,
    "n_inputs": 4,
    "dead_threshold": 5,
}
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 CSR — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CSR 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
TiedTranspose Ran
ran on a synthesized input · constructed an object; no result was computed
Y-Research-SBU/CSRv2/text/model_zoo.py
code served (permissive licence) · get_code("964f07f3af34a081")
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 an instance of its own class, TiedTranspose: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn as nn

torch.manual_seed(0)

# Create a linear layer without bias (required by TiedTranspose)
# Input features: 3, Output features: 4
linear = nn.Linear(in_features=3, out_features=4, bias=False)

# ARGS dict mapping all parameters of TiedTranspose.__init__
ARGS = {
    "linear": linear
}
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 TiedTranspose — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TiedTranspose 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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 the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance and overall system capability. Yet widely used dense embeddings are often extremely high-dimensional (e.g., 4096), incurring substantial costs in storage, memory, and inference latency. To address these, Contrastive Sparse Representation (CSR) is recently proposed as a promising direction, mapping dense embeddings into high-dimensional but k-sparse vectors, in contrast to compact dense embeddings such as Matryoshka Representation Learning (MRL). Despite its promise, CSR suffers severe degradation in the ultra-sparse regime (e.g., k ≤ 4), where over 80% of neurons remain inactive, leaving much of its efficiency potential unrealized. In this paper, we introduce CSRv2, a principled training approach designed to make ultrasparse embeddings viable. CSRv2 stabilizes sparsity learning through progressive k-annealing, enhances representational quality via supervised contrastive objectives, and ensures end-to-end adaptability with full backbone finetuning. CSRv2 reduces dead neurons from 80% to 20% and delivers a 14% accuracy gain at k = 2, bringing ultra-sparse embeddings on par with CSR at k = 8 and MRL at 32 dimensions, all with only two active features. While maintaining comparable performance, CSRv2 delivers a 7× speedup over MRL, and yields up to 300× improvements in compute and memory efficiency relative to dense embeddings in e5-mistral-7b-instruct-based text representation. Extensive experiments across text (MTEB, multiple state-of-the-art LLM embeddings (Qwen and e5-Mistral-7B), SPLADEv3, GraphRAG) and vision (ImageNet-1k) demonstrate that CSRv2 makes ultra-sparse embeddings practical without compromising performance, where CSRv2 achieves 7%/4% improvement over CSR when k = 4 and further increases this gap to 14%/6% when k = 2 in text/vision representation. By making extreme sparsity viable, CSRv2 broadens the design space for largescale, real-time, and edge-deployable AI systems where both embedding quality and efficiency are critical. Code is available at https://github.com/Y-Research-SBU/CSRv2.

For agents

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

get_harvested_code_for_paper("2602.05735")
get_code_for_paper("2602.05735")
have("2602.05735")

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

curl https://syntology.ai/api/ran/2602.05735.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.05735.svg)](https://syntology.ai/paper/2602.05735)

Connect an agent — have() is free.