SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.30120 · ICML · 2026

No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval

Stefanie Jegelka, Yifei Wang, Chenyu You, Aosong Feng, Tiansheng Wen, Lixuan Guo

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/2605.30120.json · badge: /api/ran/2605.30120.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/SSR community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
SparseAutoencoderCore Ran
ran on a synthesized input · constructed an object; no result was computed
Y-Research-SBU/SSR/ssr/sparse_autoencoder.py
code served (permissive licence) · get_code("58dfd4ad1a03e68d")
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, SparseAutoencoderCore: 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)

# Define ARGS with all parameters for SparseAutoencoderCore
ARGS = {
    'n_inputs': 4,
    'n_latents': 3,
    'topk': 2,
    'auxk': 1,
    'normalize': False,
    'dead_threshold': 30,
}
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 SparseAutoencoderCore — 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 SparseAutoencoderCore 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/SSR/ssr/sparse_autoencoder.py
code served (permissive licence) · get_code("97d3ea8ddd690437")
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 an encoder linear layer with no bias
# Input features: 4, output features: 3
encoder_linear = nn.Linear(in_features=4, out_features=3, bias=False)

# ARGS dict mapping parameter names to values
ARGS = {
    "linear": encoder_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

Retrieval performance and efficiency across MVR models (b) Comparison between three paradigms Token Dim Embed Dim … Token Dim … Dense Encoder Sparse Encoder … … … … MaxSim + Score i d=1 i d=2 i d=3 i d=4 Score Dense MVR Sparse MVR document query (a) Overview of dense and sparse MVR paradigm Figure 1. Single-stage Sparse Retrieval (SSR). (a) Paradigm Comparison. Unlike dense MVR, which compresses embeddings into low-dimensional vectors and requires exhaustive token-pair computations, our sparse MVR projects features into a high-dimensional sparse space via Sparse Autoencoders (SAE). This enables efficient interaction calculation solely on overlapping activated neurons. (b) Trade-off Analysis. Single Vector Retrieval offers high efficiency but suffers from semantic compression loss. Dense MVR preserves token-level details but incurs heavy computational overheads due to clustering and multi-stage pruning (inefficient indexing). SSR bridges this gap, accelerating retrieval via natural inverted indexing while retaining fine-grained semantic information. (c) Performance vs. Efficiency. SSR achieves state-of-the-art retrieval performance with halved retrieval latency compared to competitive baselines. Notably, it delivers a 15x reduction in indexing time (indicated by bubble size) by eliminating the clustering bottleneck.

For agents

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

get_harvested_code_for_paper("2605.30120")
get_code_for_paper("2605.30120")
have("2605.30120")

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

curl https://syntology.ai/api/ran/2605.30120.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.30120.svg)](https://syntology.ai/paper/2605.30120)

Connect an agent — have() is free.