SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.19339 · 2026

Spectral Tempering for Embedding Compression in Dense Passage Retrieval

Panagiotis Eustratiadis, Evangelos Kanoulas, Yongkang Li

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 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/2603.19339.json · badge: /api/ran/2603.19339.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
liyongkang123/SpecTemp community
Papers with Code archive
2 ran · 2 no recorded run
FunctionStatusWhere it lives
calculate_snr_curve Ran
ran; our contract draft was wrong, not the code
liyongkang123/SpecTemp/embedding_transforms/spectemp.py
pointer only (licence: NOASSERTION) · get_code("e1abac48b5fb19c8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, liyongkang123/SpecTemp (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.

l2_normalize_rows Ran
ran, honoured the contract we drafted
liyongkang123/SpecTemp/embedding_transforms/spectemp.py
pointer only (licence: NOASSERTION) · get_code("aa6a9f5019db3d66")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, liyongkang123/SpecTemp (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.

optimal_gamma_by_kneedle Not yet run
unverified (harvested, no recorded run)
liyongkang123/SpecTemp/embedding_transforms/spectemp.py
pointer only (licence: NOASSERTION) · get_code("bd0771e60e5bf982")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, liyongkang123/SpecTemp (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.

unified_spectral_tempering_truncation Not yet run
unverified (harvested, no recorded run)
liyongkang123/SpecTemp/embedding_transforms/spectemp.py
pointer only (licence: NOASSERTION) · get_code("5f7d7a38995c754c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, liyongkang123/SpecTemp (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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Dimensionality reduction is critical for deploying dense retrieval systems at scale, yet mainstream post-hoc methods face a fundamental trade-off: principal component analysis (PCA) preserves dominant variance but underutilizes representational capacity, while whitening enforces isotropy at the cost of amplifying noise in the heavy-tailed eigenspectrum of retrieval embeddings. Intermediate spectral scaling methods unify these extremes by reweighting dimensions with a power coefficient 𝛾, but treat 𝛾 as a fixed hyperparameter that requires task-specific tuning. We show that the optimal scaling strength 𝛾 is not a global constant: it varies systematically with target dimensionality 𝑘 and is governed by the signal-to-noise ratio (SNR) of the retained subspace. Based on this insight, we propose Spectral Tempering (SpecTemp), a learning-free method that derives an adaptive 𝛾 (𝑘) directly from the corpus eigenspectrum using local SNR analysis and knee-point normalization, requiring no labeled data or validation-based search. Extensive experiments demonstrate that Spectral Tempering consistently achieves nearoracle performance relative to grid-searched 𝛾 * (𝑘) while remaining fully learning-free and model-agnostic. Our code is publicly available at https://github.com/liyongkang123/SpecTemp. • Information systems → Retrieval models and ranking; • Computing methodologies → Natural language processing.

For agents

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

get_harvested_code_for_paper("2603.19339")
get_code_for_paper("2603.19339")
have("2603.19339")

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

curl https://syntology.ai/api/ran/2603.19339.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.19339.svg)](https://syntology.ai/paper/2603.19339)

Connect an agent — have() is free.