Pith Number

pith:66ZBTXSN

pith:2026:66ZBTXSNP3CVZD6QIN2YC4IM6J

not attested not anchored not stored refs resolved

Time-Varying Deep State Space Models for Sequences with Switching Dynamics

Ay\c{c}a \"Oz\c{c}elikkale, Sanja Karilanova, Subhrakanti Dey

Time-varying deep state space models learn switching dynamics via a dictionary of time-evolving basis functions and outperform time-invariant models on synthetic and audio tasks.

arxiv:2605.15311 v1 · 2026-05-14 · cs.LG · cs.SY · eess.SY

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{66ZBTXSNP3CVZD6QIN2YC4IM6J}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

The proposed time-varying model consistently outperforms its time-invariant counterparts while maintaining comparable computational complexity on both synthetic switching systems and a speech denoising task with real audio corrupted by switching dynamics noise.

C2weakest assumption

That the time-varying dynamics present in the target sequences can be adequately represented and learned through a fixed dictionary of basis functions in which each basis evolves differently over time, without requiring additional mechanisms for detecting or modeling the switches explicitly.

C3one line summary

A class of time-varying deep state-space model neural networks is proposed that learns dynamics via a dictionary of basis functions evolving differently over time, outperforming time-invariant versions on switching synthetic data and speech denoising.

References

54 extracted · 54 resolved · 1 Pith anchors

[1] SEFRON: A New Spiking Neuron Model With Time-Varying Synaptic Efficacy Function for Pattern Classification , year=

[2] 2021 , issn = 2021

[3] Deep explicit duration switching models for time series , author=. NeurIPS , volume=

[4] Switching dynamical systems with deep neural networks , author=. ICPR , pages=. 2020 , organization= 2020

[5] 2025 , issn = 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:52.033889Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f7b219de4d7ec55c8fd0437581710cf246837857d90d9e65e6e31220f55fef7c

Aliases

arxiv: 2605.15311 · arxiv_version: 2605.15311v1 · doi: 10.48550/arxiv.2605.15311 · pith_short_12: 66ZBTXSNP3CV · pith_short_16: 66ZBTXSNP3CVZD6Q · pith_short_8: 66ZBTXSN

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/66ZBTXSNP3CVZD6QIN2YC4IM6J \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: f7b219de4d7ec55c8fd0437581710cf246837857d90d9e65e6e31220f55fef7c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8c650d6343d8767a3deffd7bdc0bd388227fb0e313a7e113e8e018d74a5f4a79",
    "cross_cats_sorted": [
      "cs.SY",
      "eess.SY"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T18:25:04Z",
    "title_canon_sha256": "f875bbb9e403c5a82e753b6fae29ae412f21f244d1592469dcd4078c1b493387"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15311",
    "kind": "arxiv",
    "version": 1
  }
}