Pith Number

pith:UE5VBB4P

pith:2022:UE5VBB4PDTZCIIKHQ3JQNGQNUS

not attested not anchored not stored refs resolved

Simplified State Space Layers for Sequence Modeling

Andrew Warrington, Jimmy T.H. Smith, Scott W. Linderman

S5 uses one multi-input multi-output state space model to match S4 performance and efficiency on long sequences

arxiv:2208.04933 v3 · 2022-08-09 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UE5VBB4PDTZCIIKHQ3JQNGQNUS}

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

S5 averages 87.4% on the long range arena benchmark, and 98.5% on the most difficult Path-X task, while matching the computational efficiency of S4.

C2weakest assumption

That the initialization and parameterization obtained by connecting S5 to S4 will produce stable, high-performing models across tasks without additional per-task tuning or post-hoc adjustments.

C3one line summary

S5 uses a single MIMO state space model with S4-derived initialization to match S4 efficiency and reach 87.4% average accuracy on the Long Range Arena benchmark.

References

149 extracted · 149 resolved · 6 Pith anchors

[1] Advances in Neural Information Processing Systems , year=

[2] Voelker, Aaron and Kaji. Legendre. Advances in Neural Information Processing Systems , volume=

[3] Goel, Karan and Gu, Albert and Donahue, Chris and Re, Christopher , booktitle =. It’s Raw!. 2022 , volume = 2022

[4] Gu, Albert and Dao, Tri and Ermon, Stefano and Rudra, Atri and R. Hi. Advances in Neural Information Processing Systems , volume=

[5] 2020 , copyright = 2020 · doi:10.48550/arxiv.2006.03274

Formal links

3 machine-checked theorem links

Cited by

31 papers in Pith

3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion

EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond

L2RU: a Structured State Space Model with prescribed L2-bound

Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba

Exact expression for maximum Lyapunov exponent during transients in computationally powerful dynamical networks

Receipt and verification

First computed	2026-05-17T23:38:48.531338Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a13b50878f1cf224214786d3069a0da48079ab3f804d1f329f053962b4124946

Aliases

arxiv: 2208.04933 · arxiv_version: 2208.04933v3 · doi: 10.48550/arxiv.2208.04933 · pith_short_12: UE5VBB4PDTZC · pith_short_16: UE5VBB4PDTZCIIKH · pith_short_8: UE5VBB4P

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/UE5VBB4PDTZCIIKHQ3JQNGQNUS \
  | 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: a13b50878f1cf224214786d3069a0da48079ab3f804d1f329f053962b4124946

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c860adae180ffe3f0a2fa9861d88e17270de679593db299799e028cac402c806",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2022-08-09T17:57:43Z",
    "title_canon_sha256": "d9d336309075397c0e854e1e82fa03d3b50fef0684cd6beda25e9c71242dc572"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2208.04933",
    "kind": "arxiv",
    "version": 3
  }
}