pith. sign in
Pith Number

pith:MRDE3URM

pith:2026:MRDE3URMMZL5SLNDRTYNKK42S4
not attested not anchored not stored refs resolved

S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning

Said Slaoui

Reasoning emerges from iterative hormonal feedback in small AI models rather than from wide feed-forward layers.

arxiv:2605.13872 v1 · 2026-05-05 · cs.NE · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{MRDE3URMMZL5SLNDRTYNKK42S4}

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

Experimental validation on the SAI-UT+ testbench demonstrates that S-AI-Recursive achieves competitive reasoning performance on abstract and symbolic benchmarks with fewer than ten million parameters, confirming the central principle of temporal parsimony: iterative cognitive depth substitutes for architectural width.

C2weakest assumption

The assumption that the newly introduced hormones Clarifine and Confusionin, together with the recursive state dynamics, produce genuine iterative refinement and Lyapunov-stable convergence on real reasoning tasks rather than on the specific SAI-UT+ benchmarks alone.

C3one line summary

S-AI-Recursive operationalizes reasoning as a closed-loop hormonal iteration with Clarifine and Confusionin to reach stable equilibrium, achieving competitive benchmark performance with under 10 million parameters via temporal depth instead of width.

References

49 extracted · 49 resolved · 3 Pith anchors

[1] S-AI: A sparse artificial intelligence system orchestrated by a hormonal MetaAgent and context-aware specialized agents, 2025
[2] From Hormones to Probabilities: A Unified Doctrine of Cognitive Homeostasis in Sparse Artificial Intelligence, 2025 · doi:10.2139/ssrn.5735582
[3] S-AI-IoT: Formal Agent Specification, Mathematical Modeling, and Stability Analysis of the Hormonal Orchestration Framework,
[4] Attention is all you need, 2017
[5] Language models are few- shot learners, 1901

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-17T23:39:19.307191Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

64464dd22c6657d92da38cf0d52b9a9718db5009e4b17a06e9597d367ef722b1

Aliases

arxiv: 2605.13872 · arxiv_version: 2605.13872v1 · doi: 10.48550/arxiv.2605.13872 · pith_short_12: MRDE3URMMZL5 · pith_short_16: MRDE3URMMZL5SLND · pith_short_8: MRDE3URM
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4 \
  | 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: 64464dd22c6657d92da38cf0d52b9a9718db5009e4b17a06e9597d367ef722b1
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "84dfc896efb87d441c25a3c97c8734af1ce8bc95fe026de8944834282de79590",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.NE",
    "submitted_at": "2026-05-05T20:50:29Z",
    "title_canon_sha256": "e2e699982d7b520709ca44469398fbed35177eb2a17a4f8c20291c24455d1065"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13872",
    "kind": "arxiv",
    "version": 1
  }
}