Pith Number

pith:4PVIJ5BD

pith:2026:4PVIJ5BDVYBBNT5MLCH7OH3CU7

not attested not anchored not stored refs resolved

VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool Use

Juan S. Santillana

A 42M-parameter Spanish cybersecurity model reaches 0.78 conversational performance with native tool use after curriculum training on a 170M-token corpus.

arxiv:2605.13989 v1 · 2026-05-13 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{4PVIJ5BDVYBBNT5MLCH7OH3CU7}

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

After SFT on OASST-ES, Alpaca-ES, CVE Q&A, and 6,327 tool-use traces, the model attains a conversational gate of 0.78+-0.05 (N=4 seeds); a tool-dense corpus raises B4 to 0.145+-0.046 on the 42M model.

C2weakest assumption

That the custom conversational gate metric and B4 tool-selection benchmark accurately reflect practical cybersecurity utility and that the eight-VM corpus pipeline produces representative, high-quality Spanish security text without major domain gaps.

C3one line summary

VectraYX-Nano is a 42M-parameter Spanish cybersecurity LLM trained with curriculum learning and native MCP tool use, achieving 0.78 conversational gate and improved tool selection with denser data.

References

60 extracted · 60 resolved · 11 Pith anchors

[1] Ehsan Aghaei, Xi Niu, Waseem Shadid, and Ehab Al-Shaer. 2022. Secure- BERT: A Domain-Specific Language Model for Cybersecurity.arXiv preprint arXiv:2204.02685(2022) 2022

[2] Joshua Ainslie, James Lee-Thorp, Michiel de Jong, Yury Zemlyanskiy, Federico Lebrón, and Sumit Sanghai. 2023. GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints. InPr 2023

[3] SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model 2025 · arXiv:2502.02737

[4] Anthropic. 2024. Introducing the Model Context Protocol. https://www.anthropic. com/news/model-context-protocol. Accessed: 2026-05-08 2024

[5] AI at Meta. 2024. The Llama 3 Herd of Models. https://ai.meta.com/blog/meta- llama-3/.Meta AI(2024) 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:13.274703Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e3ea84f423ae0216cfac588ff71f62a7faed8f894dfc8c0d1b156a26487c5720

Aliases

arxiv: 2605.13989 · arxiv_version: 2605.13989v1 · doi: 10.48550/arxiv.2605.13989 · pith_short_12: 4PVIJ5BDVYBB · pith_short_16: 4PVIJ5BDVYBBNT5M · pith_short_8: 4PVIJ5BD

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/4PVIJ5BDVYBBNT5MLCH7OH3CU7 \
  | 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: e3ea84f423ae0216cfac588ff71f62a7faed8f894dfc8c0d1b156a26487c5720

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "959856d7d627d1b9f3ed6e0cbccbf16a23d1934d6dcaae2b1d92d77d7c9372e6",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T18:03:07Z",
    "title_canon_sha256": "cc04eae20381c3ca7218ca6c8462ab59e2235b268f6efd17f5025676ea99763f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13989",
    "kind": "arxiv",
    "version": 1
  }
}