Pith Number

pith:24LU7BDE

pith:2026:24LU7BDEXJAHPZ7YK5SPGXYSK4

not attested not anchored not stored refs resolved

It's not the Language Model, it's the Tool: Deterministic Mediation for Scientific Workflows

Danae Katrisioti, Emmanuel Stratakis, Marios Adamidis, Yannis Tzitzikas

Language models achieve identical scientific analysis results every time by calling fixed deterministic tools rather than generating code.

arxiv:2605.13245 v1 · 2026-05-13 · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{24LU7BDEXJAHPZ7YK5SPGXYSK4}

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 typed tool produces identical results across all runs. The commercial platforms either vary in numerical output and analytical methodology across runs, or fail to produce valid results on the task.

C2weakest assumption

That a researcher's exact analytical procedure for a given instrument can be fully captured as a deterministic tool through structured interviews, without loss of nuance or need for ongoing human judgment.

C3one line summary

Typed mediation lets LLMs orchestrate fixed deterministic tools for scientific workflows, producing identical analysis outputs across runs where direct LLM generation varies.

References

24 extracted · 24 resolved · 0 Pith anchors

[1] Defeating nondeterminism in LLM inference, September 2025 2025

[2] Measuring AI agent autonomy in practice, February 2026 2026

[3] John R. Kitchin. The evolving role of programming and LLMs in the development of self-driving laboratories.APL Machine Learning, 3(2):026111, 2025 2025

[4] Leak, cheat, repeat: Data contamination and evaluation malpractices in closed-source LLMs 2024

[5] Leemann, Antonin Sulc, and Marco Venturini 2025

Receipt and verification

First computed	2026-05-18T02:44:49.471948Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d7174f8464ba4077e7f85764f35f12572b49440ef8c8bf59e2a9593d8d625ac7

Aliases

arxiv: 2605.13245 · arxiv_version: 2605.13245v1 · doi: 10.48550/arxiv.2605.13245 · pith_short_12: 24LU7BDEXJAH · pith_short_16: 24LU7BDEXJAHPZ7Y · pith_short_8: 24LU7BDE

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/24LU7BDEXJAHPZ7YK5SPGXYSK4 \
  | 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: d7174f8464ba4077e7f85764f35f12572b49440ef8c8bf59e2a9593d8d625ac7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e5523be2341fc8483708e9c567e797f5b7198cab93fc02306b5706338ce82398",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T09:30:56Z",
    "title_canon_sha256": "45d9594ca99e8d5f4a3d67c360e4a42fb169774ce394c842130f0680269ae33b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13245",
    "kind": "arxiv",
    "version": 1
  }
}