Pith Number

pith:LGXGNG4S

pith:2026:LGXGNG4SNSXU7ZUSQBC7S37F2D

not attested not anchored not stored refs resolved

Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence

Mashrekur Rahman

A fleet of five small specialized foundation models routed by an LLM improves hydrologic reasoning over a single generalist model.

arxiv:2605.14120 v1 · 2026-05-13 · cs.LG · cs.CL

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

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

In paired LLM-as-Judge evaluation, dual retrieval over AlphaEarth and the routed fleet outperforms AlphaEarth alone on physics-matched questions (Cohen's d = 1.10, p = 0.031).

C2weakest assumption

That the five Mini-JEPA manifolds capture hydrologic signals genuinely absent from AlphaEarth and that the router LLM's perfect hit rate on the curated question set will hold for real user queries outside the test distribution.

C3one line summary

A fleet of sensor-specialized 22M-parameter JEPA models routed by an LLM improves LLM-as-judge scores on hydrologic questions over AlphaEarth alone with Cohen's d of 1.10.

References

30 extracted · 30 resolved · 1 Pith anchors

[1] AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data 2025 · arXiv:2507.22291

[2] Bruinsma, Ana Lucic, Megan Stanley, Anna Allen, Johannes Brandstetter, Patrick Garvan, Maik Riechert, Jonathan A 2025 · doi:10.1038/s41586-025-09005-y

[3] Foundation models for generalist geospatial artificial intelligence 2023

[4] A. Xiao, W. Xuan, J. Wang, J. Huang, D. Tao, S. Lu, N. Yokoya, Foundation models for remote sensing and earth observation: A survey, IEEE Geoscience and Remote Sensing Magazine (2025) 2025

[5] On the opportunities and challenges of foundation models for geospatial artificial intelligence 2023

Receipt and verification

First computed	2026-05-17T23:39:11.905033Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

59ae669b926caf4fe6928045f96fe5d0d67cb6b15e4cbc6c1077e9316f8b229d

Aliases

arxiv: 2605.14120 · arxiv_version: 2605.14120v1 · doi: 10.48550/arxiv.2605.14120 · pith_short_12: LGXGNG4SNSXU · pith_short_16: LGXGNG4SNSXU7ZUS · pith_short_8: LGXGNG4S

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/LGXGNG4SNSXU7ZUSQBC7S37F2D \
  | 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: 59ae669b926caf4fe6928045f96fe5d0d67cb6b15e4cbc6c1077e9316f8b229d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ade8fde49fb7ece80554c13675da1ea7c1fe6bde903b0dab5674383cc26aea8b",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T21:11:14Z",
    "title_canon_sha256": "63d3eaa1aff67688201a21e2e89160866d6a927959f158422f7598e99902f47e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14120",
    "kind": "arxiv",
    "version": 1
  }
}