Pith Number

pith:UHFUBLEU

pith:2026:UHFUBLEU5GUIXVDNV3JDJINZ22

not attested not anchored not stored refs resolved

PRB-RUPFormer: A Recursive Unified Probabilistic Transformer for Residual PRB Forecasting

Ajay Rajkumar, Ismail Guvenc, Matti Hiltunen, Saad Masrur, Yuxuan Jiang

A single shared probabilistic Transformer trained across carriers forecasts residual PRBs with median error below 0.05 for one- and seven-day horizons.

arxiv:2605.15363 v1 · 2026-05-14 · cs.LG · eess.SP

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UHFUBLEU5GUIXVDNV3JDJINZ22}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

Evaluations on six months of commercial LTE network data from multiple U.S. locations demonstrate median MAE below 0.05 and hit probabilities above 0.80 for both one-day and seven-day recursive forecasts.

C2weakest assumption

The assumption that a single shared model trained across all carriers and sectors can capture cross-carrier dependencies without site-specific overfitting or loss of local accuracy, as stated in the description of the unified training approach.

C3one line summary

PRB-RUPFormer delivers recursive probabilistic forecasts of residual PRBs with median MAE below 0.05 and hit rates above 0.80 using a single shared model across carriers on real LTE data.

References

13 extracted · 13 resolved · 0 Pith anchors

[1] An overview of dynamic spectrum sharing: Ongoing initiatives, challenges, and a roadmap for future research, 2016

[2] Understand- ing O-RAN: Architecture, interfaces, algorithms, security, and research challenges, 2023

[3] Data-driven energy conservation in cellular networks: A systems approach, 2021

[4] Network downlink PRB utilization rate forecasting and evaluation method based on multi-feature construction, 2023

[5] Downlink throughput pre- diction in LTE cellular networks using time series forecasting, 2022

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:54.521846Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a1cb40ac94e9a88bd46daed234a1b9d680482a72b31c167bc49adae5484f4fc5

Aliases

arxiv: 2605.15363 · arxiv_version: 2605.15363v1 · doi: 10.48550/arxiv.2605.15363 · pith_short_12: UHFUBLEU5GUI · pith_short_16: UHFUBLEU5GUIXVDN · pith_short_8: UHFUBLEU

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/UHFUBLEU5GUIXVDNV3JDJINZ22 \
  | 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: a1cb40ac94e9a88bd46daed234a1b9d680482a72b31c167bc49adae5484f4fc5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "472e9d1108cf064b696ef3358cb447308d655cb1826b5ea689bb042137c9bd78",
    "cross_cats_sorted": [
      "eess.SP"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T19:42:32Z",
    "title_canon_sha256": "eaf5ae96ac9bb3bd05dafdb49e953ab121afba93aabc104fb12c3e2f231dbb32"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15363",
    "kind": "arxiv",
    "version": 1
  }
}