Pith Number

pith:VT6CMHEO

pith:2026:VT6CMHEOWGHKIVKRUZL4J73HC2

not attested not anchored not stored refs resolved

Learning Selective Merge Policies for Deadline-Constrained Coded Caching via Deep Reinforcement Learning

Amirhossein Yousefiramandi

A graph-attention policy network trained by reinforcement learning learns selective merge decisions that cut packet expiration rates by 40.9 percent in deadline-constrained coded caching.

arxiv:2605.15236 v1 · 2026-05-13 · cs.IT · cs.AI · cs.NI · math.IT

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VT6CMHEOWGHKIVKRUZL4J73HC2}

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 policy network reduces the broadcast-packet expiration ratio ρ by 40.9% (0.208 vs. 0.352) with respect to the best coded multi-casting baseline (SACM++) on the uniform-demand benchmark, while also attaining the best broadcast-efficiency score σ across the Track A battery among the coded multi-casting methods.

C2weakest assumption

The simulator used for training and evaluation accurately captures the real-world trade-offs between current multicast opportunities and future deadline violations in coded caching systems (abstract states the formulation as a masked discrete-action queue-state control problem without providing validation against live networks).

C3one line summary

A DRL policy with graph attention learns selective merging for deadline-constrained coded caching, cutting packet expiration ratio by 40.9% versus SACM++ while merging only about 32% of the time.

References

32 extracted · 32 resolved · 5 Pith anchors

[1] Ericsson mobility report, June 2024, 2024

[2] Mobile edge caching: A survey, 2018

[3] Fundamental limits of caching, 2014

[4] Decentralized coded caching attains order-optimal memory-rate tradeoff, 2015

[5] Coded Caching for Delay-Sensitive Content 2014 · arXiv:1407.4489

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:47.756420Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

acfc261c8eb18ea45551a657c4ff6716ba0366b7560544c44e538ae9889ea187

Aliases

arxiv: 2605.15236 · arxiv_version: 2605.15236v1 · doi: 10.48550/arxiv.2605.15236 · pith_short_12: VT6CMHEOWGHK · pith_short_16: VT6CMHEOWGHKIVKR · pith_short_8: VT6CMHEO

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/VT6CMHEOWGHKIVKRUZL4J73HC2 \
  | 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: acfc261c8eb18ea45551a657c4ff6716ba0366b7560544c44e538ae9889ea187

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "15f71ba89defafc43243ae46b193f3a8d6d00c854c2c570e1e26bc8784848cf7",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.NI",
      "math.IT"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.IT",
    "submitted_at": "2026-05-13T22:18:30Z",
    "title_canon_sha256": "4e96b49917f6fe8d1ed25ea62b6a3b1d687df8424e9129b766b4a8e27b8a6faa"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15236",
    "kind": "arxiv",
    "version": 1
  }
}