pith. sign in
Pith Number

pith:GJ2S7I7Q

pith:2026:GJ2S7I7QZ3JEO3JJCGKNGZ3THD
not attested not anchored not stored refs resolved

Bridging the Rural Healthcare Gap: A Cascaded Edge-Cloud Architecture for Automated Retinal Screening

Nishi Doshi, Shrey Shah

An edge-cloud cascade cuts cloud calls for diabetic retinopathy screening by half with near-identical accuracy to full cloud processing.

arxiv:2605.14108 v1 · 2026-05-13 · cs.CV · cs.AI · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{GJ2S7I7QZ3JEO3JJCGKNGZ3THD}

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

On a stratified APTOS test split of 733 images, Tier 1 reaches 98.99% sensitivity and 84.37% specificity; the cascade forwards 49.52% of images to Tier 2, reducing cloud calls by 50.48%, and obtains 80.49% accuracy and 0.8167 quadratic weighted kappa versus 80.76% and 0.8184 for cloud-only.

C2weakest assumption

The validation-tuned high-sensitivity threshold for Tier 1 triage will maintain reliable performance and not miss referable cases when applied to real-world images from diverse populations, cameras, and lighting conditions outside the APTOS dataset.

C3one line summary

A cascaded edge-cloud architecture for diabetic retinopathy screening uses local triage to cut cloud calls by 50% with only a minor drop in grading performance on the APTOS 2019 dataset.

References

18 extracted · 18 resolved · 0 Pith anchors

[1] Global prevalence of diabetic retinopathy and projection of burden through 2045: Systematic review and meta-analysis 2045
[2] Contrastive learning-based pretrain- ing improves representation and transferability of diabetic retinopathy classification models, 2023
[3] GBD 2019 Blindness and Vision Impairment Collaborators and Vision Loss Expert Group of the Global Burden of Disease Study, “Causes of blindness and vision impairment in 2020 and trends over 30 years, 2019
[4] Global strategy on human resources for health: Workforce 2030 – a five-year check-in, 2030
[5] Barriers to digital health im- plementation in low- and middle-income countries: a narrative review, 2026
Receipt and verification
First computed 2026-05-17T23:39:12.029791Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

32752fa3f0ced2476d291194d3677338de1b91d9af5c0569bd42701747f3ca91

Aliases

arxiv: 2605.14108 · arxiv_version: 2605.14108v1 · doi: 10.48550/arxiv.2605.14108 · pith_short_12: GJ2S7I7QZ3JE · pith_short_16: GJ2S7I7QZ3JEO3JJ · pith_short_8: GJ2S7I7Q
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/GJ2S7I7QZ3JEO3JJCGKNGZ3THD \
  | 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: 32752fa3f0ced2476d291194d3677338de1b91d9af5c0569bd42701747f3ca91
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "5f4becdfd7f8a3c3e92a6c4cf9810603481465235bea0a6429ab06860e1a5ef1",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T20:47:16Z",
    "title_canon_sha256": "6a6221b5b336ccdbeb55cd2e46f1ae1b3ccbc8d97b15ae90fdc9bc31ae7e1fcb"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14108",
    "kind": "arxiv",
    "version": 1
  }
}