Pith Number

pith:ZQGNHBEV

pith:2026:ZQGNHBEVNHWKPKEBENVPKHBAIY

not attested not anchored not stored refs resolved

Position: Assistive Agents Need Accessibility Alignment

Changyuan Yan, Jiaming Zhang, Jie Hu, Yu Zheng, Ziqian Wang

Assistive agents for blind and visually impaired users fail systematically unless accessibility alignment is treated as a first-class design objective.

arxiv:2605.13579 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{ZQGNHBEVNHWKPKEBENVPKHBAIY}

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

Assistive agents for Blind and Visually Impaired users require accessibility alignment as a first-class design objective... leading to systematic failures in assistive scenarios that cannot be resolved by model scaling or post-hoc interface adaptations alone.

C2weakest assumption

That the mismatches between sighted design assumptions and BVI constraints identified in the 778 task instances are fundamental and cannot be addressed by scaling, better interfaces, or other non-alignment approaches.

C3one line summary

Assistive agents for BVI users need accessibility alignment as a core design goal, with a proposed lifecycle pipeline, because sighted assumptions cause unfixable failures in verification, risk, and interaction.

References

19 extracted · 19 resolved · 2 Pith anchors

[1] Think global, act local: Dual-scale graph transformer for vision-and-language navigation

[2] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems · arXiv:2508.07407

[3] From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review · arXiv:2504.19678

[4] Can chatgpt assist visually impaired people with micro-navigation?arXiv preprint arXiv:2408.08321,

[5] Sub- instruction aware vision-and-language navigation 2020

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:23.255917Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cc0cd3849569eca7a881236af51c20461ba3361a2b60fe4e56821e0711a25d41

Aliases

arxiv: 2605.13579 · arxiv_version: 2605.13579v1 · doi: 10.48550/arxiv.2605.13579 · pith_short_12: ZQGNHBEVNHWK · pith_short_16: ZQGNHBEVNHWKPKEB · pith_short_8: ZQGNHBEV

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/ZQGNHBEVNHWKPKEBENVPKHBAIY \
  | 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: cc0cd3849569eca7a881236af51c20461ba3361a2b60fe4e56821e0711a25d41

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c9a8153681be6c9946aa318192f7aaa6b58c08894d23608fca74ec19bed7e560",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T14:13:53Z",
    "title_canon_sha256": "c59ea7870cfa2fa510a1354051cad315af4007b5e9f6cbb0fdf5763dd72dd710"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13579",
    "kind": "arxiv",
    "version": 1
  }
}