Pith Number

pith:DKJ22TW5

pith:2026:DKJ22TW5JC73RK7BUZWQO6GLDT

not attested not anchored not stored refs resolved

Towards Fine-Grained and Verifiable Concept Bottleneck Models

Guang Yang, Haijie Xu, Mariathasan Anish, Shuang Wu, Yingying Fang

A verifiable CBM framework grounds concepts in localized image patches, achieving comparable accuracy to standard CBMs on medical benchmarks while enabling direct inspection of concept correctness.

arxiv:2605.14210 v1 · 2026-05-14 · cs.LG · 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{DKJ22TW5JC73RK7BUZWQO6GLDT}

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

Experiments on medical imaging benchmarks show that our learned concept space is information-complete and achieves predictive performance comparable to standard CBMs, while substantially improving transparency. Unlike post-hoc attribution methods, our framework validates both the presence and correctness of concept representations.

C2weakest assumption

That localizing each concept to visual evidence regions will reliably prevent the model from learning spurious correlations and that human inspection of these regions will correctly verify intended concepts without additional validation data or metrics.

C3one line summary

A verifiable CBM framework grounds concepts in localized image patches, achieving comparable accuracy to standard CBMs on medical benchmarks while enabling direct inspection of concept correctness.

References

28 extracted · 28 resolved · 2 Pith anchors

[1] Nature Machine Intelligence3(12), 1061–1070 (2021) 2021

[2] Nature Communications15(1), 524 (2024) 2024

[3] In: 2018 IEEE winter conference on applications of computer vision (WACV) 2018

[4] Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic) 2018 · arXiv:1902.03368

[5] Advances in neural information processing systems35, 21400–21413 (2022) 2022

Receipt and verification

First computed	2026-05-17T23:39:10.938204Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1a93ad4edd48bfb8abe1a66d0778cb1cdc24ff0f720300a8d2fe56ebfb2c8d01

Aliases

arxiv: 2605.14210 · arxiv_version: 2605.14210v1 · doi: 10.48550/arxiv.2605.14210 · pith_short_12: DKJ22TW5JC73 · pith_short_16: DKJ22TW5JC73RK7B · pith_short_8: DKJ22TW5

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/DKJ22TW5JC73RK7BUZWQO6GLDT \
  | 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: 1a93ad4edd48bfb8abe1a66d0778cb1cdc24ff0f720300a8d2fe56ebfb2c8d01

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d18b36420cce8c01aefc0ac9e31af333976332de468b499340243316eea4c4cb",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T00:08:09Z",
    "title_canon_sha256": "b0ae81c6429213f37b091cc4ee8ff3711c5735dd2bee6ef6ba2603a15cd2313c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14210",
    "kind": "arxiv",
    "version": 1
  }
}