Pith. sign in
Pith Number

pith:3BWCD45E

pith:2026:3BWCD45E4NX4APHFYXABWXAPZS
not attested not anchored not stored refs pending

Towards Rigorous Explainability by Feature Attribution

Joao Marques-Silva, Olivier L\'etoff\'e, Xuanxiang Huang

Symbolic methods can provide rigorous feature importance assignments in explainable AI unlike non-symbolic approaches such as Shapley values

arxiv:2604.15898 v2 · 2026-04-17 · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{3BWCD45E4NX4APHFYXABWXAPZS}

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

Non-symbolic methods such as Shapley values lack rigor and can mislead, while symbolic methods provide rigorous alternatives for feature importance assignment.

C2weakest assumption

That symbolic methods can be made practical and scalable for the complex, high-dimensional models used in real-world machine learning.

C3one line summary

The paper reviews work on symbolic methods for rigorous feature attribution in XAI as an alternative to non-rigorous non-symbolic techniques.

Receipt and verification
First computed 2026-05-28T01:05:12.286051Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

d86c21f3a4e36fc03ce5c5c01b5c0fcc8461c7515b0209391327d7a4df60b355

Aliases

arxiv: 2604.15898 · arxiv_version: 2604.15898v2 · doi: 10.48550/arxiv.2604.15898 · pith_short_12: 3BWCD45E4NX4 · pith_short_16: 3BWCD45E4NX4APHF · pith_short_8: 3BWCD45E
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/3BWCD45E4NX4APHFYXABWXAPZS \
  | 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: d86c21f3a4e36fc03ce5c5c01b5c0fcc8461c7515b0209391327d7a4df60b355
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "d9c236ebfc2cc9dd65c47a096eae33ae38139dd7974ae95b18228d4f629857d1",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-17T09:56:17Z",
    "title_canon_sha256": "bae305f7e70bea1fcfdcfeccfb155c0af9398a7bb31ae4509678d57dc6f0635c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.15898",
    "kind": "arxiv",
    "version": 2
  }
}