Pith Number

pith:LTEXOPHK

pith:2026:LTEXOPHKH7YMSK3BYGOSEARTDA

not attested not anchored not stored refs resolved

Explainable AI Isn't Enough! Rethinking Algorithmic Contestability

Gunnar K\"onig, Kristof Meding, Timo Freiesleben

Standard XAI tools like counterfactuals only flag nearby errors and fall short of providing grounds to overturn algorithmic decisions.

arxiv:2605.16041 v1 · 2026-05-15 · stat.ML · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LTEXOPHKH7YMSK3BYGOSEARTDA}

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

Standard XAI explanations such as counterfactuals, LIME, or Anchors, even when combined with human intuitions about decision continuity or monotonicity, reveal only errors in the neighborhood of the individual, but provide insufficient grounds for overturning the decision at hand.

C2weakest assumption

That the three identified types of evidence (predictive multiplicity, incorrect feature values, and neglected overruling evidence) render decisions normatively indefensible according to the decision maker's own ethical standards, as stated in the section proposing the operational definition of contestability.

C3one line summary

The paper defines algorithmic contestability as identifying evidence to overturn potentially incorrect decisions and identifies three types of such evidence that make decisions normatively indefensible under the decision maker's standards.

References

115 extracted · 115 resolved · 1 Pith anchors

[1] A practical guide, 1st ed., Cham: Springer International Publishing , volume= 2017

[2] Joint European conference on machine learning and knowledge discovery in databases , pages= 2019

[3] European Union , year=

[4] Philosophy of Science , volume= 2014

[5] New essays on semantic externalism and self-knowledge , pages=

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-20T00:01:50.381946Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5cc9773cea3ff0c92b61c19d220233180f877f50f20305cf0523f73a52dbdc41

Aliases

arxiv: 2605.16041 · arxiv_version: 2605.16041v1 · doi: 10.48550/arxiv.2605.16041 · pith_short_12: LTEXOPHKH7YM · pith_short_16: LTEXOPHKH7YMSK3B · pith_short_8: LTEXOPHK

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/LTEXOPHKH7YMSK3BYGOSEARTDA \
  | 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: 5cc9773cea3ff0c92b61c19d220233180f877f50f20305cf0523f73a52dbdc41

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f80e64b4fe3565f6722d4fb26e93b29173441afcf4c4f1e85fd7aaabd7a0696c",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2026-05-15T15:14:13Z",
    "title_canon_sha256": "a0db3d968f591ba5fa8dcb37f28b0f1e23de34a4610f52f8c71156b5465304bb"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16041",
    "kind": "arxiv",
    "version": 1
  }
}