Pith Number

pith:Q2JDPCVE

pith:2026:Q2JDPCVEJ3VX3CCUTXBMDOBNNB

not attested not anchored not stored refs resolved

Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions

Gideon Popoola, John Sheppard

Outcome-fair credit models can still apply different reasoning to similar individuals, a hidden procedural bias missed by standard metrics.

arxiv:2605.12701 v1 · 2026-05-12 · cs.LG · cs.AI · cs.CE · cs.CY

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{Q2JDPCVEJ3VX3CCUTXBMDOBNNB}

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

We show that existing outcome-fair models can still apply fundamentally different reasoning to individuals, a ``hidden procedural bias'' missed by standard fairness metrics and algorithms.

C2weakest assumption

That nearest-neighbor counterfactuals and aligned integrated gradient attributions reliably capture and enforce procedural fairness without introducing artifacts from the generation method itself.

C3one line summary

Outcome-fair credit models often exhibit hidden procedural bias through inconsistent reasoning across groups, which the CEC framework mitigates by enforcing consistent feature attributions via counterfactuals.

References

299 extracted · 299 resolved · 5 Pith anchors

[1] Women in the American Political System: An Encyclopedia of Women as Voters, Candidates, and Office Holders , volume=

[2] Home Mortgage Disclosure Act, and Community , year=

[3] Causality , author=. 2009 , publisher= 2009

[4] International Journal of Management , volume=

[5] Applied Soft Computing , volume= 2020

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:09:49.695868Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

8692378aa44eeb7d88549dc2c1b82d685991cafce3d6ebb012a3aeace6c69aa2

Aliases

arxiv: 2605.12701 · arxiv_version: 2605.12701v1 · doi: 10.48550/arxiv.2605.12701 · pith_short_12: Q2JDPCVEJ3VX · pith_short_16: Q2JDPCVEJ3VX3CCU · pith_short_8: Q2JDPCVE

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/Q2JDPCVEJ3VX3CCUTXBMDOBNNB \
  | 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: 8692378aa44eeb7d88549dc2c1b82d685991cafce3d6ebb012a3aeace6c69aa2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e9e8442b307ba1b25eed23d3068e4ab1f0c6b5d2e114c353c2a9f8d84110fe27",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CE",
      "cs.CY"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T19:54:25Z",
    "title_canon_sha256": "6f9bbb7ed1967d50950580ab3fc122e3ecadf983cbc1bd40f60804881b7527f9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12701",
    "kind": "arxiv",
    "version": 1
  }
}