Pith Number

pith:E663YUJQ

pith:2026:E663YUJQWJMVOP4GGTW6DGOB3W

not attested not anchored not stored refs pending

Automatic Causal Fairness Analysis with LLM-Generated Reporting

Alessandro Antonucci, Alessia Berarducci, Eric Rossetto, Marco Zaffalon

FairMind automates fairness checks on training datasets by computing causal effects from counterfactual queries and using LLMs to generate the reports.

arxiv:2604.27011 v2 · 2026-04-29 · 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{E663YUJQWJMVOP4GGTW6DGOB3W}

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 introduce FairMind, a software prototype aiming to automatise fairness analysis at the dataset level. We achieve that by resorting to the assumptions of the standard fairness model... After the necessary data preprocessing, the tool implements a closed-form computation of the effects. LLMs are consequently exploited to generate accurate reports on the fairness levels detected in the training dataset. We achieve that in a zero-shot setup and show by examples the expected advantages with respect to a direct analysis performed by the LLM.

C2weakest assumption

The assumptions of the standard fairness model proposed by Plečko and Bareinboim allow a sound fairness evaluation in terms of causal effects based on counterfactual queries, and that LLMs can generate accurate reports on fairness levels in a zero-shot setup without additional training or verification.

C3one line summary

FairMind automates dataset-level causal fairness analysis with closed-form counterfactual computations and zero-shot LLM-generated reports, plus extensions for ordinal and continuous variables.

Receipt and verification

First computed	2026-06-08T01:04:05.950070Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

27bdbc5130b259573f8634ede199c1dd90436ec6ce21485b9832df94c42258a9

Aliases

arxiv: 2604.27011 · arxiv_version: 2604.27011v2 · doi: 10.48550/arxiv.2604.27011 · pith_short_12: E663YUJQWJMV · pith_short_16: E663YUJQWJMVOP4G · pith_short_8: E663YUJQ

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/E663YUJQWJMVOP4GGTW6DGOB3W \
  | 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: 27bdbc5130b259573f8634ede199c1dd90436ec6ce21485b9832df94c42258a9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f2c966fa227a61c87e2f720f54d63ad69a66319f1b287b8565b3de3c8ae1c0e5",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-04-29T10:31:38Z",
    "title_canon_sha256": "580618c423561b01fedfa40f43f38f6888ddc8a2810fdb9ad2339a201c4f4ab8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.27011",
    "kind": "arxiv",
    "version": 2
  }
}