Pith Number

pith:2WYRQ72C

pith:2026:2WYRQ72CCFVZ43QY6RSWQ53XGI

not attested not anchored not stored refs resolved

On the Fragility of Data Attribution When Learning Is Distributed

Bo Hui, Min-Te Sun, Wei-shinn Ku, Xian Gao

A single participant can inflate its measured attribution value in distributed training while preserving global utility.

arxiv:2605.15520 v1 · 2026-05-15 · cs.LG · cs.AI · cs.DC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{2WYRQ72CCFVZ43QY6RSWQ53XGI}

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

A single participant in a standard distributed training workflow can substantially inflate its measured attribution value while preserving global utility.

C2weakest assumption

Standard marginal-utility attribution evaluators remain sensitive to small synthetic batches that exploit non-IID label coverage in distributed settings.

C3one line summary

A single adversary in distributed training inflates its attribution value via latent optimization on synthetic batches without degrading accuracy or triggering basic defenses.

References

37 extracted · 37 resolved · 4 Pith anchors

[1] I., Cevher, V ., and Muehlebach, M

[2] Shapley estimated explanation (shep): A fast post-hoc attribution method for interpreting intelligent fault diagnosis.arXiv preprint arXiv:2504.03773,

[3] Scaling laws for the value of individual data points in machine learning

[4] Fair and efficient contribution val- uation for vertical federated learning 2024

[5] How to probe: Simple yet effective techniques for improving post-hoc explanations.arXiv preprint arXiv:2503.00641,

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:02.983393Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d5b1187f42116b9e6e18f4656877773238c4cfe34e5a56283465818fba21f923

Aliases

arxiv: 2605.15520 · arxiv_version: 2605.15520v1 · doi: 10.48550/arxiv.2605.15520 · pith_short_12: 2WYRQ72CCFVZ · pith_short_16: 2WYRQ72CCFVZ43QY · pith_short_8: 2WYRQ72C

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/2WYRQ72CCFVZ43QY6RSWQ53XGI \
  | 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: d5b1187f42116b9e6e18f4656877773238c4cfe34e5a56283465818fba21f923

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "711a421b85e6f10f105fa51e4f42199d64b53a8d1e87759d33fccc1030ebed34",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.DC"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-15T01:34:55Z",
    "title_canon_sha256": "020537bf05c9cdef682f5d542e0c942ddfcef30b3d0ca3e66e74c46e4f251610"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15520",
    "kind": "arxiv",
    "version": 1
  }
}