Pith Number

pith:PW5LW4TR

pith:2026:PW5LW4TR7CZCLEAEL5M5EEHMCK

not attested not anchored not stored refs resolved

A Survey on Data-Dependent Worst-Case Generalization Bounds

Hubert Leroux, Jean Marcus, Julien Roger

A single template inequality unifies data-dependent generalization bounds for overparameterized networks.

arxiv:2605.13913 v1 · 2026-05-13 · 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{PW5LW4TR7CZCLEAEL5M5EEHMCK}

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 unify these contributions around a single template inequality and a head-to-head comparison of the resulting bounds.

C2weakest assumption

The survey assumes that the cited works' individual bounds remain valid when placed inside the common template; any hidden incompatibility between the data-dependent set constructions, geometric descriptors, and stability assumptions would invalidate the unification.

C3one line summary

The survey unifies extensions of PAC-Bayesian theory to data-dependent sets, geometric and topological complexity measures of optimization trajectories, and stability replacements for information terms into one template inequality with comparative evaluation.

References

17 extracted · 17 resolved · 2 Pith anchors

[1] Neural network learning: Theoretical foundations , author=. 2009 , publisher= 2009

[2] Advances in Neural Information Processing Systems , volume=

[3] Journal of machine learning research , volume=

[4] A PAC-Bayesian approach to adaptive classification , author=. preprint , volume=

[5] Proceedings of the 26th Annual International Conference on Machine Learning , pages=

Receipt and verification

First computed	2026-05-17T23:39:18.788731Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7dbabb7271f8b22590045f59d210ec12ac42949c120d3f721c5aa58f0ad7d010

Aliases

arxiv: 2605.13913 · arxiv_version: 2605.13913v1 · doi: 10.48550/arxiv.2605.13913 · pith_short_12: PW5LW4TR7CZC · pith_short_16: PW5LW4TR7CZCLEAE · pith_short_8: PW5LW4TR

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/PW5LW4TR7CZCLEAEL5M5EEHMCK \
  | 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: 7dbabb7271f8b22590045f59d210ec12ac42949c120d3f721c5aa58f0ad7d010

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "cc1291814cfd0e0fe894ed683b36851823512d366a8263ff2c4e8c35b857372f",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2026-05-13T09:03:50Z",
    "title_canon_sha256": "1a57654a3d6ac3b85842c537c0c88c9f5be87d0cd3b654710746d2dc72cd795e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13913",
    "kind": "arxiv",
    "version": 1
  }
}