Pith Number

pith:VZYYFHU7

pith:2026:VZYYFHU74ZRA7KNBURENYUWTUV

not attested not anchored not stored refs resolved

bde: A Python Package for Bayesian Deep Ensembles via MILE

Angelos Aslanidis, David R\"ugamer, Emanuel Sommer, Vyron Arvanitis

The bde Python package supplies scikit-learn compatible estimators for Bayesian deep ensembles on tabular data via efficient JAX implementation of Microcanonical Langevin Ensembles sampling.

arxiv:2605.14146 v1 · 2026-05-13 · 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{VZYYFHU74ZRA7KNBURENYUWTUV}

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

bde provides scikit-learn compatible estimators for fast training, efficient Markov Chain Monte Carlo sampling, and uncertainty quantification in both regression and classification tasks via an efficient JAX implementation of Microcanonical Langevin Ensembles.

C2weakest assumption

The assumption that the underlying MILE sampling method delivers effective Bayesian inference for deep ensembles on tabular data, which the package implements without presenting new validation or comparisons in the provided abstract.

C3one line summary

bde is a new Python package that implements Bayesian deep ensembles via efficient JAX-based Microcanonical Langevin Ensembles for tabular regression and classification with uncertainty estimates.

References

11 extracted · 11 resolved · 0 Pith anchors

[1] The Thirteenth International Conference on Learning Representations , year=

[2] Proceedings of the 41st International Conference on Machine Learning , year=

[3] Proceedings of the 41st International Conference on Machine Learning , year =

[4] BlackJAX: composable Bayesian inference in JAX

[5] James Bradbury and Roy Frostig and Peter Hawkins and Matthew James Johnson and Chris Leary and Dougal Maclaurin and George Necula and Adam Paszke and Jake Vander

Cited by

1 paper in Pith

Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning

Receipt and verification

First computed	2026-05-17T23:39:11.627277Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ae71829e9fe6620fa9a1a448dc52d3a569dbdd35c3a7812e5f19604c628d4f7b

Aliases

arxiv: 2605.14146 · arxiv_version: 2605.14146v1 · doi: 10.48550/arxiv.2605.14146 · pith_short_12: VZYYFHU74ZRA · pith_short_16: VZYYFHU74ZRA7KNB · pith_short_8: VZYYFHU7

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/VZYYFHU74ZRA7KNBURENYUWTUV \
  | 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: ae71829e9fe6620fa9a1a448dc52d3a569dbdd35c3a7812e5f19604c628d4f7b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fd70ba049b1c249c01f3640185e257b0ed0b75181dca62fe75284abcc34140a1",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T21:52:49Z",
    "title_canon_sha256": "213372e83c8ae55e3ab222f23c56127749483716a9551fdd2aca8be79c44920e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14146",
    "kind": "arxiv",
    "version": 1
  }
}