Pith Number

pith:AIOQKSXH

pith:2026:AIOQKSXHKB5YZ6EWPRIRX3PZ4H

not attested not anchored not stored refs resolved

Pitfalls of Unlabeled Disagreement-Based Drift Detection in Streaming Tree Ensembles

Afonso Louren\c{c}o, Goreti Marreiros, Lara S\'a Neves, Lizy K. John

Disagreement-based drift detection underperforms loss-based methods in incremental decision tree ensembles due to structural rigidity.

arxiv:2605.12803 v1 · 2026-05-12 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{AIOQKSXHKB5YZ6EWPRIRX3PZ4H}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

Our experiments show that, although this method performs well in ensembles of multi-layer perceptrons (MLPs), it consistently underperforms loss-based detectors when applied to IDTs. We attribute this behavior to the intrinsic rigidity of IDTs: learning primarily through structural expansion, with limited parameter adaptation, restricts model plasticity and prevents disagreement from reliably reflecting learning potential.

C2weakest assumption

That batch-specific disagreement measures constructed via label flipping accurately reflect learning potential in IDTs and that the observed underperformance is caused by model rigidity rather than other factors in the experimental design.

C3one line summary

Disagreement measures from label flipping in IDT ensembles underperform loss-based drift detectors in streaming tabular data due to the limited plasticity of tree models.

References

48 extracted · 48 resolved · 2 Pith anchors

[1] Knowledge and Information Systems , pages= 2025

[2] Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , pages=

[3] Joint European Conference on Machine Learning and Knowledge Discovery in Databases , pages= 2024

[4] arXiv preprint arXiv:2512.11668 , year=

[5] arXiv preprint arXiv:2502.14011 , year=

Receipt and verification

First computed	2026-05-18T03:09:12.683936Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

021d054ae7507b8cf8967c511bedf9e1d5b1a82458846cdebf3ad1deb660318a

Aliases

arxiv: 2605.12803 · arxiv_version: 2605.12803v1 · doi: 10.48550/arxiv.2605.12803 · pith_short_12: AIOQKSXHKB5Y · pith_short_16: AIOQKSXHKB5YZ6EW · pith_short_8: AIOQKSXH

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/AIOQKSXHKB5YZ6EWPRIRX3PZ4H \
  | 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: 021d054ae7507b8cf8967c511bedf9e1d5b1a82458846cdebf3ad1deb660318a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "acb89353fc9f23f43802e1e3e843598a89481360a086849fad91df8ad3a5a72a",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T22:53:03Z",
    "title_canon_sha256": "18caeba6e8cfbecb262799f60ed0cde2e5dabb5cea7168d14601085b7687a6df"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.12803",
    "kind": "arxiv",
    "version": 1
  }
}