Pith Number

pith:EJLJ5NLH

pith:2024:EJLJ5NLHC4UGYMBXDXMG2AIVVW

not attested not anchored not stored refs pending

Dataset-Driven Channel Masks in Transformers for Multivariate Time Series

Kibok Lee, Seunghan Lee, Taeyoung Park

Channel masks from similarity matrices and learnable domain parameters enable partial channel dependence in Transformer attention for multivariate time series.

arxiv:2410.23222 v4 · 2024-10-30 · cs.LG · cs.AI · stat.ML

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{EJLJ5NLHC4UGYMBXDXMG2AIVVW}

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

Channel masks consisting of a similarity matrix and dataset-specific learnable domain parameters, integrated via element-wise multiplication into attention matrices, achieve partial channel dependence and thereby enhance channel dependency modeling in Transformer-based multivariate time series models.

C2weakest assumption

That a similarity matrix derived from the data plus a modest number of learnable domain parameters will reliably isolate the relevant partial dependencies without introducing harmful bias or requiring per-dataset hyper-parameter search that negates the claimed benefit.

C3one line summary

Introduces channel masks built from similarity matrices plus learnable domain parameters to realize partial channel dependence inside Transformer attention for multivariate time series.

Receipt and verification

First computed	2026-05-29T01:04:51.338236Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

22569eb56717286c30371dd86d0115adac9f897e7903f31f9ad61758fbc631cc

Aliases

arxiv: 2410.23222 · arxiv_version: 2410.23222v4 · doi: 10.48550/arxiv.2410.23222 · pith_short_12: EJLJ5NLHC4UG · pith_short_16: EJLJ5NLHC4UGYMBX · pith_short_8: EJLJ5NLH

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/EJLJ5NLHC4UGYMBXDXMG2AIVVW \
  | 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: 22569eb56717286c30371dd86d0115adac9f897e7903f31f9ad61758fbc631cc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2dfe6cfb818b3cea396fd99e984693b67ef043ba895eeb899258e64122e60068",
    "cross_cats_sorted": [
      "cs.AI",
      "stat.ML"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-10-30T17:12:03Z",
    "title_canon_sha256": "fa73b375f2ee064d83f7213ab416f9a2637cc63b5448a101de214c6baf22b5fe"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2410.23222",
    "kind": "arxiv",
    "version": 4
  }
}