Pith Number

pith:UEMSOXGL

pith:2026:UEMSOXGLBETGM3AX56DLGIAZ5V

not attested not anchored not stored refs pending

HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series

(2) Forgis, (3) University of Vienna), Camilla Mazzoleni, Federico Martelli, Gian-Alessandro Lombardi, Jonas Petersen, Philipp Petersen, Philipp Petersen (3) ((1) ETH Zurich, Riccardo Maggioni

HEPA pretrains a causal Transformer on unlabeled time series by forecasting future representations at chosen horizons, then freezes the encoder to output accurate survival CDFs for rare events with far less labeled data.

arxiv:2605.11130 v3 · 2026-05-11 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UEMSOXGLBETGM3AX56DLGIAZ5V}

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

With fixed architecture and optimiser hyperparameters across all benchmarks, HEPA handles water contamination, cyberattack detection, volatility regimes, and eight further event types across 11 domains, exceeding leading time-series architectures including PatchTST, iTransformer, MAE, and Chronos-2 on at least 10 of 14 benchmarks, with an order of magnitude fewer tuned parameters and, on lifecycle datasets, an order of magnitude less labeled data.

C2weakest assumption

That the representations learned by horizon-conditioned JEPA pretraining on unlabeled data will transfer effectively to accurate event-specific survival CDF prediction after freezing the encoder, without requiring domain-specific architectural changes or extensive hyperparameter search.

C3one line summary

HEPA combines self-supervised JEPA pretraining on time series representations with horizon-conditioned finetuning to predict rare events via survival CDFs, outperforming PatchTST, iTransformer, MAE, and Chronos-2 on at least 10 of 14 benchmarks while using an order of magnitude fewer tuned params.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-26T02:05:10.420358Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a119275ccb0926666c17ef86b32019ed506e10a20038b3f76050d50493ad3613

Aliases

arxiv: 2605.11130 · arxiv_version: 2605.11130v3 · doi: 10.48550/arxiv.2605.11130 · pith_short_12: UEMSOXGLBETG · pith_short_16: UEMSOXGLBETGM3AX · pith_short_8: UEMSOXGL

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/UEMSOXGLBETGM3AX56DLGIAZ5V \
  | 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: a119275ccb0926666c17ef86b32019ed506e10a20038b3f76050d50493ad3613

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "50167656b4d48c5bb77df84e3654b05917354ccfa80f30e4300b7eb1a5740b50",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-11T18:38:03Z",
    "title_canon_sha256": "d52ad6c2e3076feefdc23a14b3097b6bd8a5b5756acb5992235707400b214783"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.11130",
    "kind": "arxiv",
    "version": 3
  }
}