Pith Number

pith:4NQXTQWO

pith:2026:4NQXTQWOF4DGN4N3Z7KAXNGQZM

not attested not anchored not stored refs resolved

SurF: A Generative Model for Multivariate Irregular Time Series Forecasting

Mohammad R. Rezaei, Rahul G. Krishnan, Tejas Balaji

SurF turns irregular multivariate event sequences into i.i.d. unit-rate exponential noise through a learnable bijection based on the Time Rescaling Theorem, allowing one generative model to train across heterogeneous datasets.

arxiv:2605.14069 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{4NQXTQWOF4DGN4N3Z7KAXNGQZM}

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

On six real-world benchmarks, SurF achieves the best reported time RMSE on Earthquake, Retweet, and Taobao, and is within trial-level noise of the strongest specialist on the remaining three. Under a strict leave-one-out protocol, the held-out checkpoint beats every classical and neural-autoregressive baseline on 5/6 datasets and beats every baseline on Amazon and Earthquake.

C2weakest assumption

That the Time Rescaling Theorem can be parameterized as an effective learnable bijection between heterogeneous event sequences and unit-rate exponential noise without introducing significant approximation errors or requiring dataset-specific tuning that undermines cross-dataset generalization.

C3one line summary

SurF applies the Time Rescaling Theorem as a learnable bijection to create a single generative model for forecasting irregular multivariate event streams that outperforms or matches baselines on six benchmarks.

References

20 extracted · 20 resolved · 5 Pith anchors

[1] A decoder-only foundation model for time-series forecasting · arXiv:2310.10688

[2] Chronos: Learning the Language of Time Series · arXiv:2403.07815

[3] Lag-Llama: Towards foundation models for probabilistic time se- ries forecasting

[4] arXiv preprint arXiv:2101.10318 , year=

[5] Fully neural network based model for general temporal point processes 1905

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:12.439378Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e36179c2ce2f0666f1bbcfd40bb4d0cb27ddc012db12bcd9bdf26ad9360f83e7

Aliases

arxiv: 2605.14069 · arxiv_version: 2605.14069v1 · doi: 10.48550/arxiv.2605.14069 · pith_short_12: 4NQXTQWOF4DG · pith_short_16: 4NQXTQWOF4DGN4N3 · pith_short_8: 4NQXTQWO

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/4NQXTQWOF4DGN4N3Z7KAXNGQZM \
  | 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: e36179c2ce2f0666f1bbcfd40bb4d0cb27ddc012db12bcd9bdf26ad9360f83e7

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4bf026dca8f7f79c95ce7754eac1116f3229b7bfa0f1bd22acdc0c3a686e9586",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T19:46:48Z",
    "title_canon_sha256": "0a571bac11b9d68043cc4fdbda7bc3f50170e30ff0975f1d14b30d01fe16edae"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14069",
    "kind": "arxiv",
    "version": 1
  }
}