Pith Number

pith:MR7OAPQB

pith:2026:MR7OAPQB5UGBHODDHWH7QW4U7C

not attested not anchored not stored refs resolved

TILT: Target-induced loss tilting under covariate shift

Kakei Yamamoto, Martin J. Wainwright

The target-side penalty on an auxiliary predictor component induces implicit relative importance weighting that stays bounded even with disjoint supports.

arxiv:2605.14280 v1 · 2026-05-14 · cs.LG · 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{MR7OAPQB5UGBHODDHWH7QW4U7C}

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

At the population level, the target-side penalty on b implicitly induces relative importance weighting in terms of an estimand b*_f that is self-localized to the current error and remains uniformly bounded for any source-target pair, even those with disjoint supports; a general finite-sample oracle inequality holds and yields an end-to-end guarantee for sparse ReLU networks.

C2weakest assumption

The analysis assumes the existence of a decomposition f + b where the penalty on b on target data produces a useful weighting without requiring the supports of source and target to overlap or any explicit density estimation.

C3one line summary

TILT adds a target-data penalty on an auxiliary predictor component to induce effective importance weighting for unsupervised domain adaptation under covariate shift.

References

144 extracted · 144 resolved · 4 Pith anchors

[1] Tyrrell Rockafellar and Ren

[2] 2009 , publisher = 2009

[3] Tyrrell Rockafellar and Roger J.-B

[4] Foundations and Trends in Optimization , volume = 2014

[5] Proceedings of the 29th Annual Conference on Learning Theory , series = 2016

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:10.296601Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

647ee03e01ed0c13b8633d8ff85b94f8a54a93512fd1332897b48317b2e2dc02

Aliases

arxiv: 2605.14280 · arxiv_version: 2605.14280v1 · doi: 10.48550/arxiv.2605.14280 · pith_short_12: MR7OAPQB5UGB · pith_short_16: MR7OAPQB5UGBHODD · pith_short_8: MR7OAPQB

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/MR7OAPQB5UGBHODDHWH7QW4U7C \
  | 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: 647ee03e01ed0c13b8633d8ff85b94f8a54a93512fd1332897b48317b2e2dc02

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "08bcddc4dbe97e64f2c3caa4af0c30f64d44d1fe03b4f481470ccb67f120162f",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T02:26:34Z",
    "title_canon_sha256": "cab922bc611b9364badeda283d335b82f4bc07a37a4e2d18c0fbea8f69c9ac6f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14280",
    "kind": "arxiv",
    "version": 1
  }
}