pith. sign in
Pith Number

pith:G5PHVFID

pith:2026:G5PHVFIDGAADWC23K6NVBP63LN
not attested not anchored not stored refs pending

Demystifying Mergeability: Interpretable Properties to Predict Model Merging Success

Bo Zhao, Emanuele Rodol\`a, Luca Zhou, Rose Yu

Gradient alignment between fine-tuned models is the strongest predictor of successful merging across methods and tasks.

arxiv:2601.22285 v7 · 2026-01-29 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{G5PHVFIDGAADWC23K6NVBP63LN}

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

Crucially, however, gradient alignment metrics consistently emerge as the most fundamental signals of compatibility.

C2weakest assumption

That the chosen set of interpretable pairwise metrics (such as gradient L2 distance) plus L1-regularized linear optimization is sufficient to identify the true drivers of merge success without missing key unmeasured factors.

C3one line summary

Mergeability is not intrinsic to models but depends on merging method and tasks, with gradient alignment as the key predictive signal uncovered via interpretable metrics.

Cited by

3 papers in Pith

Receipt and verification
First computed 2026-05-20T01:05:07.281625Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

375e7a950330003b0b5b579b50bfdb5b67b3a269208585bf5dd3c0aa84c7e4d7

Aliases

arxiv: 2601.22285 · arxiv_version: 2601.22285v7 · doi: 10.48550/arxiv.2601.22285 · pith_short_12: G5PHVFIDGAAD · pith_short_16: G5PHVFIDGAADWC23 · pith_short_8: G5PHVFID
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/G5PHVFIDGAADWC23K6NVBP63LN \
  | 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: 375e7a950330003b0b5b579b50bfdb5b67b3a269208585bf5dd3c0aa84c7e4d7
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "12d878280646b316ab674d039cd7d2ac0928643b7de47e413c5b730ca4cfa0ba",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-01-29T20:00:26Z",
    "title_canon_sha256": "f7b423489f9f9ad0a232ce96a629dcadcaf3bb5155bc709c0dc487ee8cd977f3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.22285",
    "kind": "arxiv",
    "version": 7
  }
}