Pith Number

pith:ZHQU76YF

pith:2026:ZHQU76YFLFDXDC4MXZMIVBJKPS

not attested not anchored not stored refs resolved

Understanding Generalization through Decision Pattern Shift

Hongbin Pei, Huiqi Deng, Peng Zhang, Quanshi Zhang, Xia Hu, Yibo Li

Decision pattern shifts in neural networks correlate linearly with generalization gaps, framing failure as internal mechanism drift.

arxiv:2605.13148 v1 · 2026-05-13 · cs.LG · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ZHQU76YFLFDXDC4MXZMIVBJKPS}

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

the DPS magnitude correlates linearly with the generalization gap (nearly all Pearson r > 0.8), revealing generalization as a systematic drift in the model's internal decision mechanism

C2weakest assumption

that a GradCAM-based channel-contribution vector faithfully represents the model's internal decision pattern and that deviation from the class-average pattern is the correct way to quantify harmful shift

C3one line summary

DPS quantifies deviation of per-sample decision patterns from class averages and shows linear correlation with generalization gaps while unifying degradation scenarios into a continuous trajectory.

References

82 extracted · 82 resolved · 2 Pith anchors

[1] A closer look at memorization in deep networks 2017

[2] Nearly-tight vc-dimension and pseudodimension bounds for piecewise linear neural networks 2019

[3] Network dissection: Quantifying interpretability of deep visual representations 2017

[4] Analysis of representations for domain adaptation 2006

[5] Estimating generalization under distribution shifts via domain-invariant representations 2020

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:08:57.236923Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c9e14ffb055947718b8cbe588a852a7ca3df2af51019c17d4bd3b4e06e942028

Aliases

arxiv: 2605.13148 · arxiv_version: 2605.13148v1 · doi: 10.48550/arxiv.2605.13148 · pith_short_12: ZHQU76YFLFDX · pith_short_16: ZHQU76YFLFDXDC4M · pith_short_8: ZHQU76YF

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/ZHQU76YFLFDXDC4MXZMIVBJKPS \
  | 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: c9e14ffb055947718b8cbe588a852a7ca3df2af51019c17d4bd3b4e06e942028

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b8dc1b40bfaf3b19e7629b41de6f994e57b4d3d0a89405b298526ce33cc0239f",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T08:14:59Z",
    "title_canon_sha256": "d1e0e1e1cb83c4ca7a77de909c6b25677714b8add39fccdef779a3c172124658"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13148",
    "kind": "arxiv",
    "version": 1
  }
}