Pith Number

pith:U6J2OD54

pith:2026:U6J2OD54ACYHPFBJWAECFPES4P

not attested not anchored not stored refs resolved

Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning

Da-Wei Zhou, Hao Sun, Zi-Jun Ding

Aligning CLIP patch features to semantic descriptions improves class-incremental learning.

arxiv:2605.13835 v1 · 2026-05-13 · 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{U6J2OD54ACYHPFBJWAECFPES4P}

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

Extensive experiments demonstrate that SPA achieves state-of-the-art performance.

C2weakest assumption

That GPT-5-generated class-wise semantic descriptions reliably identify discriminative patches and that optimal transport alignment between selected patches and semantic tokens yields a meaningful recognition improvement beyond global embeddings.

C3one line summary

SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.

References

72 extracted · 72 resolved · 7 Pith anchors

[1] Memory aware synapses: Learning what (not) to forget 2018

[2] Qwen-vl: A versatile vision-language model for understanding, localization.Text Reading, and Beyond, 2(1):1, 2023 2023

[3] Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models.Advances in neural information processing systems, 32, 2019 2019

[4] Food-101–mining discriminative components with random forests 2014

[5] Efficient lifelong learning with A-GEM.CoRR, abs/1812.00420 2018 · arXiv:1812.00420

Receipt and verification

First computed	2026-05-18T02:44:14.944708Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a793a70fbc00b0779429b00822bc92e3e181b1c1a3ef2a907fb50e73c0b47cc2

Aliases

arxiv: 2605.13835 · arxiv_version: 2605.13835v1 · doi: 10.48550/arxiv.2605.13835 · pith_short_12: U6J2OD54ACYH · pith_short_16: U6J2OD54ACYHPFBJ · pith_short_8: U6J2OD54

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/U6J2OD54ACYHPFBJWAECFPES4P \
  | 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: a793a70fbc00b0779429b00822bc92e3e181b1c1a3ef2a907fb50e73c0b47cc2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c26a1c0cad34eea2175be1335d6ebfaed5362e077320d5b34f78c4ef05e8ab4f",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T17:56:23Z",
    "title_canon_sha256": "bbe520d2b68ca1ed89b41ab3c8ced9b1702690ee969a576c1c0529a747da49d6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13835",
    "kind": "arxiv",
    "version": 1
  }
}