Pith Number

pith:OK6CIMY2

pith:2026:OK6CIMY2AXSYSPYBVGVZXNXC2P

not attested not anchored not stored refs pending

Unlocking Compositional Generalization in Continual Few-Shot Learning

Chi-Nguyen Tran, Dao Sy Duy Minh, Huynh Trung Kiet, Long Tran-Thanh, Phu-Hoa Pham, Phu-Quy Nguyen-Lam

By optimizing slot representations for holistic class identity in training and composing them at inference, the framework achieves strong generalization to novel concepts with minimal forgetting.

arxiv:2605.11710 v2 · 2026-05-12 · 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{OK6CIMY2AXSYSPYBVGVZXNXC2P}

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

our framework employs a dual-phase strategy. During training, slot representations are optimized entirely toward holistic class identity, preserving highly generalizable, object-level geometries. At inference, preserved slots are dynamically composed to match novel scenes... achieving state-of-the-art unseen-concept generalization and minimal forgetting across standard continual learning benchmarks.

C2weakest assumption

Leveraging the inherent patch-level semantic geometry of self-supervised Vision Transformers (ViTs) that remains generalizable when optimized holistically for class identity rather than tying to seen patterns.

C3one line summary

A dual-phase framework using self-supervised ViT slots optimizes representations for class identity during training and composes them dynamically at inference to achieve state-of-the-art generalization to unseen concepts with minimal forgetting in continual few-shot learning.

Receipt and verification

First computed	2026-05-20T00:05:47.173025Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

72bc24331a05e5893f01a9ab9bb6e2d3e7d045dff269dda6f4ce4bf326ebee21

Aliases

arxiv: 2605.11710 · arxiv_version: 2605.11710v2 · doi: 10.48550/arxiv.2605.11710 · pith_short_12: OK6CIMY2AXSY · pith_short_16: OK6CIMY2AXSYSPYB · pith_short_8: OK6CIMY2

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/OK6CIMY2AXSYSPYBVGVZXNXC2P \
  | 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: 72bc24331a05e5893f01a9ab9bb6e2d3e7d045dff269dda6f4ce4bf326ebee21

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5541458649b3dbe1fdfbf6907ee105b0fab0f1423634d8f2cf81c44835a76c44",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-12T08:02:31Z",
    "title_canon_sha256": "1b76d8df970131856b7ae6642ed9aa765dfbc0f0008157436f31c93c8bc432b8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.11710",
    "kind": "arxiv",
    "version": 2
  }
}