Pith Number

pith:YRTVKMRP

pith:2026:YRTVKMRPQ5BRNASUFO6HUDJPIJ

not attested not anchored not stored refs resolved

Scaling few-shot spoken word classification with generative meta-continual learning

Batsirayi Mupamhi Ziki, Louise Beyers, Ruan van der Merwe

Generative meta-continual learning scales few-shot spoken word classification to 1000 classes while matching strong baselines at far lower adaptation cost.

arxiv:2605.13075 v2 · 2026-05-13 · cs.CL · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{YRTVKMRPQ5BRNASUFO6HUDJPIJ}

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

GeMCL produces exceptionally stable performance, and although it does not always outperform a repeatedly fully-finetuned HuBERT model nor a frozen HuBERT model with a repeatedly trained classifier head, it produces comparable performance to the latter while adapting 2000 times faster, having been trained less than half of the data for two orders of magnitude less time.

C2weakest assumption

That the generative component of GeMCL sufficiently prevents catastrophic forgetting when the number of sequential classes reaches 1000, without the need for task-specific hyperparameter retuning or additional regularization beyond what is described.

C3one line summary

GeMCL scales few-shot spoken word classification to 1000 classes with 5 shots each, matching frozen-HuBERT baseline performance while adapting 2000 times faster on less than half the data.

References

27 extracted · 27 resolved · 0 Pith anchors

[1] Proceedings of the 35th International Conference on Neural Information Processing Systems , articleno = 2021

[2] Three types of incremental learning , volume =

[3] Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) , year=

[4] HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units , year=

[5] Proceedings of the 34th International Conference on Neural Information Processing Systems , articleno = 2020

Receipt and verification

First computed	2026-05-18T03:08:58.789616Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c46755322f87431682542bbc7a0d2f424e6546ccc54c0b2fa778e00d00aaa448

Aliases

arxiv: 2605.13075 · arxiv_version: 2605.13075v2 · doi: 10.48550/arxiv.2605.13075 · pith_short_12: YRTVKMRPQ5BR · pith_short_16: YRTVKMRPQ5BRNASU · pith_short_8: YRTVKMRP

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/YRTVKMRPQ5BRNASUFO6HUDJPIJ \
  | 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: c46755322f87431682542bbc7a0d2f424e6546ccc54c0b2fa778e00d00aaa448

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "49609323773799ff264f47980d2f9727e84d15a4be70175d90f84afd9a58be3b",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T06:47:57Z",
    "title_canon_sha256": "44cbf462fbadec377a16ff436dc7ea50a00f39f82ae324857a2621d7a9506804"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13075",
    "kind": "arxiv",
    "version": 2
  }
}