Pith Number

pith:7PM2BGWC

pith:2026:7PM2BGWCSFMDPXLAYQR2B775YU

not attested not anchored not stored refs resolved

Reliability-Gated Source Anchoring for Continual Test-Time Adaptation

Biyao Zhang, Christian Gagn\'e, Debargha Ganguly, Mohsen Harir, Osama Zafar, Sabyasachi Sahoo, Shouren Wang, Sreehari Sankar, Vikash Singh, Vipin Chaudhary, Weicong Chen

RMemSafe uses normalized predictive entropy to gate source anchoring in continual test-time adaptation, disabling unreliable anchors when the source posterior flattens.

arxiv:2605.14063 v1 · 2026-05-13 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{7PM2BGWCSFMDPXLAYQR2B775YU}

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

Combined with ASR, RMemSafe achieves the lowest error on 8 of 9 matched-split continual-corruption cells and is the best reset-based method on all 9, improving ROID+ASR by 1.05 pp on ResNet-50 and 0.48 pp on ViT-B/16. A controlled source-degradation sweep shows a 1.13× shallower harm slope than ROID+ASR.

C2weakest assumption

That normalized predictive entropy from the frozen source reliably signals when anchoring should be attenuated, without missing cases of confidently wrong low-entropy predictions or introducing instability in the fallback objective.

C3one line summary

RMemSafe gates source anchoring via entropy in CTTA, reducing error by 1.05pp on ResNet-50 when source accuracy collapses and showing shallower degradation slope than prior methods.

References

43 extracted · 43 resolved · 2 Pith anchors

[1] $K^4$: Online Log Anomaly Detection Via Unsupervised Typicality Learning 2025 · arXiv:2507.20051

[2] A., and Yang, B 2023

[3] Ganguly, D., Iyengar, S., Chaudhary, V ., and Kalyanaraman, S. (2024). PROOF OF THOUGHT : Neurosymbolic program synthesis allows robust and interpretable reasoning. InThe First Workshop on System-2 Re 2024

[4] Ganguly, D., Morningstar, W. R., Yu, A. S., and Chaudhary, V . (2025a). Forte : Finding outliers with representation typicality estimation. InThe Thirteenth International Conference on Learning Repres

[5] Ganguly, D., Sankar, S., Zhang, B., Singh, V ., Gupta, K., Kavuru, H., Luo, A., et al. (2026). Trust the typical: An out-of-distribution safety detection framework.arXiv preprint arXiv:2602.04581. ICL 2026

Receipt and verification

First computed	2026-05-17T23:39:12.504463Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fbd9a09ac2915837dd60c423a0fffdc504060b99dde629e7bf591899659d21c1

Aliases

arxiv: 2605.14063 · arxiv_version: 2605.14063v1 · doi: 10.48550/arxiv.2605.14063 · pith_short_12: 7PM2BGWCSFMD · pith_short_16: 7PM2BGWCSFMDPXLA · pith_short_8: 7PM2BGWC

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/7PM2BGWCSFMDPXLAYQR2B775YU \
  | 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: fbd9a09ac2915837dd60c423a0fffdc504060b99dde629e7bf591899659d21c1

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "092510612e284079b36665f3fe019d4ed6b9b09c3373c6524387541ff799183e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T19:38:08Z",
    "title_canon_sha256": "201e6dceaad416954a613e3aa88498817e443ba8b72820cebadef7e25c61b251"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14063",
    "kind": "arxiv",
    "version": 1
  }
}