Pith Number

pith:XLYU654C

pith:2026:XLYU654C4RUXH4M4S4D46ASLZ3

not attested not anchored not stored refs resolved

Hidden State Poisoning Attacks against Mamba-based Language Models

Alexandre Le Mercier, Chris Develder, Thomas Demeester

Short input phrases can irreversibly overwrite hidden states in Mamba models, inducing amnesia on retrieval tasks that pure Transformers resist.

arxiv:2601.01972 v4 · 2026-01-05 · cs.CL · cs.AI · 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{XLYU654C4RUXH4M4S4D46ASLZ3}

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

Specific short input phrases induce a partial amnesia effect in Mamba-based models by irreversibly overwriting information in their hidden states, confirmed by collapse on RoBench-25 while pure Transformers remain unaffected.

C2weakest assumption

That the observed performance drops are caused specifically by irreversible hidden-state overwriting rather than other mechanisms such as attention disruption or output formatting changes, and that RoBench-25 isolates this effect without confounding factors.

C3one line summary

Short input phrases can irreversibly overwrite hidden states in Mamba models, impairing information retrieval on a new benchmark while leaving pure Transformer models unaffected.

References

25 extracted · 25 resolved · 5 Pith anchors

[1] arXiv preprint arXiv:2402.01771 , year=

[2] Nemotron-h: A family of accurate and efficient hybrid mamba-transformer models

[3] Mahabaleshwarkar, Shih- Yang Liu, Matthijs Van Keirsbilck, Min-Hung Chen, Yoshi Suhara, et al

[4] Investigating the indirect object identification circuit in mamba.arXiv preprint arXiv:2407.14008,

[5] The Pile: An 800GB Dataset of Diverse Text for Language Modeling · arXiv:2101.00027

Receipt and verification

First computed	2026-05-17T23:39:04.524425Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

baf14f7782e46973f19c9707cf024bcedd6828d1905a8257862e7a9a3bd2fd70

Aliases

arxiv: 2601.01972 · arxiv_version: 2601.01972v4 · doi: 10.48550/arxiv.2601.01972 · pith_short_12: XLYU654C4RUX · pith_short_16: XLYU654C4RUXH4M4 · pith_short_8: XLYU654C

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/XLYU654C4RUXH4M4S4D46ASLZ3 \
  | 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: baf14f7782e46973f19c9707cf024bcedd6828d1905a8257862e7a9a3bd2fd70

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "280a24a132efba1de55e29405797d479ae87fbabcf2744fb8d296e8250bdacee",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-01-05T10:27:19Z",
    "title_canon_sha256": "2e0bcb19e80d0349d0fdc24f12870751dcde889c95cf9f568bd49e86f84ffe28"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.01972",
    "kind": "arxiv",
    "version": 4
  }
}