Pith. sign in
Pith Number

pith:QKBIFHSL

pith:2026:QKBIFHSLYL2DKHDO5AII2GHL3E
not attested not anchored not stored refs pending

Learning State-Tracking from Code Using Linear RNNs

Babak Rahmani, Hitesh Ballani, Julien Siems, Kirill Kalinin, Korbinian P\"oppel, Riccardo Grazzi

Linear RNNs track states from code traces of permutation compositions where Transformers fail.

arxiv:2602.14814 v3 · 2026-02-16 · cs.LG · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{QKBIFHSLYL2DKHDO5AII2GHL3E}

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

linear RNNs capable of state-tracking excel also in this setting, while Transformers still fail

C2weakest assumption

That the REPL trace conversion of permutation composition preserves the core state-tracking difficulty without introducing artifacts that favor linear RNNs over Transformers

C3one line summary

Linear RNNs track states from REPL code traces of permutations better than Transformers, but non-linear RNNs outperform them in partially observable probabilistic automata.

Cited by

1 paper in Pith

Receipt and verification
First computed 2026-06-26T01:15:49.523626Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

8282829e4bc2f4351c6ee8108d18ebd91d67e1977277a0116332e2557f69e4de

Aliases

arxiv: 2602.14814 · arxiv_version: 2602.14814v3 · doi: 10.48550/arxiv.2602.14814 · pith_short_12: QKBIFHSLYL2D · pith_short_16: QKBIFHSLYL2DKHDO · pith_short_8: QKBIFHSL
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/QKBIFHSLYL2DKHDO5AII2GHL3E \
  | 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: 8282829e4bc2f4351c6ee8108d18ebd91d67e1977277a0116332e2557f69e4de
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "4f1957b2ee2225df17b2f6857f4c613ad67d87357f688904a44cc071b2ced8c7",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-02-16T15:07:51Z",
    "title_canon_sha256": "44c9e4dba39c39d27e3e18c5b946737b5e3f5e0d261c15be2a6044475b9115c9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.14814",
    "kind": "arxiv",
    "version": 3
  }
}