Pith Number

pith:GILA6RH7

pith:2026:GILA6RH7KAAVPR6CT424VC6NBJ

not attested not anchored not stored refs resolved

Enhanced and Efficient Reasoning in Large Learning Models

Leslie G. Valiant

Recoding data to Unary Relational Integracode lets large models learn relational rules in polynomial time.

arxiv:2605.14036 v1 · 2026-05-13 · cs.AI · cs.CC · cs.CL · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{GILA6RH7KAAVPR6CT424VC6NBJ}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

This recoding has the surprising and fortuitous property that, while succinct, it makes the task of learning a core subset of relational rules that hold in the world described in the training data polynomial time learnable in a defined sense, the polynomial depending on the complexity of the rule.

C2weakest assumption

That preprocessing natural language text into Unary Relational Integracode can be performed efficiently and accurately enough to expose the relevant relationships without introducing prohibitive computational cost or information loss.

C3one line summary

Preprocessing text into Unary Relational Integracode enables polynomial-time learning of relational rules for sound reasoning in large language models.

References

40 extracted · 40 resolved · 0 Pith anchors

[1] J. R. Anderson and G. H. Bower.Human Associative Memory. Psychology Press, New York, 1973 1973

[2] B. Barak, B. Edelman, S. Goel, S. Kakade, E. Malach, and C. Zhang. Hidden progress in deep learning: Sgd learns parities near the computational limit. InAdvances in Neural Information Processing Syste 2022

[3] I. Beltagy, M. E. Peters, and A. Cohan. Longformer: The long-document transformer. arXiv preprint, 2020 2020

[4] Choromanski and et al 2020

[5] A. Daniely and G. Vardi. From local pseudorandom generators to hardness of learning. InConference on Learning Theory, pages 358–1394. PMLR, 2021 2021

Receipt and verification

First computed	2026-05-17T23:39:12.790602Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

32160f44ff500157c7c29f35ca8bcd0a53b5c3ae15cc79f3205aba972254c6db

Aliases

arxiv: 2605.14036 · arxiv_version: 2605.14036v1 · doi: 10.48550/arxiv.2605.14036 · pith_short_12: GILA6RH7KAAV · pith_short_16: GILA6RH7KAAVPR6C · pith_short_8: GILA6RH7

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/GILA6RH7KAAVPR6CT424VC6NBJ \
  | 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: 32160f44ff500157c7c29f35ca8bcd0a53b5c3ae15cc79f3205aba972254c6db

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "23cb108551527bdead40da023a647b74a5962a98c4906f5f4ef605cd482d0711",
    "cross_cats_sorted": [
      "cs.CC",
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-13T18:56:02Z",
    "title_canon_sha256": "7bae97d102aa2a92bf707888b448dc0f6cab7cdb252106230e0e7c0c7b47607f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14036",
    "kind": "arxiv",
    "version": 1
  }
}