Pith Number

pith:NRUDAJ65

pith:2024:NRUDAJ65J47VYHCUTC3KKNZ3DF

not attested not anchored not stored refs resolved

Compressed Chain of Thought: Efficient Reasoning Through Dense Representations

Benjamin Van Durme, Jeffrey Cheng

Language models can reason more accurately by generating compressed continuous tokens that stand in for full reasoning chains.

arxiv:2412.13171 v1 · 2024-12-17 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{NRUDAJ65J47VYHCUTC3KKNZ3DF}

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

Through experiments, we illustrate how CCoT enables additional reasoning over dense contentful representations to achieve corresponding improvements in accuracy. Moreover, the reasoning improvements can be adaptively modified on demand by controlling the number of contemplation tokens generated.

C2weakest assumption

That the generated continuous contemplation tokens actually encode and preserve the semantic content of explicit reasoning chains rather than functioning primarily as additional learned parameters or regularizers whose benefit is not tied to interpretable reasoning.

C3one line summary

CCoT generates variable-length continuous contemplation tokens that compress explicit reasoning chains, enabling additional dense reasoning and accuracy gains in off-the-shelf language models while allowing adaptive control of token count.

References

23 extracted · 23 resolved · 10 Pith anchors

[1] arXiv preprint arXiv:2006.11527 , year= 2006

[2] Training Verifiers to Solve Math Word Problems · arXiv:2110.14168

[3] Implicit chain of thought reasoning via knowledge distillation

[4] From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step · arXiv:2405.14838

[5] In-context autoencoder for context compression in a large language model.arXiv preprint arXiv:2307.06945

Formal links

2 machine-checked theorem links

Cited by

26 papers in Pith

Training-Free Looped Transformers

Efficient Reasoning with Hidden Thinking

On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective

Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner

CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation

Receipt and verification

First computed	2026-05-17T23:38:15.084912Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

6c683027dd4f3f5c1c5498b6a5373b1968ba25b3c53307f3264a913496a2cfdb

Aliases

arxiv: 2412.13171 · arxiv_version: 2412.13171v1 · doi: 10.48550/arxiv.2412.13171 · pith_short_12: NRUDAJ65J47V · pith_short_16: NRUDAJ65J47VYHCU · pith_short_8: NRUDAJ65

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/NRUDAJ65J47VYHCUTC3KKNZ3DF \
  | 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: 6c683027dd4f3f5c1c5498b6a5373b1968ba25b3c53307f3264a913496a2cfdb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c5c44621015278e87fe24c7e5eb44ccc9cdd13eafe424e2424c51a0f8874ed69",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-12-17T18:50:33Z",
    "title_canon_sha256": "c90be175ba0892e0bb9f340f2945ab6ac8db699543ec10a296369e88e1c85c64"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2412.13171",
    "kind": "arxiv",
    "version": 1
  }
}