Pith Number

pith:OV6P2JTV

pith:2026:OV6P2JTV7LJPILFH6UXU4QI52A

not attested not anchored not stored refs pending

Unified Deployment-Aware Evaluation of Open Reasoning Language Models

Ge Wang, Md Motaleb Hossen Manik

Accuracy-efficiency tradeoffs in reasoning LLMs depend jointly on architecture, prompting protocol, and task rather than sparse activation alone.

arxiv:2604.07035 v2 · 2026-04-08 · 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{OV6P2JTV7LJPILFH6UXU4QI52A}

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

These results show that sparse activation alone does not guarantee the best practical operating point: observed accuracy-efficiency tradeoffs depend jointly on architecture, prompting protocol, and task composition.

C2weakest assumption

That the four chosen benchmarks and three prompting strategies are representative enough of real-world reasoning workloads to support general claims about accuracy-efficiency tradeoffs.

C3one line summary

Gemma-4-E4B with few-shot chain-of-thought reaches the highest weighted accuracy of 0.675 at 14.9 GB VRAM, while the larger Gemma-4-26B-A4B MoE model scores 0.663 but uses 48.1 GB.

Cited by

2 papers in Pith

Simple Self-Conditioning Adaptation for Masked Diffusion Models

From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification

Receipt and verification

First computed	2026-05-20T01:05:12.591934Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

757cfd2675fad2f42ca7f52f4e411dd01459177b3dd47ff7c13db0f7d27b9898

Aliases

arxiv: 2604.07035 · arxiv_version: 2604.07035v2 · doi: 10.48550/arxiv.2604.07035 · pith_short_12: OV6P2JTV7LJP · pith_short_16: OV6P2JTV7LJPILFH · pith_short_8: OV6P2JTV

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/OV6P2JTV7LJPILFH6UXU4QI52A \
  | 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: 757cfd2675fad2f42ca7f52f4e411dd01459177b3dd47ff7c13db0f7d27b9898

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e6c8d5e5a812be39a8d8a0da79f389eafe196787038db3dc44cf29431659897d",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-04-08T12:50:52Z",
    "title_canon_sha256": "8ca16ca16ac778a2a73492f3ad4f744c08b705095d09c9592cb55b11a4a06d3b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.07035",
    "kind": "arxiv",
    "version": 2
  }
}