Pith Number

pith:J3EEN5IP

pith:2026:J3EEN5IPVDLTUCLQ2QRSWHL6YO

not attested not anchored not stored refs resolved

Effort as Ceiling, Not Dial: Reasoning Budget Does Not Modulate Cognitive Cost Alignment Between Humans and Large Reasoning Models

Tianhong Wang, Yueqing Hu

Large reasoning models keep the same human cognitive cost alignment no matter the effort budget set at inference.

arxiv:2605.16938 v1 · 2026-05-16 · cs.CL · cs.AI · q-bio.NC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{J3EEN5IPVDLTUCLQ2QRSWHL6YO}

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

Across GPT-OSS-20B and GPT-OSS-120B, three effort levels, and six reasoning tasks, within-task and cross-task alignment remain invariant: Bayes Factors lean toward the null, and mean alignment is numerically near-identical across conditions.

C2weakest assumption

The effort parameter is assumed to modulate real-time reasoning allocation, yet the manipulation check shows it only imposes an upper budget on generation length rather than driving dynamic allocation.

C3one line summary

Reasoning budget in LRMs functions as a generation ceiling rather than a real-time dial, leaving cognitive cost alignment with humans invariant across effort levels and supporting a training-time compiled account.

References

23 extracted · 23 resolved · 5 Pith anchors

[1] gpt-oss-120b & gpt-oss-20b Model Card 2025 · arXiv:2508.10925

[2] Anderson, J. R. (1982). Acquisition of cognitive skill.Psy- chological Review,89(4), 369–406 1982

[3] Ashcraft, M. H. (1992). Cognitive arithmetic: A review of data and theory.Cognition,44(1–2), 75–106. Binz,M.,&Schulz,E.(2023).Usingcognitivepsychologyto understand GPT-3.Proceedings of the National Ac 1992

[4] Campbell, J. I. D., & Xue, Q. (2001). Cognitive arithmetic across cultures.Journal of Experimental Psychology: Gen- eral,130(2), 299–315 2001

[5] Think deep, not just long: Measuring llm reasoning effort via deep-thinking tokens 2026

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:31.857017Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4ec846f50fa8d73a0970d4232b1d7ec3971d7ac92522626c2a787a55a4336a09

Aliases

arxiv: 2605.16938 · arxiv_version: 2605.16938v1 · doi: 10.48550/arxiv.2605.16938 · pith_short_12: J3EEN5IPVDLT · pith_short_16: J3EEN5IPVDLTUCLQ · pith_short_8: J3EEN5IP

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/J3EEN5IPVDLTUCLQ2QRSWHL6YO \
  | 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: 4ec846f50fa8d73a0970d4232b1d7ec3971d7ac92522626c2a787a55a4336a09

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "bf0e3d37e09d680b4b5762b85fe65d4a1efbc9e690e64d52f1e2ae07123598dd",
    "cross_cats_sorted": [
      "cs.AI",
      "q-bio.NC"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-16T11:20:01Z",
    "title_canon_sha256": "57b730c77b58618b216862cec37976289c4363f93f512a50390a3b907d796a5e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16938",
    "kind": "arxiv",
    "version": 1
  }
}