Pith Number

pith:TRRS5IT2

pith:2022:TRRS5IT2GHTQ4SJS3552DBVHYS

not attested not anchored not stored refs resolved

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Aakanksha Chowdhery, Denny Zhou, Ed H. Chi, Hyung Won Chung, Jason Wei, Mirac Suzgun, Nathanael Sch\"arli, Nathan Scales, Quoc V. Le, Sebastian Gehrmann, Yi Tay

Chain-of-thought prompting lets current models surpass average humans on 17 of 23 BIG-Bench Hard tasks.

arxiv:2210.09261 v1 · 2022-10-17 · cs.CL · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{TRRS5IT2GHTQ4SJS3552DBVHYS}

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

Applying chain-of-thought (CoT) prompting to BBH tasks enables PaLM to surpass the average human-rater performance on 10 of the 23 tasks, and Codex (code-davinci-002) to surpass the average human-rater performance on 17 of the 23 tasks.

C2weakest assumption

That the average human-rater scores reported in the original BIG-Bench paper constitute a stable and fair external benchmark against which model performance can be directly compared without additional controls for prompt sensitivity or rater variability.

C3one line summary

Chain-of-thought prompting enables large language models to surpass average human performance on 17 of 23 challenging BIG-Bench tasks.

References

42 extracted · 42 resolved · 15 Pith anchors

[1] Program Synthesis with Large Language Models · arXiv:2108.07732

[2] Language models are few-shot learners 1901

[3] Evaluating Large Language Models Trained on Code · arXiv:2107.03374

[4] Smith, and Tao Yu

[5] PaLM: Scaling Language Modeling with Pathways · arXiv:2204.02311

Cited by

120 papers in Pith

Unified Audio Intelligence Without Regressing on Text Intelligence

Improved Large Language Diffusion Models

SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference

Beyond Prediction: Tail-Aware Scheduling for LLM Inference

DRIFT: Refining Instruction Data via On-Policy Data Attribution

Receipt and verification

First computed	2026-07-05T05:07:20.597704Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9c632ea27a31e70e4932df7ba186a7c49aec1ad1af2f8b945a131ecc28216e5f

Aliases

arxiv: 2210.09261 · arxiv_version: 2210.09261v1 · doi: 10.48550/arxiv.2210.09261 · pith_short_12: TRRS5IT2GHTQ · pith_short_16: TRRS5IT2GHTQ4SJS · pith_short_8: TRRS5IT2

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/TRRS5IT2GHTQ4SJS3552DBVHYS \
  | 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: 9c632ea27a31e70e4932df7ba186a7c49aec1ad1af2f8b945a131ecc28216e5f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "19b2f797d21adaeb164d1511924c3c019f94f58cbabe0e47ceb3b95b35741065",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2022-10-17T17:08:26Z",
    "title_canon_sha256": "18ef4a27704c509abd2f75c40a443aeda786c987da847eea56365bf08165d9b6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2210.09261",
    "kind": "arxiv",
    "version": 1
  }
}