Pith Number

pith:JUP2Q7U5

pith:2025:JUP2Q7U5OJMPVWDHDC4JXKLRS5

not attested not anchored not stored refs resolved

ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems

Bryan Landers, Francois Chollet, Gregory Kamradt, Henry Pinkard, Mike Knoop

ARC-AGI-2 introduces an expanded set of tasks to evaluate higher levels of abstract reasoning in AI systems.

arxiv:2505.11831 v2 · 2025-05-17 · 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{JUP2Q7U5OJMPVWDHDC4JXKLRS5}

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

ARC-AGI-2 incorporates a newly curated and expanded set of tasks specifically designed to provide a more granular signal to assess abstract reasoning and problem-solving abilities at higher levels of fluid intelligence.

C2weakest assumption

The newly selected tasks genuinely require higher levels of fluid intelligence with only minimal prior knowledge, and the human testing protocol produces a reliable and representative baseline.

C3one line summary

ARC-AGI-2 adds a larger, more complex set of tasks to the original ARC-AGI benchmark to give finer-grained measurement of fluid intelligence in AI.

References

13 extracted · 13 resolved · 0 Pith anchors

[1] ARC Prize - Leaderboard.https://arcprize.org/leaderboard

[2] ARC Prize - Policy.https://arcprize.org/policy

[3] Kaggle competition 2020

[4] Lab42 competi- tion 2022

[5] Lab42 competi- tion 2023

Formal links

3 machine-checked theorem links

Cited by

30 papers in Pith

MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?

Generative Recursive Reasoning

Open-World Evaluations for Measuring Frontier AI Capabilities

Language models fail at extended rule following

Generative Recursive Reasoning

Receipt and verification

First computed	2026-05-17T23:38:50.833466Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4d1fa87e9d7258fad86718b89ba97197530ba15f60f9eb57cc3f5466b683aef2

Aliases

arxiv: 2505.11831 · arxiv_version: 2505.11831v2 · doi: 10.48550/arxiv.2505.11831 · pith_short_12: JUP2Q7U5OJMP · pith_short_16: JUP2Q7U5OJMPVWDH · pith_short_8: JUP2Q7U5

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/JUP2Q7U5OJMPVWDHDC4JXKLRS5 \
  | 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: 4d1fa87e9d7258fad86718b89ba97197530ba15f60f9eb57cc3f5466b683aef2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c666d70bf85b4a5989194f51c6434f3e73d3397e9c1081c732e66dc8f0811ec8",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-05-17T04:34:48Z",
    "title_canon_sha256": "597cec621d6cb1f3586f0bdb55926f5783a602101251a516d1835619aa5bbd88"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.11831",
    "kind": "arxiv",
    "version": 2
  }
}