Pith Number

pith:LVIF2CDC

pith:2025:LVIF2CDCVEMAT56A6MVCSEPCWN

not attested not anchored not stored refs pending

Measuring AI Ability to Complete Long Software Tasks

Amy Deng, Ben West, Brian Goodrich, Chris Painter, Daniel M. Ziegler, David Rein, Elizabeth Barnes, Haoxing Du, Hjalmar Wijk, Joel Becker, Katharyn Garcia, Lawrence Chan, Lucas Jun Koba Sato, Luke Harold Miles, Max Hasin, Megan Kinniment, Nate Rush, Neev Parikh, Nikola Jurkovic, Ryan Bloom, Sami Jawhar, Seraphina Nix, Sydney von Arx, Tao Lin, Thomas Broadley, Thomas Kwa

arxiv:2503.14499 v4 · 2025-03-18 · cs.AI · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LVIF2CDCVEMAT56A6MVCSEPCWN}

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.

Cited by

47 papers in Pith

Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring

RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications

AI Integrity: Defending Against Backdoors and Secret Loyalties

Human vs Machine Mathematical Difficulty on Project Euler: An Experimental Analysis

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

Receipt and verification

First computed	2026-07-14T00:18:18.548212Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5d505d0862a91809f7c0f32a2911e2b37ff0e618dbc3ae2821a3b72f1d8147d2

Aliases

arxiv: 2503.14499 · arxiv_version: 2503.14499v4 · doi: 10.48550/arxiv.2503.14499 · pith_short_12: LVIF2CDCVEMA · pith_short_16: LVIF2CDCVEMAT56A · pith_short_8: LVIF2CDC

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/LVIF2CDCVEMAT56A6MVCSEPCWN \
  | 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: 5d505d0862a91809f7c0f32a2911e2b37ff0e618dbc3ae2821a3b72f1d8147d2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e702d008f561eedce194021837e05019ec617f99f259f86da88efe27237db942",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-03-18T17:59:31Z",
    "title_canon_sha256": "bc9b28b5968b80a4075a2ad5e4e139cc5c7d55e38872bcdda7135c58a6c4fe2f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.14499",
    "kind": "arxiv",
    "version": 4
  }
}