Pith Number

pith:XC46HSFB

pith:2026:XC46HSFBDQEO3FT2RVX65HMIWN

not attested not anchored not stored refs pending

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation

Anoop Rachakonda, Daehyeok Kim, Geon-Woo Kim, Joon Ha Kim

Dooly reuses profiled LLM operation latencies across model configurations by tracing input-dimension origins in a single inference pass.

arxiv:2605.07985 v2 · 2026-05-08 · cs.DC · 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{XC46HSFBDQEO3FT2RVX65HMIWN}

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 two GPU platforms, three attention backends, and diverse model architectures, Dooly achieves simulation accuracy within 5% MAPE for TTFT and 8% for TPOT while reducing profiling GPU-hours by 56.4% across 12 models compared to the existing profiling approach.

C2weakest assumption

That labeling input dimensions by origin via taint propagation during one inference pass is sufficient to identify all reusable operations across arbitrary model configurations, and that the resulting latency database plus regression models generalize without hidden dependencies or post-hoc tuning.

C3one line summary

Dooly reduces LLM inference profiling costs by 56.4% via configuration-agnostic taint-based labeling and selective database reuse, delivering simulation accuracy within 5% MAPE for TTFT and 8% for TPOT across 12 models.

Receipt and verification

First computed	2026-05-22T01:04:05.469584Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b8b9e3c8a11c08ed967a8d6fee9d88b3720dc03a369c9f993c71a982301ed297

Aliases

arxiv: 2605.07985 · arxiv_version: 2605.07985v2 · doi: 10.48550/arxiv.2605.07985 · pith_short_12: XC46HSFBDQEO · pith_short_16: XC46HSFBDQEO3FT2 · pith_short_8: XC46HSFB

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/XC46HSFBDQEO3FT2RVX65HMIWN \
  | 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: b8b9e3c8a11c08ed967a8d6fee9d88b3720dc03a369c9f993c71a982301ed297

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "834ef73fc769407acf33c8e36ffc97a63b6e35819da18dbebc1f198915b12784",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.DC",
    "submitted_at": "2026-05-08T16:44:47Z",
    "title_canon_sha256": "d776310694207b5c955b74fc08e4fdfe53a7d02b736402c7ec58d1ee6ba53c83"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.07985",
    "kind": "arxiv",
    "version": 2
  }
}