Pith Number

pith:UHF6IZ5R

pith:2026:UHF6IZ5RCMR5B6NPRQU4FA7KQQ

not attested not anchored not stored refs pending

Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents

Chenyu Zhao, Chetan Bansal, Dan Pei, Minghua Ma, Saravan Rajmohan, Shenglin Zhang, Wenwei Gu, Yihang Lin, Yongqian Sun, Zhimin Chen

PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools.

arxiv:2605.08717 v2 · 2026-05-09 · cs.SE · 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{UHF6IZ5RCMR5B6NPRQU4FA7KQQ}

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

On 257 initially unresolved cases, PROBE achieves 65.37% Top-1 diagnosis accuracy and a 21.79% recovery rate, outperforming the strongest non-PROBE baseline by 43.58 and 12.45 percentage points.

C2weakest assumption

That the Guidance Gate can reliably produce diagnosis-derived guidance that is both evidence-grounded and executable within the unchanged scope of the agent's existing policy, toolset, and execution budget.

C3one line summary

PROBE structures runtime telemetry into diagnoses and evidence-grounded guidance, raising recovery rates by 12.45 points over baselines on 257 unresolved software repair and AIOps cases.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation

Receipt and verification

First computed	2026-06-08T01:04:07.071982Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a1cbe467b11323d0f9af8c29c283ea840c6b9511fa49994e64054388c3eb3841

Aliases

arxiv: 2605.08717 · arxiv_version: 2605.08717v2 · doi: 10.48550/arxiv.2605.08717 · pith_short_12: UHF6IZ5RCMR5 · pith_short_16: UHF6IZ5RCMR5B6NP · pith_short_8: UHF6IZ5R

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/UHF6IZ5RCMR5B6NPRQU4FA7KQQ \
  | 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: a1cbe467b11323d0f9af8c29c283ea840c6b9511fa49994e64054388c3eb3841

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1b080022cb5a99fef2f3c76cab995cba4114931db8992531ecd03d3f9c1140c1",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SE",
    "submitted_at": "2026-05-09T06:02:08Z",
    "title_canon_sha256": "7684fc60f87469cfd0f508d9be12c37293cd6f19c56ff84b07106587cdb61984"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.08717",
    "kind": "arxiv",
    "version": 2
  }
}