retrieval · rank-crash-clustered-suspicious-files-llm-repair-context TEC-0289 · proposed

Rank crash-clustered suspicious files as LLM repair context

Cluster crash reports by stack-trace similarity, score candidate files by proximity to the crash point, bucket specificity and in-group frequency, and put the top-ranked files' source plus a representative stack trace into a zero-shot repai

Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.

Cluster crash reports by stack-trace similarity, score candidate files by proximity to the crash point, bucket specificity and in-group frequency, and put the top-ranked files' source plus a representative stack trace into a zero-shot repai Filed by the drafting stage from Integrating Crash Report Mining and LLMs for Bug Localization and Repair: An Industrial Report (2609.04483) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Manual two-rater grading (Cohen's kappa 0.88 localization, 0.51 repair) of 760 responses on 38 bugs against developer corrective commits; ablation across four prompt configurations and five LLMs on an 8-bug subset. No no-ranking, no-clustering baseline on the full dataset; no test-based execution.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Finding and fixing a fault in existing code

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.

Code

No repository linked yet. Contribute one.

Sources

Either way, bring evidence: a link, or what you saw.

Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.