{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ICRATJUQA72VC3ZDVQK4APDRLW","short_pith_number":"pith:ICRATJUQ","schema_version":"1.0","canonical_sha256":"40a209a69007f5516f23ac15c03c715d9cc12fdf18921da2d14d312bdab26d4e","source":{"kind":"arxiv","id":"2406.12806","version":1},"attestation_state":"computed","paper":{"title":"Identifying Performance-Sensitive Configurations in Software Systems through Code Analysis with LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dong Jae Kim, Tse-Hsun Chen, Zehao Wang","submitted_at":"2024-06-18T17:22:48Z","abstract_excerpt":"Configuration settings are essential for tailoring software behavior to meet specific performance requirements. However, incorrect configurations are widespread, and identifying those that impact system performance is challenging due to the vast number and complexity of possible settings. In this work, we present PerfSense, a lightweight framework that leverages Large Language Models (LLMs) to efficiently identify performance-sensitive configurations with minimal overhead. PerfSense employs LLM agents to simulate interactions between developers and performance engineers using advanced promptin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.12806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-18T17:22:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f05f22b822749754703793902e17781a4958d89ba60354ce386e8c95c5defd6","abstract_canon_sha256":"5cbc12819f5731713cd823443c44d6b310d70fe527901c56f9b62f847ba35240"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:51.467448Z","signature_b64":"G23Or+C2aF8hctFPLdoctHQWa7iFbJQLdxJoxQGVHXtsjrzo45hBOKTBHdTyEiLmm1mgK0sSalcd5NlO64K7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40a209a69007f5516f23ac15c03c715d9cc12fdf18921da2d14d312bdab26d4e","last_reissued_at":"2026-07-05T08:33:51.467043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:51.467043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifying Performance-Sensitive Configurations in Software Systems through Code Analysis with LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Dong Jae Kim, Tse-Hsun Chen, Zehao Wang","submitted_at":"2024-06-18T17:22:48Z","abstract_excerpt":"Configuration settings are essential for tailoring software behavior to meet specific performance requirements. However, incorrect configurations are widespread, and identifying those that impact system performance is challenging due to the vast number and complexity of possible settings. In this work, we present PerfSense, a lightweight framework that leverages Large Language Models (LLMs) to efficiently identify performance-sensitive configurations with minimal overhead. PerfSense employs LLM agents to simulate interactions between developers and performance engineers using advanced promptin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12806","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.12806/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.12806","created_at":"2026-07-05T08:33:51.467100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12806v1","created_at":"2026-07-05T08:33:51.467100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12806","created_at":"2026-07-05T08:33:51.467100+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICRATJUQA72V","created_at":"2026-07-05T08:33:51.467100+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICRATJUQA72VC3ZD","created_at":"2026-07-05T08:33:51.467100+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICRATJUQ","created_at":"2026-07-05T08:33:51.467100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.13766","citing_title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW","json":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW.json","graph_json":"https://pith.science/api/pith-number/ICRATJUQA72VC3ZDVQK4APDRLW/graph.json","events_json":"https://pith.science/api/pith-number/ICRATJUQA72VC3ZDVQK4APDRLW/events.json","paper":"https://pith.science/paper/ICRATJUQ"},"agent_actions":{"view_html":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW","download_json":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW.json","view_paper":"https://pith.science/paper/ICRATJUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12806&json=true","fetch_graph":"https://pith.science/api/pith-number/ICRATJUQA72VC3ZDVQK4APDRLW/graph.json","fetch_events":"https://pith.science/api/pith-number/ICRATJUQA72VC3ZDVQK4APDRLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW/action/storage_attestation","attest_author":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW/action/author_attestation","sign_citation":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW/action/citation_signature","submit_replication":"https://pith.science/pith/ICRATJUQA72VC3ZDVQK4APDRLW/action/replication_record"}},"created_at":"2026-07-05T08:33:51.467100+00:00","updated_at":"2026-07-05T08:33:51.467100+00:00"}