{
  "schema_version": "0.6.0",
  "paper_id": "software-mining-investigating-correlation-between-source-code-features-and-michrobenchmark-s-ste",
  "page_url": "https://naser.github.io/research-publications/papers/software-mining-investigating-correlation-between-source-code-features-and-michrobenchmark-s-ste/",
  "title": "Software Mining - Investigating Correlation between Source Code Features and Michrobenchmark's Steady State",
  "title_variants": [
    "Software Mining - Investigating Correlation between Source Code Features and Microbenchmark's Steady State"
  ],
  "authors": [
    "Amirmahdi Khosravi Tabrizi",
    "Naser Ezzati-Jivan"
  ],
  "author_details": [
    {
      "name": "Amirmahdi Khosravi Tabrizi",
      "orcid": "https://orcid.org/0000-0002-6498-9319",
      "profile_url": "https://dblp.org/pid/344/3160.html"
    },
    {
      "name": "Naser Ezzati-Jivan",
      "orcid": "https://orcid.org/0000-0003-1435-6297",
      "profile_url": "https://naser.github.io/"
    }
  ],
  "publication": {
    "year": 2023,
    "venue": "Companion of the 2023 ACM/SPEC International Conference on Performance Engineering (ICPE '23 Companion)",
    "type": "conference paper",
    "publication_date": "2023-04-15",
    "online_date": "2023-04-15",
    "print_date": "2023-04-15",
    "volume": null,
    "issue": null,
    "pages": "107-111",
    "article_number": null,
    "publisher": "ACM",
    "issn": [],
    "isbn": [],
    "crossref_type": "proceedings-article"
  },
  "publication_type": "conference paper",
  "status": "published_with_public_full_text",
  "canonical_source_url": "https://doi.org/10.1145/3578245.3584695",
  "source_record_id": "software-mining-investigating-correlation-between-source-code-features-and-michrobenchmark-s-ste-bd15de158b",
  "identifiers": {
    "doi": "10.1145/3578245.3584695"
  },
  "abstract": null,
  "abstract_source": null,
  "abstract_available": false,
  "scholar_eligibility": {
    "eligible": false,
    "basis": "not-eligible",
    "note": "The page is a discovery record; it does not claim Google Scholar article-host eligibility."
  },
  "description": "The study examines whether static source-code features are associated with the steady-state behavior of Java microbenchmarks during JVM warmup.",
  "evidence_level": "full-text-reviewed",
  "evidence": {
    "source_basis": "full-text-reviewed",
    "coverage": "material paper sections",
    "summary_origin": "AI-assisted catalog editorial summary",
    "review_status": "catalog-reviewed; paper-author approval pending",
    "verified_on": "2026-08-09",
    "sources": [
      {
        "note": "Private full PDF read: pdf-evidence/notes/parallel-batch-02-software-mining-investigating-correlation-between-source-code-features-and-michrobenchmark-s-ste-bd15de158b.md"
      },
      {
        "note": "Software Mining PDF pp. 1-4: JMH, 586 results from 30 Java projects, srcML/Lizard features, steady-state labels, group counts, and Apriori confidences"
      },
      {
        "note": "Local PDF hash verified: D883BDDA4B750A791CF29D206A9FD20C3E75F6BF21276761B563206134FF43DC"
      },
      {
        "note": "Public source: https://research.spec.org/icpe_proceedings/2023/companion/p107.pdf"
      }
    ]
  },
  "summary": {
    "core_contribution": "The study examines whether static source-code features are associated with the steady-state behavior of Java microbenchmarks during JVM warmup.",
    "problem": "JVM JIT compilation makes Java microbenchmark results unstable during warmup; the study asks whether static source features are associated with reaching steady state (p. 1).",
    "method": "The study uses 586 JMH results from 30 open-source Java projects and 10 forks per benchmark method. srcML and Lizard extract 11 static features; dynamic features include DNNSF, DANCP, and DANITS. Twenty-seven records were excluded after feature-extraction errors. Manual comparisons at benchmark-method/file level are followed by Apriori descriptive association mining (pp. 2-4).",
    "findings": "At benchmark-method level, 321 cases are steady, 236 inconsistent, and 2 non-steady. Reported Apriori associations are BMNFC_HIGH -> DNNSF_ZERO with confidence 0.63 and BMLOC_HIGH -> DNNSF_ZERO with confidence 0.61; the paper interprets higher function count/LOC as associated with zero non-steady forks (p. 4).",
    "limitations": "This is exploratory association analysis, not causal evidence. Only two benchmark methods are in the non-steady class, 27 records were removed, and independent replication/generalization across JVMs, hardware, languages, and workloads are not established. The paper does not specify a complete OS/hardware/JVM configuration.",
    "future_work": "Add source features for system calls, threading, locks, and other function-call types (p. 4)."
  },
  "tags": [
    "performance-analysis",
    "performance-engineering",
    "machine-learning"
  ],
  "keywords": [
    "Java Microbenchmark Harness",
    "JMH",
    "srcML",
    "Lizard",
    "Apriori",
    "Java microbenchmarks",
    "JVM warmup",
    "steady state",
    "source-code features",
    "BMNFC",
    "BMLOC",
    "DNNSF"
  ],
  "versions": [
    {
      "id": "published-version",
      "label": "Published version",
      "relation": "version-of-record",
      "title": "Software Mining - Investigating Correlation between Source Code Features and Michrobenchmark's Steady State",
      "url": "https://doi.org/10.1145/3578245.3584695",
      "pdf_url": null,
      "status": "published",
      "canonical_for_citation": true
    },
    {
      "id": "public-conference-pdf",
      "label": "Public conference PDF",
      "relation": "source-record",
      "title": "Software Mining - Investigating Correlation between Source Code Features and Michrobenchmark's Steady State",
      "url": "https://research.spec.org/icpe_proceedings/2023/companion/p107.pdf",
      "pdf_url": "https://research.spec.org/icpe_proceedings/2023/companion/p107.pdf",
      "status": "public_full_text",
      "canonical_for_citation": false
    }
  ],
  "access": {
    "status": "published_with_public_full_text",
    "note": "The DOI is the canonical citation target; the public conference PDF is linked as an external source and is not redistributed here.",
    "license": null
  },
  "resources": {
    "code": null,
    "data": "https://github.com/amirmahdiKhosravi/ACM-SPEC-ICPE-2023-DataTrack",
    "slides": null,
    "demo": null
  },
  "citation_guidance": {
    "when_to_cite": "Cite this paper when your work uses or compares exploratory mining of source-code LOC/function-count features against JMH steady-state indicators.",
    "points": [
      "For exploratory mining of source-code LOC/function-count features against JMH steady-state indicators.",
      "For the BMNFC/BMLOC to DNNSF_ZERO associations and their reported 0.63/0.61 confidence values, explicitly as non-causal associations.",
      "For the 30-project/586-result/10-fork corpus and the DNNSF, DANCP, and DANITS feature vocabulary."
    ],
    "canonical_version_id": "published-version"
  },
  "provenance": {
    "metadata_verified_on": "2026-08-09",
    "metadata_source": [
      "Private full PDF read: pdf-evidence/notes/parallel-batch-02-software-mining-investigating-correlation-between-source-code-features-and-michrobenchmark-s-ste-bd15de158b.md",
      "Software Mining PDF pp. 1-4: JMH, 586 results from 30 Java projects, srcML/Lizard features, steady-state labels, group counts, and Apriori confidences",
      "Local PDF hash verified: D883BDDA4B750A791CF29D206A9FD20C3E75F6BF21276761B563206134FF43DC",
      "Public source: https://research.spec.org/icpe_proceedings/2023/companion/p107.pdf"
    ],
    "summary_written_by": "AI-assisted",
    "summary_verified_by": "full-text-grounded catalog review; author approval pending",
    "linked_preprint_record": null,
    "author_order_note": null
  },
  "batch": {
    "phase": 2,
    "batch_label": "expanded forty-paper release",
    "status": "included_in_expanded_catalog",
    "selected_at": "2026-08-09"
  }
}