{ "schema_version": "0.6.0", "paper_id": "execution-trace-reconstruction-using-diffusion-based-generative-models", "page_url": "https://naser.github.io/research-publications/papers/execution-trace-reconstruction-using-diffusion-based-generative-models/", "title": "Execution Trace Reconstruction Using Diffusion-Based Generative Models", "title_variants": [], "authors": [ "Madeline Janecek", "Naser Ezzati-Jivan", "Abdelwahab Hamou-Lhadj" ], "author_details": [ { "name": "Madeline Janecek", "orcid": null, "profile_url": "https://dblp.org/pid/307/5913.html" }, { "name": "Naser Ezzati-Jivan", "orcid": "https://orcid.org/0000-0003-1435-6297", "profile_url": "https://naser.github.io/" }, { "name": "Abdelwahab Hamou-Lhadj", "orcid": "https://orcid.org/0000-0002-3319-5006", "profile_url": "https://dblp.org/pid/70/2136.html" } ], "publication": { "year": 2025, "venue": "IEEE/ACM International Conference on Software Engineering (ICSE)", "type": "conference paper", "publication_date": "2025-04-26", "online_date": null, "print_date": "2025-04-26", "volume": null, "issue": null, "pages": "1077-1088", "article_number": null, "publisher": "IEEE", "issn": [], "isbn": [], "crossref_type": "proceedings-article" }, "publication_type": "conference paper", "status": "published_with_public_full_text", "canonical_source_url": "https://doi.org/10.1109/ICSE55347.2025.00063", "source_record_id": "execution-trace-reconstruction-using-diffusion-based-generative-models-fc4b2482f1", "identifiers": { "doi": "10.1109/ICSE55347.2025.00063" }, "abstract": null, "abstract_source": "Author-hosted published-paper PDF reviewed; abstract paraphrased for this catalog.", "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 paper reconstructs missing system-call events in execution traces with diffusion and structured state-space generative models.", "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": "ICSE published PDF: nine PTS workloads, PTS 6.2.2, LTTng 2.8, Debian kernel, Xeon/32 GB/SSD platform, and 32 runs per benchmark" }, { "note": "ICSE published PDF: integer event encoding, DiffWave/SSSDS4/SSSDSA/CSDIS4 configurations, blackout protocol, accuracy, perfect rate, ROUGE-L, and LSTM baseline" }, { "note": "ICSE published PDF: controlled-loss limitation, functional-plausibility example, and future work" }, { "note": "Local thesis/manuscript and published-paper PDF are retained as distinct version evidence; local hashes are recorded in pdf-evidence/extraction-manifest.json" } ] }, "summary": { "core_contribution": "The paper reconstructs missing system-call events in execution traces with diffusion and structured state-space generative models.", "problem": "Ring-buffer overflow and resource constraints can discard contiguous system-call events, weakening trace-based diagnosis, anomaly detection, and performance analysis. Increasing buffers or blocking the application changes collection cost or system behavior.", "method": "Nine Phoronix Test Suite datasets are collected from LTTng 2.8 traces on Debian with kernel 4.4.0-1-amd64. System calls are filtered from kernel events, sorted by training frequency, and encoded as integer IDs. DiffWave, SSSDS4, SSSDSA, and CSDIS4 diffusion/imputation models reconstruct artificial contiguous blackouts; accuracy, perfect rate, and ROUGE-L are compared with an LSTM next-event baseline.", "findings": "The setup uses PTS 6.2.23, 32 runs per benchmark, 10,000 training and 500 test sequences per dataset, sequence lengths up to 200, and blackout sizes 5/10/20/30/40. For a ten-event blackout, SSSDS4 averages 81.62% accuracy, 74.27% perfect rate, and 90.84% ROUGE-L; SSSDSA reports 81.71%, 74.38%, and 90.90%. The LSTM reaches 29.61% average accuracy for five-event reconstruction. At blackout size 40, average SSSDS4 accuracy is 77.11%; the paper reports degradation once missingness exceeds about 20%.", "limitations": "Events are removed artificially rather than recovered from naturally lost traces. Exact-match metrics do not measure functional plausibility, and results are bounded by nine PTS workloads, one Debian/kernel environment, model parameter choices, and system-call-only representations. Timing, arguments, and authentic loss are not evaluated.", "future_work": "Add event timing, arguments, and duration; test authentic loss; explore other state-space/diffusion/transformer models; use expert or LLM-based functional evaluation; and assess usefulness in diagnosis, anomaly detection, and optimization." }, "tags": [ "kernel-tracing", "system-tracing", "trace-analysis", "trace-reduction", "performance-analysis" ], "keywords": [ "execution trace reconstruction", "trace imputation", "diffusion models", "DiffWave", "SSSDS4", "SSSDSA", "CSDIS4", "structured state-space", "system-call sequences", "LTTng", "Phoronix Test Suite", "ROUGE-L", "perfect rate", "missing events", "ring-buffer overflow" ], "versions": [ { "id": "published-version", "label": "Published version", "relation": "version-of-record", "title": "Execution Trace Reconstruction Using Diffusion-Based Generative Models", "url": "https://doi.org/10.1109/ICSE55347.2025.00063", "pdf_url": null, "status": "published", "canonical_for_citation": true }, { "id": "public-full-text", "label": "Public full text", "relation": "source-record", "title": "Execution Trace Reconstruction Using Diffusion-Based Generative Models", "url": "https://users.encs.concordia.ca/~abdelw/papers/ICSE2025_TraceConstruction.pdf", "pdf_url": "https://users.encs.concordia.ca/~abdelw/papers/ICSE2025_TraceConstruction.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 full-text or author-manuscript link is external and the PDF is not redistributed here.", "license": null }, "resources": { "code": "https://github.com/janecekm/TraceReconstruction", "data": null, "slides": null, "demo": null }, "citation_guidance": { "when_to_cite": "Cite this paper when your work uses or compares diffusion-based imputation of contiguous missing system-call events in execution traces.", "points": [ "diffusion-based imputation of contiguous missing system-call events in execution traces.", "the SSSDS4 comparison across nine PTS workloads using exact accuracy, perfect rate, and ROUGE-L.", "the finding that structured state-space diffusion models outperform the LSTM baseline on multi-event reconstruction, with the artificial-blackout caveat.", "the need to add timing/arguments and functional-plausibility metrics to trace reconstruction." ], "canonical_version_id": "published-version" }, "provenance": { "metadata_verified_on": "2026-08-09", "metadata_source": [ "ICSE published PDF: nine PTS workloads, PTS 6.2.2, LTTng 2.8, Debian kernel, Xeon/32 GB/SSD platform, and 32 runs per benchmark", "ICSE published PDF: integer event encoding, DiffWave/SSSDS4/SSSDSA/CSDIS4 configurations, blackout protocol, accuracy, perfect rate, ROUGE-L, and LSTM baseline", "ICSE published PDF: controlled-loss limitation, functional-plausibility example, and future work", "Local thesis/manuscript and published-paper PDF are retained as distinct version evidence; local hashes are recorded in pdf-evidence/extraction-manifest.json" ], "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" } }