{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4YXZHENBD5LDIVUHXHSDQPC6QS","short_pith_number":"pith:4YXZHENB","schema_version":"1.0","canonical_sha256":"e62f9391a11f56345687b9e4383c5e84841dff67a884f416aa159b217620a9ac","source":{"kind":"arxiv","id":"2510.16384","version":2},"attestation_state":"computed","paper":{"title":"SemOpt: LLM-Driven Code Optimization via Rule-Based Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Qianyu Xiao, Yingfei Xiong, Yuan-An Xiao, Yuwei Zhao, Zhao Zhang","submitted_at":"2025-10-18T07:44:18Z","abstract_excerpt":"Automated code optimization improves program performance through refactoring, and recent studies leverage LLMs for this purpose. Existing approaches mine optimization commits from open-source codebases to build large-scale knowledge bases, then employ retrieval techniques such as BM25 to obtain relevant examples for hotspot code, guiding LLMs in optimization. However, semantically equivalent optimizations often appear in syntactically dissimilar code, so current retrieval methods fail to identify pertinent examples, leading to suboptimal results. To address these limitations, we propose SemOpt"},"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":"2510.16384","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-10-18T07:44:18Z","cross_cats_sorted":[],"title_canon_sha256":"a87bbd3e68f8acadf8aa420ae888409491a7f744dfa8610732c42a3d5fdd8817","abstract_canon_sha256":"6ffd000657dbe3d7ba3b350c84a24a91c0687e3bca04a47b80aa1cfb3fb5739c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:45.389006Z","signature_b64":"tLscU1Zzi0wGRw6QWiMuRqKSLuw3kdTeeKvE3liBzFYF7/U6A+4DUU5ujbW6/nG/FV/QLaHT7si/RGWx3uM4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e62f9391a11f56345687b9e4383c5e84841dff67a884f416aa159b217620a9ac","last_reissued_at":"2026-06-10T01:09:45.387993Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:45.387993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemOpt: LLM-Driven Code Optimization via Rule-Based Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Qianyu Xiao, Yingfei Xiong, Yuan-An Xiao, Yuwei Zhao, Zhao Zhang","submitted_at":"2025-10-18T07:44:18Z","abstract_excerpt":"Automated code optimization improves program performance through refactoring, and recent studies leverage LLMs for this purpose. Existing approaches mine optimization commits from open-source codebases to build large-scale knowledge bases, then employ retrieval techniques such as BM25 to obtain relevant examples for hotspot code, guiding LLMs in optimization. However, semantically equivalent optimizations often appear in syntactically dissimilar code, so current retrieval methods fail to identify pertinent examples, leading to suboptimal results. To address these limitations, we propose SemOpt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.16384","kind":"arxiv","version":2},"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/2510.16384/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":"2510.16384","created_at":"2026-06-10T01:09:45.388150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.16384v2","created_at":"2026-06-10T01:09:45.388150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.16384","created_at":"2026-06-10T01:09:45.388150+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YXZHENBD5LD","created_at":"2026-06-10T01:09:45.388150+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YXZHENBD5LDIVUH","created_at":"2026-06-10T01:09:45.388150+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YXZHENB","created_at":"2026-06-10T01:09:45.388150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20244","citing_title":"Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS","json":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS.json","graph_json":"https://pith.science/api/pith-number/4YXZHENBD5LDIVUHXHSDQPC6QS/graph.json","events_json":"https://pith.science/api/pith-number/4YXZHENBD5LDIVUHXHSDQPC6QS/events.json","paper":"https://pith.science/paper/4YXZHENB"},"agent_actions":{"view_html":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS","download_json":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS.json","view_paper":"https://pith.science/paper/4YXZHENB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.16384&json=true","fetch_graph":"https://pith.science/api/pith-number/4YXZHENBD5LDIVUHXHSDQPC6QS/graph.json","fetch_events":"https://pith.science/api/pith-number/4YXZHENBD5LDIVUHXHSDQPC6QS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS/action/storage_attestation","attest_author":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS/action/author_attestation","sign_citation":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS/action/citation_signature","submit_replication":"https://pith.science/pith/4YXZHENBD5LDIVUHXHSDQPC6QS/action/replication_record"}},"created_at":"2026-06-10T01:09:45.388150+00:00","updated_at":"2026-06-10T01:09:45.388150+00:00"}