{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2BAA6HIGWQ2UKSWAHERUO27V2Q","short_pith_number":"pith:2BAA6HIG","schema_version":"1.0","canonical_sha256":"d0400f1d06b435454ac03923476bf5d43516f8448a3ca2e3c9d55fb072aaec38","source":{"kind":"arxiv","id":"2607.20353","version":1},"attestation_state":"computed","paper":{"title":"Multi-Source and Cross-Scenario Strategy-Guided Code Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Qianyu Xiao, Ye Cui, Yijun Yu, Yingfei Xiong, Yuwei Zhao","submitted_at":"2026-07-22T16:38:56Z","abstract_excerpt":"Automated code optimization improves program performance by refactoring source code, and recent studies use LLMs to generate optimization patches. The newest approaches are strategy-guided: they summarize strategies from historical optimization commits as static analysis rules, and use these rules to match code locations for LLMs to optimize. However, these approaches have two limitations: (1) the strategies may come from other knowledge sources, such as textbooks and web pages, but the existing approaches cannot utilize them; (2) a strategy may be applicable to different scenarios, e.g., diff"},"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":"2607.20353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-22T16:38:56Z","cross_cats_sorted":[],"title_canon_sha256":"440bca559b38ea262ca98e849320875b3c6b96690f46e6c286c348eb771b5a29","abstract_canon_sha256":"8bc573acb006af5907611c283728bd2006c345a409a33d103ae1df334ea25ed1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:25:15.965452Z","signature_b64":"H3bwlYMK0VmZPQ/Pc9YkSAN21oZGmPcZsKPIAixZAQsgrBuo0KJfxuvvs0twr+Pe/XGWvgg2bEo/JIDZ/nfxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0400f1d06b435454ac03923476bf5d43516f8448a3ca2e3c9d55fb072aaec38","last_reissued_at":"2026-07-23T01:25:15.964607Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:25:15.964607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Source and Cross-Scenario Strategy-Guided Code Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Qianyu Xiao, Ye Cui, Yijun Yu, Yingfei Xiong, Yuwei Zhao","submitted_at":"2026-07-22T16:38:56Z","abstract_excerpt":"Automated code optimization improves program performance by refactoring source code, and recent studies use LLMs to generate optimization patches. The newest approaches are strategy-guided: they summarize strategies from historical optimization commits as static analysis rules, and use these rules to match code locations for LLMs to optimize. However, these approaches have two limitations: (1) the strategies may come from other knowledge sources, such as textbooks and web pages, but the existing approaches cannot utilize them; (2) a strategy may be applicable to different scenarios, e.g., diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20353","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/2607.20353/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":"2607.20353","created_at":"2026-07-23T01:25:15.965006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20353v1","created_at":"2026-07-23T01:25:15.965006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20353","created_at":"2026-07-23T01:25:15.965006+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BAA6HIGWQ2U","created_at":"2026-07-23T01:25:15.965006+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BAA6HIGWQ2UKSWA","created_at":"2026-07-23T01:25:15.965006+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BAA6HIG","created_at":"2026-07-23T01:25:15.965006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q","json":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q.json","graph_json":"https://pith.science/api/pith-number/2BAA6HIGWQ2UKSWAHERUO27V2Q/graph.json","events_json":"https://pith.science/api/pith-number/2BAA6HIGWQ2UKSWAHERUO27V2Q/events.json","paper":"https://pith.science/paper/2BAA6HIG"},"agent_actions":{"view_html":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q","download_json":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q.json","view_paper":"https://pith.science/paper/2BAA6HIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20353&json=true","fetch_graph":"https://pith.science/api/pith-number/2BAA6HIGWQ2UKSWAHERUO27V2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/2BAA6HIGWQ2UKSWAHERUO27V2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q/action/storage_attestation","attest_author":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q/action/author_attestation","sign_citation":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q/action/citation_signature","submit_replication":"https://pith.science/pith/2BAA6HIGWQ2UKSWAHERUO27V2Q/action/replication_record"}},"created_at":"2026-07-23T01:25:15.965006+00:00","updated_at":"2026-07-23T01:25:15.965006+00:00"}