{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FFUVTZ2PBIEVJPMU6SJVXSORR5","short_pith_number":"pith:FFUVTZ2P","schema_version":"1.0","canonical_sha256":"296959e74f0a0954bd94f4935bc9d18f585f218c3351bfd8c942f708f7ef8933","source":{"kind":"arxiv","id":"2503.19449","version":3},"attestation_state":"computed","paper":{"title":"VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.SE","authors_text":"Jianjiang Zeng, Kan Wu, Long Cheng, Lu Li, Rodrigo C. O. Rocha, Tianyi Liu, Wei Wei, Xianwei Zhang, Yaoqing Gao, Zhongchun Zheng","submitted_at":"2025-03-25T08:39:35Z","abstract_excerpt":"Auto-vectorization is a fundamental optimization for modern compilers to exploit SIMD parallelism. However, state-of-the-art approaches still struggle to handle intricate code patterns, often requiring manual hints or domain-specific expertise. Large language models (LLMs), with their ability to capture intricate patterns, provide a promising solution, yet their effective application in compiler optimizations remains an open challenge due to issues such as hallucinations and a lack of domain-specific reasoning. In this paper, we present VecTrans, a novel framework that leverages LLMs to enhanc"},"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":"2503.19449","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-25T08:39:35Z","cross_cats_sorted":["cs.AI","cs.LG","cs.PF"],"title_canon_sha256":"13d77f2e906b4480a26d921171350a473ba543ca46810345f342dc86064577cd","abstract_canon_sha256":"07ac978a2083c2712f939ea4b8ca9b1c92aefa886719d5aa62ba072da79dd621"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:45.690296Z","signature_b64":"sFqM54nJ9FE0yB4SYrfTN3NrILMRXkD/uxKFBrUwVlntzM7fHjav+uV1WnVMF3v6ihN7Cuisd9byRAnJs+HlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296959e74f0a0954bd94f4935bc9d18f585f218c3351bfd8c942f708f7ef8933","last_reissued_at":"2026-07-05T11:15:45.689809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:45.689809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.PF"],"primary_cat":"cs.SE","authors_text":"Jianjiang Zeng, Kan Wu, Long Cheng, Lu Li, Rodrigo C. O. Rocha, Tianyi Liu, Wei Wei, Xianwei Zhang, Yaoqing Gao, Zhongchun Zheng","submitted_at":"2025-03-25T08:39:35Z","abstract_excerpt":"Auto-vectorization is a fundamental optimization for modern compilers to exploit SIMD parallelism. However, state-of-the-art approaches still struggle to handle intricate code patterns, often requiring manual hints or domain-specific expertise. Large language models (LLMs), with their ability to capture intricate patterns, provide a promising solution, yet their effective application in compiler optimizations remains an open challenge due to issues such as hallucinations and a lack of domain-specific reasoning. In this paper, we present VecTrans, a novel framework that leverages LLMs to enhanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19449","kind":"arxiv","version":3},"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/2503.19449/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":"2503.19449","created_at":"2026-07-05T11:15:45.689870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19449v3","created_at":"2026-07-05T11:15:45.689870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19449","created_at":"2026-07-05T11:15:45.689870+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFUVTZ2PBIEV","created_at":"2026-07-05T11:15:45.689870+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFUVTZ2PBIEVJPMU","created_at":"2026-07-05T11:15:45.689870+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFUVTZ2P","created_at":"2026-07-05T11:15:45.689870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20373","citing_title":"AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17978","citing_title":"AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13927","citing_title":"AI Coding Agents Need Better Compiler Remarks","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5","json":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5.json","graph_json":"https://pith.science/api/pith-number/FFUVTZ2PBIEVJPMU6SJVXSORR5/graph.json","events_json":"https://pith.science/api/pith-number/FFUVTZ2PBIEVJPMU6SJVXSORR5/events.json","paper":"https://pith.science/paper/FFUVTZ2P"},"agent_actions":{"view_html":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5","download_json":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5.json","view_paper":"https://pith.science/paper/FFUVTZ2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19449&json=true","fetch_graph":"https://pith.science/api/pith-number/FFUVTZ2PBIEVJPMU6SJVXSORR5/graph.json","fetch_events":"https://pith.science/api/pith-number/FFUVTZ2PBIEVJPMU6SJVXSORR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5/action/storage_attestation","attest_author":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5/action/author_attestation","sign_citation":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5/action/citation_signature","submit_replication":"https://pith.science/pith/FFUVTZ2PBIEVJPMU6SJVXSORR5/action/replication_record"}},"created_at":"2026-07-05T11:15:45.689870+00:00","updated_at":"2026-07-05T11:15:45.689870+00:00"}