{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T4RS5ZXHZYJTGILFAA5GYEGKMY","short_pith_number":"pith:T4RS5ZXH","schema_version":"1.0","canonical_sha256":"9f232ee6e7ce13332165003a6c10ca661130006f71a3464476f199577d5b8f07","source":{"kind":"arxiv","id":"2605.30359","version":1},"attestation_state":"computed","paper":{"title":"Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG","cs.PF","cs.SE","cs.SY","eess.SY"],"primary_cat":"cs.NE","authors_text":"Da Chen, Huiling Zhen, Kecheng Huang, Lihao Yin, Mingxuan Yuan, Xing Li, Zili Shao, Zixuan Huang","submitted_at":"2026-05-08T03:41:54Z","abstract_excerpt":"Generating high-performance GPU kernels remains challenging due to the need for both correctness and hardware-aware optimization. While large language models (LLMs) show promise in code generation, they often fail to produce kernels that are both correct and efficient.\n  We propose Kernel Foundry, a diagnosis-driven evolutionary framework for automatic GPU kernel optimization. Our method combines expert-guided, retrieval-augmented initialization with a multi-island evolutionary search, where candidate kernels are iteratively refined using structured diagnostic feedback. A centralized experienc"},"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":"2605.30359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-08T03:41:54Z","cross_cats_sorted":["cs.DC","cs.LG","cs.PF","cs.SE","cs.SY","eess.SY"],"title_canon_sha256":"ca800bb0693a5011d880370481c04fccad7c16a195d46ba9ed09f136d14d0f99","abstract_canon_sha256":"97ea35cf8b9d8c2c4cec543f1730f2885bdbeb21f89fdb0cb7526a80593fecd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T00:02:06.642519Z","signature_b64":"iG0zU6rTRO3f4BHS92/NjDruKm7jEp3QcVxmEW+APHCVF62SfApX0De2hdMXoj5iPocD5G4k2P2BJzV12Hx2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f232ee6e7ce13332165003a6c10ca661130006f71a3464476f199577d5b8f07","last_reissued_at":"2026-06-01T00:02:06.641597Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T00:02:06.641597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG","cs.PF","cs.SE","cs.SY","eess.SY"],"primary_cat":"cs.NE","authors_text":"Da Chen, Huiling Zhen, Kecheng Huang, Lihao Yin, Mingxuan Yuan, Xing Li, Zili Shao, Zixuan Huang","submitted_at":"2026-05-08T03:41:54Z","abstract_excerpt":"Generating high-performance GPU kernels remains challenging due to the need for both correctness and hardware-aware optimization. While large language models (LLMs) show promise in code generation, they often fail to produce kernels that are both correct and efficient.\n  We propose Kernel Foundry, a diagnosis-driven evolutionary framework for automatic GPU kernel optimization. Our method combines expert-guided, retrieval-augmented initialization with a multi-island evolutionary search, where candidate kernels are iteratively refined using structured diagnostic feedback. A centralized experienc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30359","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/2605.30359/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":"2605.30359","created_at":"2026-06-01T00:02:06.641724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30359v1","created_at":"2026-06-01T00:02:06.641724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30359","created_at":"2026-06-01T00:02:06.641724+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4RS5ZXHZYJT","created_at":"2026-06-01T00:02:06.641724+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4RS5ZXHZYJTGILF","created_at":"2026-06-01T00:02:06.641724+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4RS5ZXH","created_at":"2026-06-01T00:02:06.641724+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/T4RS5ZXHZYJTGILFAA5GYEGKMY","json":"https://pith.science/pith/T4RS5ZXHZYJTGILFAA5GYEGKMY.json","graph_json":"https://pith.science/api/pith-number/T4RS5ZXHZYJTGILFAA5GYEGKMY/graph.json","events_json":"https://pith.science/api/pith-number/T4RS5ZXHZYJTGILFAA5GYEGKMY/events.json","paper":"https://pith.science/paper/T4RS5ZXH"},"agent_actions":{"view_html":"https://pith.science/pith/T4RS5ZXHZYJTGILFAA5GYEGKMY","download_json":"https://pith.science/pith/T4RS5ZXHZYJTGILFAA5GYEGKMY.json","view_paper":"https://pith.science/paper/T4RS5ZXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30359&json=true","fetch_graph":"https://pith.science/api/pith-number/T4RS5ZXHZYJTGILFAA5GYEGKMY/graph.json","fetch_events":"https://pith.science/api/pith-number/T4RS5ZXHZYJTGILFAA5GYEGKMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4RS5ZXHZYJTGILFAA5GYEGKMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4RS5ZXHZYJTGILFAA5GYEGKMY/action/storage_attestation","attest_author":"https://pith.science/pith/T4RS5ZXHZYJTGILFAA5GYEGKMY/action/author_attestation","sign_citation":"https://pith.science/pith/T4RS5ZXHZYJTGILFAA5GYEGKMY/action/citation_signature","submit_replication":"https://pith.science/pith/T4RS5ZXHZYJTGILFAA5GYEGKMY/action/replication_record"}},"created_at":"2026-06-01T00:02:06.641724+00:00","updated_at":"2026-06-01T00:02:06.641724+00:00"}