{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DTDH5IKNQWVFKPH32SMS4O4J5C","short_pith_number":"pith:DTDH5IKN","schema_version":"1.0","canonical_sha256":"1cc67ea14d85aa553cfbd4992e3b89e8b922adc79cbb2b342c77584b5ac70c22","source":{"kind":"arxiv","id":"2607.27231","version":1},"attestation_state":"computed","paper":{"title":"KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guang Liu, Jialing Zhang, Jian Tao, Peiyu Zang, Wentao Zhang, Yichen Yuan, Yonghua Lin","submitted_at":"2026-07-22T12:40:11Z","abstract_excerpt":"Large language models (LLMs) have significantly increased the demand for efficient accelerator kernels, but kernel development remains a highly specialized and labor-intensive task. The recent rise of LLMs and agentic frameworks offers a promising pathway toward automatic kernel generation. However, despite rapid progress, there is still no comprehensive benchmark to rigorously evaluate LLM-generated kernels across diverse operator sources or heterogeneous hardware platforms. We present KernelGenBench, a unified benchmark for systematically evaluating LLM- and agent-generated Triton kernels ac"},"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":"2607.27231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-22T12:40:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1b8ffd83d8575f4f87f86fe8d953b2ebaa0c18c429baa1b3a3e630533899bacb","abstract_canon_sha256":"d8abb658d880b8ffff02b4e03abc9e1ea2fded5b50dc1d74e9da59acab9247d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cc67ea14d85aa553cfbd4992e3b89e8b922adc79cbb2b342c77584b5ac70c22","last_reissued_at":"2026-07-31T00:10:22.541706Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:22.541706Z"},"graph_snapshot":{"paper":{"title":"KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Guang Liu, Jialing Zhang, Jian Tao, Peiyu Zang, Wentao Zhang, Yichen Yuan, Yonghua Lin","submitted_at":"2026-07-22T12:40:11Z","abstract_excerpt":"Large language models (LLMs) have significantly increased the demand for efficient accelerator kernels, but kernel development remains a highly specialized and labor-intensive task. The recent rise of LLMs and agentic frameworks offers a promising pathway toward automatic kernel generation. However, despite rapid progress, there is still no comprehensive benchmark to rigorously evaluate LLM-generated kernels across diverse operator sources or heterogeneous hardware platforms. We present KernelGenBench, a unified benchmark for systematically evaluating LLM- and agent-generated Triton kernels ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27231","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/2607.27231/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":"2607.27231","created_at":"2026-07-31T00:10:22.544038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27231v1","created_at":"2026-07-31T00:10:22.544038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27231","created_at":"2026-07-31T00:10:22.544038+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTDH5IKNQWVF","created_at":"2026-07-31T00:10:22.544038+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTDH5IKNQWVFKPH3","created_at":"2026-07-31T00:10:22.544038+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTDH5IKN","created_at":"2026-07-31T00:10:22.544038+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/DTDH5IKNQWVFKPH32SMS4O4J5C","json":"https://pith.science/pith/DTDH5IKNQWVFKPH32SMS4O4J5C.json","graph_json":"https://pith.science/api/pith-number/DTDH5IKNQWVFKPH32SMS4O4J5C/graph.json","events_json":"https://pith.science/api/pith-number/DTDH5IKNQWVFKPH32SMS4O4J5C/events.json","paper":"https://pith.science/paper/DTDH5IKN"},"agent_actions":{"view_html":"https://pith.science/pith/DTDH5IKNQWVFKPH32SMS4O4J5C","download_json":"https://pith.science/pith/DTDH5IKNQWVFKPH32SMS4O4J5C.json","view_paper":"https://pith.science/paper/DTDH5IKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27231&json=true","fetch_graph":"https://pith.science/api/pith-number/DTDH5IKNQWVFKPH32SMS4O4J5C/graph.json","fetch_events":"https://pith.science/api/pith-number/DTDH5IKNQWVFKPH32SMS4O4J5C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTDH5IKNQWVFKPH32SMS4O4J5C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTDH5IKNQWVFKPH32SMS4O4J5C/action/storage_attestation","attest_author":"https://pith.science/pith/DTDH5IKNQWVFKPH32SMS4O4J5C/action/author_attestation","sign_citation":"https://pith.science/pith/DTDH5IKNQWVFKPH32SMS4O4J5C/action/citation_signature","submit_replication":"https://pith.science/pith/DTDH5IKNQWVFKPH32SMS4O4J5C/action/replication_record"}},"created_at":"2026-07-31T00:10:22.544038+00:00","updated_at":"2026-07-31T00:10:22.544038+00:00"}