{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5HYM2CB6BUJKIHFU6IZ3Z2FWNC","short_pith_number":"pith:5HYM2CB6","schema_version":"1.0","canonical_sha256":"e9f0cd083e0d12a41cb4f233bce8b668bcc6451819b07eba363e6a1db13549c6","source":{"kind":"arxiv","id":"2606.20373","version":1},"attestation_state":"computed","paper":{"title":"AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jie Ren, Jie Zheng, Zepeng Li, Zhanyong Tang, Zheng Wang","submitted_at":"2026-06-18T15:35:40Z","abstract_excerpt":"Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a multi-agent framework for compiler performance tuning that uses compiler and runtime evidence to guide LLM-generated optimization decisions. Rather than treating the compiler as a black box like prior auto-tuning schemes, AutoPass opens up the compiler to the LLM, enabling it to query compiler-internal optimization states and analyze the intermediate representation to o"},"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":"2606.20373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-18T15:35:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0632884db923128a2835f604ccd1d3770b96619a26e3269d12cca596434f67e6","abstract_canon_sha256":"269deb58c5998e177d1ac9a79c938e280bcee86e8b4f1b9328d6bd9e7f41db96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:10.401710Z","signature_b64":"965eZceckjtmvLaKe39BGNcXkHNVZhi/0DcaASZo0eYlq3MsoTtAgHYbFvCXKOT+3PotaELxqe+PD4CLOIwDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9f0cd083e0d12a41cb4f233bce8b668bcc6451819b07eba363e6a1db13549c6","last_reissued_at":"2026-06-19T16:13:10.401338Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:10.401338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jie Ren, Jie Zheng, Zepeng Li, Zhanyong Tang, Zheng Wang","submitted_at":"2026-06-18T15:35:40Z","abstract_excerpt":"Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and noisy runtime measurements. We present AutoPass, a multi-agent framework for compiler performance tuning that uses compiler and runtime evidence to guide LLM-generated optimization decisions. Rather than treating the compiler as a black box like prior auto-tuning schemes, AutoPass opens up the compiler to the LLM, enabling it to query compiler-internal optimization states and analyze the intermediate representation to o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20373","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/2606.20373/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":"2606.20373","created_at":"2026-06-19T16:13:10.401400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20373v1","created_at":"2026-06-19T16:13:10.401400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20373","created_at":"2026-06-19T16:13:10.401400+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HYM2CB6BUJK","created_at":"2026-06-19T16:13:10.401400+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HYM2CB6BUJKIHFU","created_at":"2026-06-19T16:13:10.401400+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HYM2CB6","created_at":"2026-06-19T16:13:10.401400+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/5HYM2CB6BUJKIHFU6IZ3Z2FWNC","json":"https://pith.science/pith/5HYM2CB6BUJKIHFU6IZ3Z2FWNC.json","graph_json":"https://pith.science/api/pith-number/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/graph.json","events_json":"https://pith.science/api/pith-number/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/events.json","paper":"https://pith.science/paper/5HYM2CB6"},"agent_actions":{"view_html":"https://pith.science/pith/5HYM2CB6BUJKIHFU6IZ3Z2FWNC","download_json":"https://pith.science/pith/5HYM2CB6BUJKIHFU6IZ3Z2FWNC.json","view_paper":"https://pith.science/paper/5HYM2CB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20373&json=true","fetch_graph":"https://pith.science/api/pith-number/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/graph.json","fetch_events":"https://pith.science/api/pith-number/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/action/storage_attestation","attest_author":"https://pith.science/pith/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/action/author_attestation","sign_citation":"https://pith.science/pith/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/action/citation_signature","submit_replication":"https://pith.science/pith/5HYM2CB6BUJKIHFU6IZ3Z2FWNC/action/replication_record"}},"created_at":"2026-06-19T16:13:10.401400+00:00","updated_at":"2026-06-19T16:13:10.401400+00:00"}