{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OWKL3RMN4VTLSQZU53OKRVJEOO","short_pith_number":"pith:OWKL3RMN","schema_version":"1.0","canonical_sha256":"7594bdc58de566b94334eedca8d52473a9cd9772573782f0661ca3828ef70798","source":{"kind":"arxiv","id":"2608.06183","version":1},"attestation_state":"computed","paper":{"title":"MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changwen Xing, Chen Bai, Chenxu Niu, Guangyuan Gao, Jia Xiong, Jieran Cui, Ming Ling, Runkai Li, Tao Xie, Xinlai Wan, Xi Wang, Yifan Zhang, Ying Wang, Yusheng Hua","submitted_at":"2026-08-06T15:43:31Z","abstract_excerpt":"Microarchitecture design space exploration suffers from expansive search spaces and expensive PPA evaluation, leaving only a small simulation budget for design decision-making. Existing methods perform blind search without considering microarchitectural dependencies and fail to learn from the iterative search effectively, leading to wasted evaluations and weak Pareto convergence. In this paper, we propose MicroEvo, a knowledge-guided framework that couples off-the-shelf LLMs with Monte Carlo Tree Search (MCTS) for multi-objective microarchitecture optimization. MicroEvo combines LLM-driven evo"},"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":"2608.06183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T15:43:31Z","cross_cats_sorted":[],"title_canon_sha256":"e3bd0575b907136e97f6d3e93f8731201aebb0af86233dee4794ad73acf70c2b","abstract_canon_sha256":"d7c755fe9ac7336c7c1ec615e3e3396a93e5b9f69c7d485aa31cc7e226c6c644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:40:53.815166Z","signature_b64":"G20Aj07x0aTx2IUK4DrGpBzg5dIIRfiC18icolugBPsPdZKeCJo3lm2IvT45I120w8gFJfdItUf1hFLK832UCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7594bdc58de566b94334eedca8d52473a9cd9772573782f0661ca3828ef70798","last_reissued_at":"2026-08-07T01:40:53.813519Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:40:53.813519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changwen Xing, Chen Bai, Chenxu Niu, Guangyuan Gao, Jia Xiong, Jieran Cui, Ming Ling, Runkai Li, Tao Xie, Xinlai Wan, Xi Wang, Yifan Zhang, Ying Wang, Yusheng Hua","submitted_at":"2026-08-06T15:43:31Z","abstract_excerpt":"Microarchitecture design space exploration suffers from expansive search spaces and expensive PPA evaluation, leaving only a small simulation budget for design decision-making. Existing methods perform blind search without considering microarchitectural dependencies and fail to learn from the iterative search effectively, leading to wasted evaluations and weak Pareto convergence. In this paper, we propose MicroEvo, a knowledge-guided framework that couples off-the-shelf LLMs with Monte Carlo Tree Search (MCTS) for multi-objective microarchitecture optimization. MicroEvo combines LLM-driven evo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06183","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/2608.06183/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":"2608.06183","created_at":"2026-08-07T01:40:53.816139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06183v1","created_at":"2026-08-07T01:40:53.816139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06183","created_at":"2026-08-07T01:40:53.816139+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWKL3RMN4VTL","created_at":"2026-08-07T01:40:53.816139+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWKL3RMN4VTLSQZU","created_at":"2026-08-07T01:40:53.816139+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWKL3RMN","created_at":"2026-08-07T01:40:53.816139+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/OWKL3RMN4VTLSQZU53OKRVJEOO","json":"https://pith.science/pith/OWKL3RMN4VTLSQZU53OKRVJEOO.json","graph_json":"https://pith.science/api/pith-number/OWKL3RMN4VTLSQZU53OKRVJEOO/graph.json","events_json":"https://pith.science/api/pith-number/OWKL3RMN4VTLSQZU53OKRVJEOO/events.json","paper":"https://pith.science/paper/OWKL3RMN"},"agent_actions":{"view_html":"https://pith.science/pith/OWKL3RMN4VTLSQZU53OKRVJEOO","download_json":"https://pith.science/pith/OWKL3RMN4VTLSQZU53OKRVJEOO.json","view_paper":"https://pith.science/paper/OWKL3RMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06183&json=true","fetch_graph":"https://pith.science/api/pith-number/OWKL3RMN4VTLSQZU53OKRVJEOO/graph.json","fetch_events":"https://pith.science/api/pith-number/OWKL3RMN4VTLSQZU53OKRVJEOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWKL3RMN4VTLSQZU53OKRVJEOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWKL3RMN4VTLSQZU53OKRVJEOO/action/storage_attestation","attest_author":"https://pith.science/pith/OWKL3RMN4VTLSQZU53OKRVJEOO/action/author_attestation","sign_citation":"https://pith.science/pith/OWKL3RMN4VTLSQZU53OKRVJEOO/action/citation_signature","submit_replication":"https://pith.science/pith/OWKL3RMN4VTLSQZU53OKRVJEOO/action/replication_record"}},"created_at":"2026-08-07T01:40:53.816139+00:00","updated_at":"2026-08-07T01:40:53.816139+00:00"}