{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FYJQYRQOM4WRRJB2I2A4WBNRYZ","short_pith_number":"pith:FYJQYRQO","schema_version":"1.0","canonical_sha256":"2e130c460e672d18a43a4681cb05b1c6472d3ec3479e900986ecb6c4139af064","source":{"kind":"arxiv","id":"2607.06619","version":1},"attestation_state":"computed","paper":{"title":"HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Hanwei Fan, Jiang Xu, Wei Zhang, Xiaofeng Zhou, Yangdi Lyu, Ya Wang, Zhenguo Liu","submitted_at":"2026-07-07T09:27:30Z","abstract_excerpt":"Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing. We propose HiFuzz, a novel hierarchical reinforcement learning framework that replaces mutation with a structured, two-layer generation process: a Program Agent for global layout and a Basic Block Agent for precise instruction filling. To overcome reward sparsity, HiFuzz integrates an adaptive coverage reward mechanism and a semantic-aware basic block encoder providing intrinsic feedback. Extensive evaluations on three real-world RISC-V cores demonstrate t"},"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":"2607.06619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-07-07T09:27:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"80420a2fbca48d233c30fa43b4255a8543549dae04d8de3b22f1cdea0e49ae74","abstract_canon_sha256":"e263e662811aae542aaf75a1084547b0a71ffabe099659ea255d47161771abdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:20.599485Z","signature_b64":"TkA8+JLYmpweEv1irYnvJ3IHKatDXHA30RP1/a/OhUu8BuoCVZtp8nOUj7XdcleyphnVNj2rNGuxry9X/423AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e130c460e672d18a43a4681cb05b1c6472d3ec3479e900986ecb6c4139af064","last_reissued_at":"2026-07-09T00:19:20.598962Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:20.598962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AR","authors_text":"Hanwei Fan, Jiang Xu, Wei Zhang, Xiaofeng Zhou, Yangdi Lyu, Ya Wang, Zhenguo Liu","submitted_at":"2026-07-07T09:27:30Z","abstract_excerpt":"Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing. We propose HiFuzz, a novel hierarchical reinforcement learning framework that replaces mutation with a structured, two-layer generation process: a Program Agent for global layout and a Basic Block Agent for precise instruction filling. To overcome reward sparsity, HiFuzz integrates an adaptive coverage reward mechanism and a semantic-aware basic block encoder providing intrinsic feedback. Extensive evaluations on three real-world RISC-V cores demonstrate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06619","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/2607.06619/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":"2607.06619","created_at":"2026-07-09T00:19:20.599036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.06619v1","created_at":"2026-07-09T00:19:20.599036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06619","created_at":"2026-07-09T00:19:20.599036+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYJQYRQOM4WR","created_at":"2026-07-09T00:19:20.599036+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYJQYRQOM4WRRJB2","created_at":"2026-07-09T00:19:20.599036+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYJQYRQO","created_at":"2026-07-09T00:19:20.599036+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/FYJQYRQOM4WRRJB2I2A4WBNRYZ","json":"https://pith.science/pith/FYJQYRQOM4WRRJB2I2A4WBNRYZ.json","graph_json":"https://pith.science/api/pith-number/FYJQYRQOM4WRRJB2I2A4WBNRYZ/graph.json","events_json":"https://pith.science/api/pith-number/FYJQYRQOM4WRRJB2I2A4WBNRYZ/events.json","paper":"https://pith.science/paper/FYJQYRQO"},"agent_actions":{"view_html":"https://pith.science/pith/FYJQYRQOM4WRRJB2I2A4WBNRYZ","download_json":"https://pith.science/pith/FYJQYRQOM4WRRJB2I2A4WBNRYZ.json","view_paper":"https://pith.science/paper/FYJQYRQO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.06619&json=true","fetch_graph":"https://pith.science/api/pith-number/FYJQYRQOM4WRRJB2I2A4WBNRYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FYJQYRQOM4WRRJB2I2A4WBNRYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYJQYRQOM4WRRJB2I2A4WBNRYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYJQYRQOM4WRRJB2I2A4WBNRYZ/action/storage_attestation","attest_author":"https://pith.science/pith/FYJQYRQOM4WRRJB2I2A4WBNRYZ/action/author_attestation","sign_citation":"https://pith.science/pith/FYJQYRQOM4WRRJB2I2A4WBNRYZ/action/citation_signature","submit_replication":"https://pith.science/pith/FYJQYRQOM4WRRJB2I2A4WBNRYZ/action/replication_record"}},"created_at":"2026-07-09T00:19:20.599036+00:00","updated_at":"2026-07-09T00:19:20.599036+00:00"}