{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UL6WVUXQTVWNUI23PSMVWXKFVH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fa532640c38646009388c505477026c4e135dadada1909213ad4c37f501d8074","cross_cats_sorted":["cs.AI","cs.CR","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T09:10:52Z","title_canon_sha256":"c4ead843a15903fce555ac3ac1058a34027cc94910b7eab8afd3ab38b42603c4"},"schema_version":"1.0","source":{"id":"2509.02113","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02113","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02113v2","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02113","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"UL6WVUXQTVWN","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"UL6WVUXQTVWNUI23","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"UL6WVUXQ","created_at":"2026-05-26T02:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:4fe964b4eac9ec87b31f0243eb1e8b03862d84a547f5bf2684bfa177ed213b44","target":"graph","created_at":"2026-05-26T02:05:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.02113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of graph-based malware analysis is critically limited by the absence of large-scale datasets that capture the inherent hierarchical structure of software. Existing methods often oversimplify programs into single level graphs, failing to model the crucial semantic relationship between high-level functional interactions and low-level instruction logic. To bridge this gap, we introduce \\dataset, the largest public hierarchical graph dataset for malware analysis, comprising over \\textbf{200M} Control Flow Graphs (CFGs) nested within \\textbf{595K} Function Call Graphs (FCGs). This t","authors_text":"Han Chen, Hanchen Wang, Hongmei Chen, Lu Qin, Wenjie Zhang, Ying Zhang","cross_cats":["cs.AI","cs.CR","cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T09:10:52Z","title":"HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02113","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a09cdb089a59191bcec38d38d0a3054571f76718876e2bf0a622914a4d41e465","target":"record","created_at":"2026-05-26T02:05:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fa532640c38646009388c505477026c4e135dadada1909213ad4c37f501d8074","cross_cats_sorted":["cs.AI","cs.CR","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T09:10:52Z","title_canon_sha256":"c4ead843a15903fce555ac3ac1058a34027cc94910b7eab8afd3ab38b42603c4"},"schema_version":"1.0","source":{"id":"2509.02113","kind":"arxiv","version":2}},"canonical_sha256":"a2fd6ad2f09d6cda235b7c995b5d45a9c4180fb56f2ae9c35eac713367f85c5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2fd6ad2f09d6cda235b7c995b5d45a9c4180fb56f2ae9c35eac713367f85c5e","first_computed_at":"2026-05-26T02:05:01.847949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:01.847949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z61oxwXcSwe0HX7sT5BdBzL0WmE1nWYjHFB1tx6WEMHc/9eN/Yy9ZkegcUp8x3FPIsCPV5dLMoXlIW5bWAr/Bw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:01.848563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02113","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a09cdb089a59191bcec38d38d0a3054571f76718876e2bf0a622914a4d41e465","sha256:4fe964b4eac9ec87b31f0243eb1e8b03862d84a547f5bf2684bfa177ed213b44"],"state_sha256":"ee323973dfa3650732577a7afd7f0bab8e8297d0eee4362c2b46a794a4680bc5"}