{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UL6WVUXQTVWNUI23PSMVWXKFVH","short_pith_number":"pith:UL6WVUXQ","schema_version":"1.0","canonical_sha256":"a2fd6ad2f09d6cda235b7c995b5d45a9c4180fb56f2ae9c35eac713367f85c5e","source":{"kind":"arxiv","id":"2509.02113","version":2},"attestation_state":"computed","paper":{"title":"HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.SI"],"primary_cat":"cs.LG","authors_text":"Han Chen, Hanchen Wang, Hongmei Chen, Lu Qin, Wenjie Zhang, Ying Zhang","submitted_at":"2025-09-02T09:10:52Z","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"},"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":"2509.02113","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-02T09:10:52Z","cross_cats_sorted":["cs.AI","cs.CR","cs.SI"],"title_canon_sha256":"c4ead843a15903fce555ac3ac1058a34027cc94910b7eab8afd3ab38b42603c4","abstract_canon_sha256":"fa532640c38646009388c505477026c4e135dadada1909213ad4c37f501d8074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:01.848563Z","signature_b64":"Z61oxwXcSwe0HX7sT5BdBzL0WmE1nWYjHFB1tx6WEMHc/9eN/Yy9ZkegcUp8x3FPIsCPV5dLMoXlIW5bWAr/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2fd6ad2f09d6cda235b7c995b5d45a9c4180fb56f2ae9c35eac713367f85c5e","last_reissued_at":"2026-05-26T02:05:01.847949Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:01.847949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.SI"],"primary_cat":"cs.LG","authors_text":"Han Chen, Hanchen Wang, Hongmei Chen, Lu Qin, Wenjie Zhang, Ying Zhang","submitted_at":"2025-09-02T09:10:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02113","kind":"arxiv","version":2},"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/2509.02113/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":"2509.02113","created_at":"2026-05-26T02:05:01.848028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02113v2","created_at":"2026-05-26T02:05:01.848028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02113","created_at":"2026-05-26T02:05:01.848028+00:00"},{"alias_kind":"pith_short_12","alias_value":"UL6WVUXQTVWN","created_at":"2026-05-26T02:05:01.848028+00:00"},{"alias_kind":"pith_short_16","alias_value":"UL6WVUXQTVWNUI23","created_at":"2026-05-26T02:05:01.848028+00:00"},{"alias_kind":"pith_short_8","alias_value":"UL6WVUXQ","created_at":"2026-05-26T02:05:01.848028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.06894","citing_title":"McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH","json":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH.json","graph_json":"https://pith.science/api/pith-number/UL6WVUXQTVWNUI23PSMVWXKFVH/graph.json","events_json":"https://pith.science/api/pith-number/UL6WVUXQTVWNUI23PSMVWXKFVH/events.json","paper":"https://pith.science/paper/UL6WVUXQ"},"agent_actions":{"view_html":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH","download_json":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH.json","view_paper":"https://pith.science/paper/UL6WVUXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02113&json=true","fetch_graph":"https://pith.science/api/pith-number/UL6WVUXQTVWNUI23PSMVWXKFVH/graph.json","fetch_events":"https://pith.science/api/pith-number/UL6WVUXQTVWNUI23PSMVWXKFVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH/action/storage_attestation","attest_author":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH/action/author_attestation","sign_citation":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH/action/citation_signature","submit_replication":"https://pith.science/pith/UL6WVUXQTVWNUI23PSMVWXKFVH/action/replication_record"}},"created_at":"2026-05-26T02:05:01.848028+00:00","updated_at":"2026-05-26T02:05:01.848028+00:00"}