{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VRK3Z6WZKJVJ4DNJAJ24443OUQ","short_pith_number":"pith:VRK3Z6WZ","schema_version":"1.0","canonical_sha256":"ac55bcfad9526a9e0da90275ce736ea415f9aab70ee518883de116bd35407366","source":{"kind":"arxiv","id":"2406.18379","version":3},"attestation_state":"computed","paper":{"title":"MALSIGHT: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CR","authors_text":"Cheng Wang, Guoshun Nan, Haolang Lu, Hongrui Peng, Jiaoyang Cui, Shengli Pan, Songtao Wang, Weifei Jin, Xiaofeng Tao","submitted_at":"2024-06-26T14:21:09Z","abstract_excerpt":"Binary malware summarization aims to automatically generate human-readable descriptions of malware behaviors from executable files, facilitating tasks like malware cracking and detection. Previous methods based on Large Language Models (LLMs) have shown great promise. However, they still face significant issues, including poor usability, inaccurate explanations,and incomplete summaries, primarily due to the obscure pseudocode structure and the lack of malware training summaries. Further, calling relationships between functions, which involve the rich interactions within a binary malware, remai"},"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":"2406.18379","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-06-26T14:21:09Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"4a7413d067d12ab2a0e64cdedde16d9dbbee21d9fbbc0c42556b96d0a627932f","abstract_canon_sha256":"f64dcb494e797657912abdca109c1708edff6e53c1204126c3c32d7fb8db465b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:31.149953Z","signature_b64":"1gpSDf9rmBb+ak8aeMTd928RNuLe3mqsCzkTQUdnVKHVPKnGs6UHSDLokun5KFlt8VVUDcymRQ5dfeNjnYZfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac55bcfad9526a9e0da90275ce736ea415f9aab70ee518883de116bd35407366","last_reissued_at":"2026-07-05T11:22:31.149140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:31.149140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MALSIGHT: Exploring Malicious Source Code and Benign Pseudocode for Iterative Binary Malware Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CR","authors_text":"Cheng Wang, Guoshun Nan, Haolang Lu, Hongrui Peng, Jiaoyang Cui, Shengli Pan, Songtao Wang, Weifei Jin, Xiaofeng Tao","submitted_at":"2024-06-26T14:21:09Z","abstract_excerpt":"Binary malware summarization aims to automatically generate human-readable descriptions of malware behaviors from executable files, facilitating tasks like malware cracking and detection. Previous methods based on Large Language Models (LLMs) have shown great promise. However, they still face significant issues, including poor usability, inaccurate explanations,and incomplete summaries, primarily due to the obscure pseudocode structure and the lack of malware training summaries. Further, calling relationships between functions, which involve the rich interactions within a binary malware, remai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18379","kind":"arxiv","version":3},"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/2406.18379/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":"2406.18379","created_at":"2026-07-05T11:22:31.149193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18379v3","created_at":"2026-07-05T11:22:31.149193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18379","created_at":"2026-07-05T11:22:31.149193+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRK3Z6WZKJVJ","created_at":"2026-07-05T11:22:31.149193+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRK3Z6WZKJVJ4DNJ","created_at":"2026-07-05T11:22:31.149193+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRK3Z6WZ","created_at":"2026-07-05T11:22:31.149193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20436","citing_title":"Multi-View Decompilation for LLM-Based Malware Classification","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ","json":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ.json","graph_json":"https://pith.science/api/pith-number/VRK3Z6WZKJVJ4DNJAJ24443OUQ/graph.json","events_json":"https://pith.science/api/pith-number/VRK3Z6WZKJVJ4DNJAJ24443OUQ/events.json","paper":"https://pith.science/paper/VRK3Z6WZ"},"agent_actions":{"view_html":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ","download_json":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ.json","view_paper":"https://pith.science/paper/VRK3Z6WZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18379&json=true","fetch_graph":"https://pith.science/api/pith-number/VRK3Z6WZKJVJ4DNJAJ24443OUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VRK3Z6WZKJVJ4DNJAJ24443OUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ/action/storage_attestation","attest_author":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ/action/author_attestation","sign_citation":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ/action/citation_signature","submit_replication":"https://pith.science/pith/VRK3Z6WZKJVJ4DNJAJ24443OUQ/action/replication_record"}},"created_at":"2026-07-05T11:22:31.149193+00:00","updated_at":"2026-07-05T11:22:31.149193+00:00"}