{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7C5VKZ4OHOK7RRDFBMRMBXYWD2","short_pith_number":"pith:7C5VKZ4O","schema_version":"1.0","canonical_sha256":"f8bb55678e3b95f8c4650b22c0df161e873a74509fbd751be471f9dd5953e44c","source":{"kind":"arxiv","id":"2509.08865","version":1},"attestation_state":"computed","paper":{"title":"TraceRAG: A LLM-Based Framework for Explainable Android Malware Detection and Behavior Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Guangyu Zhang, Kun Sun, Peiyan Xiao, Shiyu Sun, Xixuan Wang, Yanhai Xiong","submitted_at":"2025-09-10T06:07:12Z","abstract_excerpt":"Sophisticated evasion tactics in malicious Android applications, combined with their intricate behavioral semantics, enable attackers to conceal malicious logic within legitimate functions, underscoring the critical need for robust and in-depth analysis frameworks. However, traditional analysis techniques often fail to recover deeply hidden behaviors or provide human-readable justifications for their decisions. Inspired by advances in large language models (LLMs), we introduce TraceRAG, a retrieval-augmented generation (RAG) framework that bridges natural language queries and Java code to deli"},"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":"2509.08865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-09-10T06:07:12Z","cross_cats_sorted":[],"title_canon_sha256":"fee5084147bd5f41b5da64261f7e7bdcf700d9bf4a7a2fe49703ff35b2645357","abstract_canon_sha256":"bfcffdf1df897cf72bd7b87846205cfd3d930a34c44bf3257ac4deecd4781015"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:38.247911Z","signature_b64":"IOqfEttVDtiXsuiabt/wWvan4LEwCBHC6E03RNZ6lN1GANsbfckxB6lDGXDmrOfR8/qYGA+hJAkm5ONKprWJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8bb55678e3b95f8c4650b22c0df161e873a74509fbd751be471f9dd5953e44c","last_reissued_at":"2026-07-05T12:08:38.247393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:38.247393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TraceRAG: A LLM-Based Framework for Explainable Android Malware Detection and Behavior Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Guangyu Zhang, Kun Sun, Peiyan Xiao, Shiyu Sun, Xixuan Wang, Yanhai Xiong","submitted_at":"2025-09-10T06:07:12Z","abstract_excerpt":"Sophisticated evasion tactics in malicious Android applications, combined with their intricate behavioral semantics, enable attackers to conceal malicious logic within legitimate functions, underscoring the critical need for robust and in-depth analysis frameworks. However, traditional analysis techniques often fail to recover deeply hidden behaviors or provide human-readable justifications for their decisions. Inspired by advances in large language models (LLMs), we introduce TraceRAG, a retrieval-augmented generation (RAG) framework that bridges natural language queries and Java code to deli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08865","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/2509.08865/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":"2509.08865","created_at":"2026-07-05T12:08:38.247458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08865v1","created_at":"2026-07-05T12:08:38.247458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08865","created_at":"2026-07-05T12:08:38.247458+00:00"},{"alias_kind":"pith_short_12","alias_value":"7C5VKZ4OHOK7","created_at":"2026-07-05T12:08:38.247458+00:00"},{"alias_kind":"pith_short_16","alias_value":"7C5VKZ4OHOK7RRDF","created_at":"2026-07-05T12:08:38.247458+00:00"},{"alias_kind":"pith_short_8","alias_value":"7C5VKZ4O","created_at":"2026-07-05T12:08:38.247458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05807","citing_title":"LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00297","citing_title":"Trident: Improving Malware Detection with LLMs and Behavioral Features","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2","json":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2.json","graph_json":"https://pith.science/api/pith-number/7C5VKZ4OHOK7RRDFBMRMBXYWD2/graph.json","events_json":"https://pith.science/api/pith-number/7C5VKZ4OHOK7RRDFBMRMBXYWD2/events.json","paper":"https://pith.science/paper/7C5VKZ4O"},"agent_actions":{"view_html":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2","download_json":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2.json","view_paper":"https://pith.science/paper/7C5VKZ4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08865&json=true","fetch_graph":"https://pith.science/api/pith-number/7C5VKZ4OHOK7RRDFBMRMBXYWD2/graph.json","fetch_events":"https://pith.science/api/pith-number/7C5VKZ4OHOK7RRDFBMRMBXYWD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2/action/storage_attestation","attest_author":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2/action/author_attestation","sign_citation":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2/action/citation_signature","submit_replication":"https://pith.science/pith/7C5VKZ4OHOK7RRDFBMRMBXYWD2/action/replication_record"}},"created_at":"2026-07-05T12:08:38.247458+00:00","updated_at":"2026-07-05T12:08:38.247458+00:00"}