{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4WYABC5EIJ246BUFEH33LLRT3M","short_pith_number":"pith:4WYABC5E","schema_version":"1.0","canonical_sha256":"e5b0008ba44275cf068521f7b5ae33db268ccacf12706fd6a03292f68cafd3c6","source":{"kind":"arxiv","id":"2605.16455","version":1},"attestation_state":"computed","paper":{"title":"MalwarePT: A Binary-Level Foundation Model for Malware Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Christopher Kruegel, Giovanni Vigna, Hojjat Aghakhani, Kaie Chen, Roman Vasilenko, Saastha Vasan, Wenbo Guo, Yigitcan Kaya, Yuzhou Nie","submitted_at":"2026-05-15T05:31:59Z","abstract_excerpt":"Automated malware analysis increasingly relies on machine learning, yet most existing methods remain task-specific and depend on handcrafted features or narrowly scoped models. Recent developments in binary-level foundation models suggest a path toward reusable program representations, but their application to malware analysis remains underexplored, and most still operate at byte-level tokenization, limiting their ability to capture multi-byte code patterns.\n  In this work, we introduce MalwarePT, a binary-level foundation model for malware analysis built on a ModernBERT-style encoder and pret"},"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":"2605.16455","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-15T05:31:59Z","cross_cats_sorted":[],"title_canon_sha256":"90f246620be6b40066f2b54ef1a321cc2f591af1fcc0b1ab34399e717117e3ea","abstract_canon_sha256":"9e99c93520a948084ffc5afd18d3819a472d12cbfa8103de1a2f854515ff9ea1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:23.020916Z","signature_b64":"X3RcpjEHH8cU0+Ur2RLpWCDhiGarhZiCvuEk5slbiGEkUxdVHaekWdO0gI/sVz1k0N1nrofowTsZZ3PR27d6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5b0008ba44275cf068521f7b5ae33db268ccacf12706fd6a03292f68cafd3c6","last_reissued_at":"2026-05-20T00:02:23.020083Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:23.020083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MalwarePT: A Binary-Level Foundation Model for Malware Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Christopher Kruegel, Giovanni Vigna, Hojjat Aghakhani, Kaie Chen, Roman Vasilenko, Saastha Vasan, Wenbo Guo, Yigitcan Kaya, Yuzhou Nie","submitted_at":"2026-05-15T05:31:59Z","abstract_excerpt":"Automated malware analysis increasingly relies on machine learning, yet most existing methods remain task-specific and depend on handcrafted features or narrowly scoped models. Recent developments in binary-level foundation models suggest a path toward reusable program representations, but their application to malware analysis remains underexplored, and most still operate at byte-level tokenization, limiting their ability to capture multi-byte code patterns.\n  In this work, we introduce MalwarePT, a binary-level foundation model for malware analysis built on a ModernBERT-style encoder and pret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16455","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/2605.16455/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:35.677176Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:21:57.076427Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3344d26fe04c70dd6a55f22c0e7ae896cb11fc32deeaee284d4ea7029bdff44f"},"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":"2605.16455","created_at":"2026-05-20T00:02:23.020209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16455v1","created_at":"2026-05-20T00:02:23.020209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16455","created_at":"2026-05-20T00:02:23.020209+00:00"},{"alias_kind":"pith_short_12","alias_value":"4WYABC5EIJ24","created_at":"2026-05-20T00:02:23.020209+00:00"},{"alias_kind":"pith_short_16","alias_value":"4WYABC5EIJ246BUF","created_at":"2026-05-20T00:02:23.020209+00:00"},{"alias_kind":"pith_short_8","alias_value":"4WYABC5E","created_at":"2026-05-20T00:02:23.020209+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/4WYABC5EIJ246BUFEH33LLRT3M","json":"https://pith.science/pith/4WYABC5EIJ246BUFEH33LLRT3M.json","graph_json":"https://pith.science/api/pith-number/4WYABC5EIJ246BUFEH33LLRT3M/graph.json","events_json":"https://pith.science/api/pith-number/4WYABC5EIJ246BUFEH33LLRT3M/events.json","paper":"https://pith.science/paper/4WYABC5E"},"agent_actions":{"view_html":"https://pith.science/pith/4WYABC5EIJ246BUFEH33LLRT3M","download_json":"https://pith.science/pith/4WYABC5EIJ246BUFEH33LLRT3M.json","view_paper":"https://pith.science/paper/4WYABC5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16455&json=true","fetch_graph":"https://pith.science/api/pith-number/4WYABC5EIJ246BUFEH33LLRT3M/graph.json","fetch_events":"https://pith.science/api/pith-number/4WYABC5EIJ246BUFEH33LLRT3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4WYABC5EIJ246BUFEH33LLRT3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4WYABC5EIJ246BUFEH33LLRT3M/action/storage_attestation","attest_author":"https://pith.science/pith/4WYABC5EIJ246BUFEH33LLRT3M/action/author_attestation","sign_citation":"https://pith.science/pith/4WYABC5EIJ246BUFEH33LLRT3M/action/citation_signature","submit_replication":"https://pith.science/pith/4WYABC5EIJ246BUFEH33LLRT3M/action/replication_record"}},"created_at":"2026-05-20T00:02:23.020209+00:00","updated_at":"2026-05-20T00:02:23.020209+00:00"}