{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6UN44APSUB2R6UKNTIAH3SHDEF","short_pith_number":"pith:6UN44APS","schema_version":"1.0","canonical_sha256":"f51bce01f2a0751f514d9a007dc8e3216d237aa5cf707679f8a60e3203643a70","source":{"kind":"arxiv","id":"2607.24177","version":1},"attestation_state":"computed","paper":{"title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Andrea Ponte, Battista Biggio, Daniel Gibert, Dmitrijs Trizna, Fabio Roli, Luca Demetrio, Matous Kozak, Maura Pintor","submitted_at":"2026-07-27T09:02:56Z","abstract_excerpt":"Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ in terms of data used for both training and testing; (ii) do not consider temporal analysis to showcase whether models withstand the passage of time; (iii) avoid security evaluations with adversarial attacks that could highlight their brittleness against content-injection attacks; and (iv) neglect the computational requirements for deployment, risking slow inference on endpoints. For these reasons, we develop EXE-Benc"},"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":"2607.24177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-07-27T09:02:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5804505d305de2d5ef3a406d9528d9ffe4e0c6b9655792eccd84f2b45a504393","abstract_canon_sha256":"63d321fdd6c9a2037012c018bb09461cd151e8b4c0cfe730da5ffb660d523168"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:48.733089Z","signature_b64":"hrVCVk2KFKpVdzsqsRUyQ88hpCpBM3Q339sr7M1xjR/fquU79CoW8ytDjYdRAfO/kZcgcIRZRZitNm7/ST3ABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f51bce01f2a0751f514d9a007dc8e3216d237aa5cf707679f8a60e3203643a70","last_reissued_at":"2026-07-28T01:23:48.732231Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:48.732231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Andrea Ponte, Battista Biggio, Daniel Gibert, Dmitrijs Trizna, Fabio Roli, Luca Demetrio, Matous Kozak, Maura Pintor","submitted_at":"2026-07-27T09:02:56Z","abstract_excerpt":"Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ in terms of data used for both training and testing; (ii) do not consider temporal analysis to showcase whether models withstand the passage of time; (iii) avoid security evaluations with adversarial attacks that could highlight their brittleness against content-injection attacks; and (iv) neglect the computational requirements for deployment, risking slow inference on endpoints. For these reasons, we develop EXE-Benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24177","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/2607.24177/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":"2607.24177","created_at":"2026-07-28T01:23:48.732672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24177v1","created_at":"2026-07-28T01:23:48.732672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24177","created_at":"2026-07-28T01:23:48.732672+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UN44APSUB2R","created_at":"2026-07-28T01:23:48.732672+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UN44APSUB2R6UKN","created_at":"2026-07-28T01:23:48.732672+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UN44APS","created_at":"2026-07-28T01:23:48.732672+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/6UN44APSUB2R6UKNTIAH3SHDEF","json":"https://pith.science/pith/6UN44APSUB2R6UKNTIAH3SHDEF.json","graph_json":"https://pith.science/api/pith-number/6UN44APSUB2R6UKNTIAH3SHDEF/graph.json","events_json":"https://pith.science/api/pith-number/6UN44APSUB2R6UKNTIAH3SHDEF/events.json","paper":"https://pith.science/paper/6UN44APS"},"agent_actions":{"view_html":"https://pith.science/pith/6UN44APSUB2R6UKNTIAH3SHDEF","download_json":"https://pith.science/pith/6UN44APSUB2R6UKNTIAH3SHDEF.json","view_paper":"https://pith.science/paper/6UN44APS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24177&json=true","fetch_graph":"https://pith.science/api/pith-number/6UN44APSUB2R6UKNTIAH3SHDEF/graph.json","fetch_events":"https://pith.science/api/pith-number/6UN44APSUB2R6UKNTIAH3SHDEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UN44APSUB2R6UKNTIAH3SHDEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UN44APSUB2R6UKNTIAH3SHDEF/action/storage_attestation","attest_author":"https://pith.science/pith/6UN44APSUB2R6UKNTIAH3SHDEF/action/author_attestation","sign_citation":"https://pith.science/pith/6UN44APSUB2R6UKNTIAH3SHDEF/action/citation_signature","submit_replication":"https://pith.science/pith/6UN44APSUB2R6UKNTIAH3SHDEF/action/replication_record"}},"created_at":"2026-07-28T01:23:48.732672+00:00","updated_at":"2026-07-28T01:23:48.732672+00:00"}