{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QXUWUAWW73V4KJ4456OOEQA3ZF","short_pith_number":"pith:QXUWUAWW","schema_version":"1.0","canonical_sha256":"85e96a02d6feebc5279cef9ce2401bc943e5fc6f4801569172031fb7313c022d","source":{"kind":"arxiv","id":"2608.12077","version":1},"attestation_state":"computed","paper":{"title":"A Comparison of Malware Image Transformations Using Grad-CAM and Hybrid Learning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Mark Stamp, Vibha Bhavikatti","submitted_at":"2026-08-12T14:00:44Z","abstract_excerpt":"Recent studies have shown that binary-to-image representations can enable effective machine learning-based results for malware detection and classification. However, performance can vary significantly, depending on the technique used to convert binaries to images. Furthermore, the explainability and interpretability of image-based models is largely unexplored within the malware domain. In this research, we employ Gradient-weighted Class Activation Maps (Grad-CAM) as an eXplainable AI (XAI) tool, which we use to analyze eight distinct image types derived from malware samples. We provide quantit"},"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":"2608.12077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-12T14:00:44Z","cross_cats_sorted":[],"title_canon_sha256":"90d44d69e7b3db2b632840f89ff4d296e6677b8a036e8e0a8c5f7fa715b78efb","abstract_canon_sha256":"f794e8834a1656d084458c4281fd1aafe211df9673ec82eb734b39a021a07c21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:29:25.958593Z","signature_b64":"vZNzvJQyLLhVlq1Insao77ep4y12zwVLRyRJvN6HWZXetttwzeyroxiWfBeSi0bsZe8l9o7VXect5T/qqlt7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85e96a02d6feebc5279cef9ce2401bc943e5fc6f4801569172031fb7313c022d","last_reissued_at":"2026-08-13T01:29:25.956271Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:29:25.956271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparison of Malware Image Transformations Using Grad-CAM and Hybrid Learning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Mark Stamp, Vibha Bhavikatti","submitted_at":"2026-08-12T14:00:44Z","abstract_excerpt":"Recent studies have shown that binary-to-image representations can enable effective machine learning-based results for malware detection and classification. However, performance can vary significantly, depending on the technique used to convert binaries to images. Furthermore, the explainability and interpretability of image-based models is largely unexplored within the malware domain. In this research, we employ Gradient-weighted Class Activation Maps (Grad-CAM) as an eXplainable AI (XAI) tool, which we use to analyze eight distinct image types derived from malware samples. We provide quantit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12077","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/2608.12077/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":"2608.12077","created_at":"2026-08-13T01:29:25.957529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12077v1","created_at":"2026-08-13T01:29:25.957529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12077","created_at":"2026-08-13T01:29:25.957529+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXUWUAWW73V4","created_at":"2026-08-13T01:29:25.957529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXUWUAWW73V4KJ44","created_at":"2026-08-13T01:29:25.957529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXUWUAWW","created_at":"2026-08-13T01:29:25.957529+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/QXUWUAWW73V4KJ4456OOEQA3ZF","json":"https://pith.science/pith/QXUWUAWW73V4KJ4456OOEQA3ZF.json","graph_json":"https://pith.science/api/pith-number/QXUWUAWW73V4KJ4456OOEQA3ZF/graph.json","events_json":"https://pith.science/api/pith-number/QXUWUAWW73V4KJ4456OOEQA3ZF/events.json","paper":"https://pith.science/paper/QXUWUAWW"},"agent_actions":{"view_html":"https://pith.science/pith/QXUWUAWW73V4KJ4456OOEQA3ZF","download_json":"https://pith.science/pith/QXUWUAWW73V4KJ4456OOEQA3ZF.json","view_paper":"https://pith.science/paper/QXUWUAWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12077&json=true","fetch_graph":"https://pith.science/api/pith-number/QXUWUAWW73V4KJ4456OOEQA3ZF/graph.json","fetch_events":"https://pith.science/api/pith-number/QXUWUAWW73V4KJ4456OOEQA3ZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXUWUAWW73V4KJ4456OOEQA3ZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXUWUAWW73V4KJ4456OOEQA3ZF/action/storage_attestation","attest_author":"https://pith.science/pith/QXUWUAWW73V4KJ4456OOEQA3ZF/action/author_attestation","sign_citation":"https://pith.science/pith/QXUWUAWW73V4KJ4456OOEQA3ZF/action/citation_signature","submit_replication":"https://pith.science/pith/QXUWUAWW73V4KJ4456OOEQA3ZF/action/replication_record"}},"created_at":"2026-08-13T01:29:25.957529+00:00","updated_at":"2026-08-13T01:29:25.957529+00:00"}