{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GDDPJJLGKHDV4LGSFLEP44VGOI","short_pith_number":"pith:GDDPJJLG","schema_version":"1.0","canonical_sha256":"30c6f4a56651c75e2cd22ac8fe72a67231e8cbde07ea7bfd653ba169783700dd","source":{"kind":"arxiv","id":"2608.11634","version":1},"attestation_state":"computed","paper":{"title":"CAM-Guided Saliency Cutout and Image-Based Malware Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mark Stamp, Martin Jurecek, Yasaman Ebrahimi","submitted_at":"2026-08-12T04:32:00Z","abstract_excerpt":"Dropout regularization is commonly used to reduce overfitting by removing parts of a neural network during training. For Convolutional Neural Networks (CNN), cutouts serve a somewhat analogous purpose. Cutouts can be implemented as data augmentation: the original training image is retained, and additional copies are created with regions removed. In this chapter, we test whether cutout placement can be improved by using High-Resolution Class Activation Mapping (HiResCAM). We compare four controlled training conditions: no cutout, standard random cutout, low-saliency cutout, and high-saliency cu"},"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":"2608.11634","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-12T04:32:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2a65c82313ec20b95609a63d242e9772eb61a17d9ecb4bdf9bfeae00663794ff","abstract_canon_sha256":"735ccd7239d242ec114bff4b257f407205cb0bde2223d9f2ad0ee2e451a81c69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:23:02.629637Z","signature_b64":"jE1PJiimZUBcoJS19eb7sas0CqzEJltcnWMECIkywk6O5enZNM0u5JsZsLcMUwKkCwyvDwvx0Vvttqpk7X7TBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30c6f4a56651c75e2cd22ac8fe72a67231e8cbde07ea7bfd653ba169783700dd","last_reissued_at":"2026-08-13T00:23:02.626946Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:23:02.626946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAM-Guided Saliency Cutout and Image-Based Malware Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mark Stamp, Martin Jurecek, Yasaman Ebrahimi","submitted_at":"2026-08-12T04:32:00Z","abstract_excerpt":"Dropout regularization is commonly used to reduce overfitting by removing parts of a neural network during training. For Convolutional Neural Networks (CNN), cutouts serve a somewhat analogous purpose. Cutouts can be implemented as data augmentation: the original training image is retained, and additional copies are created with regions removed. In this chapter, we test whether cutout placement can be improved by using High-Resolution Class Activation Mapping (HiResCAM). We compare four controlled training conditions: no cutout, standard random cutout, low-saliency cutout, and high-saliency cu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11634","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/2608.11634/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":"2608.11634","created_at":"2026-08-13T00:23:02.628034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11634v1","created_at":"2026-08-13T00:23:02.628034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11634","created_at":"2026-08-13T00:23:02.628034+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDDPJJLGKHDV","created_at":"2026-08-13T00:23:02.628034+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDDPJJLGKHDV4LGS","created_at":"2026-08-13T00:23:02.628034+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDDPJJLG","created_at":"2026-08-13T00:23:02.628034+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/GDDPJJLGKHDV4LGSFLEP44VGOI","json":"https://pith.science/pith/GDDPJJLGKHDV4LGSFLEP44VGOI.json","graph_json":"https://pith.science/api/pith-number/GDDPJJLGKHDV4LGSFLEP44VGOI/graph.json","events_json":"https://pith.science/api/pith-number/GDDPJJLGKHDV4LGSFLEP44VGOI/events.json","paper":"https://pith.science/paper/GDDPJJLG"},"agent_actions":{"view_html":"https://pith.science/pith/GDDPJJLGKHDV4LGSFLEP44VGOI","download_json":"https://pith.science/pith/GDDPJJLGKHDV4LGSFLEP44VGOI.json","view_paper":"https://pith.science/paper/GDDPJJLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11634&json=true","fetch_graph":"https://pith.science/api/pith-number/GDDPJJLGKHDV4LGSFLEP44VGOI/graph.json","fetch_events":"https://pith.science/api/pith-number/GDDPJJLGKHDV4LGSFLEP44VGOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDDPJJLGKHDV4LGSFLEP44VGOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDDPJJLGKHDV4LGSFLEP44VGOI/action/storage_attestation","attest_author":"https://pith.science/pith/GDDPJJLGKHDV4LGSFLEP44VGOI/action/author_attestation","sign_citation":"https://pith.science/pith/GDDPJJLGKHDV4LGSFLEP44VGOI/action/citation_signature","submit_replication":"https://pith.science/pith/GDDPJJLGKHDV4LGSFLEP44VGOI/action/replication_record"}},"created_at":"2026-08-13T00:23:02.628034+00:00","updated_at":"2026-08-13T00:23:02.628034+00:00"}