{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4NIS6HCTEPC34L5T3ZUNAJXSXR","short_pith_number":"pith:4NIS6HCT","schema_version":"1.0","canonical_sha256":"e3512f1c5323c5be2fb3de68d026f2bc6c6210fdd10da6903a04ba3c8acc02cc","source":{"kind":"arxiv","id":"2103.00602","version":1},"attestation_state":"computed","paper":{"title":"Virus-MNIST: A Benchmark Malware Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"David Noever, Samantha E. Miller Noever","submitted_at":"2021-02-28T19:55:19Z","abstract_excerpt":"The short note presents an image classification dataset consisting of 10 executable code varieties and approximately 50,000 virus examples. The malicious classes include 9 families of computer viruses and one benign set. The image formatting for the first 1024 bytes of the Portable Executable (PE) mirrors the familiar MNIST handwriting dataset, such that most of the previously explored algorithmic methods can transfer with minor modifications. The designation of 9 virus families for malware derives from unsupervised learning of class labels; we discover the families with KMeans clustering that"},"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":"2103.00602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-02-28T19:55:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"660769c33150f18105ec9fcc4aab76dd6e97c21871e3a29a0496ea39eef9968b","abstract_canon_sha256":"6f225c5a6313805d814b59ffff220aff059fa998c24d1fea91d91e5219ae23e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:07.459655Z","signature_b64":"FkD072Ri71E8d4Mg2JhQAgERFb9AsgrAlB3ZmsKsdJ8mK6oe8l+O7g3Cnnpp3ccs8LMOtPCRaB4C1841Rnt7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3512f1c5323c5be2fb3de68d026f2bc6c6210fdd10da6903a04ba3c8acc02cc","last_reissued_at":"2026-07-05T02:19:07.459167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:07.459167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Virus-MNIST: A Benchmark Malware Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"David Noever, Samantha E. Miller Noever","submitted_at":"2021-02-28T19:55:19Z","abstract_excerpt":"The short note presents an image classification dataset consisting of 10 executable code varieties and approximately 50,000 virus examples. The malicious classes include 9 families of computer viruses and one benign set. The image formatting for the first 1024 bytes of the Portable Executable (PE) mirrors the familiar MNIST handwriting dataset, such that most of the previously explored algorithmic methods can transfer with minor modifications. The designation of 9 virus families for malware derives from unsupervised learning of class labels; we discover the families with KMeans clustering that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00602","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/2103.00602/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":"2103.00602","created_at":"2026-07-05T02:19:07.459228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00602v1","created_at":"2026-07-05T02:19:07.459228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00602","created_at":"2026-07-05T02:19:07.459228+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NIS6HCTEPC3","created_at":"2026-07-05T02:19:07.459228+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NIS6HCTEPC34L5T","created_at":"2026-07-05T02:19:07.459228+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NIS6HCT","created_at":"2026-07-05T02:19:07.459228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21153","citing_title":"Image-Based Malware Type Classification on MalNet-Image Tiny: Effects of Multi-Scale Fusion, Transfer Learning, Data Augmentation, and Schedule-Free Optimization","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR","json":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR.json","graph_json":"https://pith.science/api/pith-number/4NIS6HCTEPC34L5T3ZUNAJXSXR/graph.json","events_json":"https://pith.science/api/pith-number/4NIS6HCTEPC34L5T3ZUNAJXSXR/events.json","paper":"https://pith.science/paper/4NIS6HCT"},"agent_actions":{"view_html":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR","download_json":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR.json","view_paper":"https://pith.science/paper/4NIS6HCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00602&json=true","fetch_graph":"https://pith.science/api/pith-number/4NIS6HCTEPC34L5T3ZUNAJXSXR/graph.json","fetch_events":"https://pith.science/api/pith-number/4NIS6HCTEPC34L5T3ZUNAJXSXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR/action/storage_attestation","attest_author":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR/action/author_attestation","sign_citation":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR/action/citation_signature","submit_replication":"https://pith.science/pith/4NIS6HCTEPC34L5T3ZUNAJXSXR/action/replication_record"}},"created_at":"2026-07-05T02:19:07.459228+00:00","updated_at":"2026-07-05T02:19:07.459228+00:00"}