{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KQFLU3F3HY225AY5W46LAI7KZY","short_pith_number":"pith:KQFLU3F3","schema_version":"1.0","canonical_sha256":"540aba6cbb3e35ae831db73cb023eace3cfeec5cc2e9f0e453bc539ba2862272","source":{"kind":"arxiv","id":"2506.05074","version":1},"attestation_state":"computed","paper":{"title":"EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Edward Raff, Elliott Zaresky-Williams, Gideon Miller, Hyrum Anderson, James Holt, Phil Roth, Richard Zak, Robert J. Joyce","submitted_at":"2025-06-05T14:20:36Z","abstract_excerpt":"A lack of accessible data has historically restricted malware analysis research, and practitioners have relied heavily on datasets provided by industry sources to advance. Existing public datasets are limited by narrow scope - most include files targeting a single platform, have labels supporting just one type of malware classification task, and make no effort to capture the evasive files that make malware detection difficult in practice. We present EMBER2024, a new dataset that enables holistic evaluation of malware classifiers. Created in collaboration with the authors of EMBER2017 and EMBER"},"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":"2506.05074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-06-05T14:20:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1521a5256c4a7dd5efda50e789e493e50a2fac4ec169503df0028c8666f4a550","abstract_canon_sha256":"16deeac354c0db8b70c0eb119363163e9a5cf76635756cde505c446613832c88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:41.849479Z","signature_b64":"k5FBqDTa3GEvEbfRxoCKs/CdLktZxFBs29xPEzktUxHoQvss5nPtpDIBoyiqTTmrh7YQJ8dJJ8kvhw9PHAcjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"540aba6cbb3e35ae831db73cb023eace3cfeec5cc2e9f0e453bc539ba2862272","last_reissued_at":"2026-07-05T11:16:41.848896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:41.848896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Edward Raff, Elliott Zaresky-Williams, Gideon Miller, Hyrum Anderson, James Holt, Phil Roth, Richard Zak, Robert J. Joyce","submitted_at":"2025-06-05T14:20:36Z","abstract_excerpt":"A lack of accessible data has historically restricted malware analysis research, and practitioners have relied heavily on datasets provided by industry sources to advance. Existing public datasets are limited by narrow scope - most include files targeting a single platform, have labels supporting just one type of malware classification task, and make no effort to capture the evasive files that make malware detection difficult in practice. We present EMBER2024, a new dataset that enables holistic evaluation of malware classifiers. Created in collaboration with the authors of EMBER2017 and EMBER"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05074","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/2506.05074/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":"2506.05074","created_at":"2026-07-05T11:16:41.848959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05074v1","created_at":"2026-07-05T11:16:41.848959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05074","created_at":"2026-07-05T11:16:41.848959+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQFLU3F3HY22","created_at":"2026-07-05T11:16:41.848959+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQFLU3F3HY225AY5","created_at":"2026-07-05T11:16:41.848959+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQFLU3F3","created_at":"2026-07-05T11:16:41.848959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06894","citing_title":"McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY","json":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY.json","graph_json":"https://pith.science/api/pith-number/KQFLU3F3HY225AY5W46LAI7KZY/graph.json","events_json":"https://pith.science/api/pith-number/KQFLU3F3HY225AY5W46LAI7KZY/events.json","paper":"https://pith.science/paper/KQFLU3F3"},"agent_actions":{"view_html":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY","download_json":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY.json","view_paper":"https://pith.science/paper/KQFLU3F3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05074&json=true","fetch_graph":"https://pith.science/api/pith-number/KQFLU3F3HY225AY5W46LAI7KZY/graph.json","fetch_events":"https://pith.science/api/pith-number/KQFLU3F3HY225AY5W46LAI7KZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY/action/storage_attestation","attest_author":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY/action/author_attestation","sign_citation":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY/action/citation_signature","submit_replication":"https://pith.science/pith/KQFLU3F3HY225AY5W46LAI7KZY/action/replication_record"}},"created_at":"2026-07-05T11:16:41.848959+00:00","updated_at":"2026-07-05T11:16:41.848959+00:00"}