{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CR3LI26CCIBOQDVEBW72JOZGGD","short_pith_number":"pith:CR3LI26C","schema_version":"1.0","canonical_sha256":"1476b46bc21202e80ea40dbfa4bb2630f40717eced25add8e2dfac86149a691d","source":{"kind":"arxiv","id":"2006.09271","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Machine Learning Methods and Challenges for Windows Malware Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.ML"],"primary_cat":"cs.CR","authors_text":"Charles Nicholas, Edward Raff","submitted_at":"2020-06-15T17:46:12Z","abstract_excerpt":"Malware classification is a difficult problem, to which machine learning methods have been applied for decades. Yet progress has often been slow, in part due to a number of unique difficulties with the task that occur through all stages of the developing a machine learning system: data collection, labeling, feature creation and selection, model selection, and evaluation. In this survey we will review a number of the current methods and challenges related to malware classification, including data collection, feature extraction, and model construction, and evaluation. Our discussion will include"},"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":"2006.09271","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-06-15T17:46:12Z","cross_cats_sorted":["cs.LG","stat.AP","stat.ML"],"title_canon_sha256":"a03cab8f5db750e96305440ea0ac912fabfe8d5b6632f2838b339675fbb4eb09","abstract_canon_sha256":"e4a7b4311d5a42bee25d122768ca6fbb65e104fd41b208b04b619021bf70d353"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:42.633903Z","signature_b64":"h6AbpWMzcIiJSigplAJjjq94/7rJ1BD4jNTh5AU2JVD6IF2OTC/f4gZgaQYSBFvQMfop+zAfWmn/lwQ5DjeoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1476b46bc21202e80ea40dbfa4bb2630f40717eced25add8e2dfac86149a691d","last_reissued_at":"2026-07-05T01:51:42.633470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:42.633470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Machine Learning Methods and Challenges for Windows Malware Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.AP","stat.ML"],"primary_cat":"cs.CR","authors_text":"Charles Nicholas, Edward Raff","submitted_at":"2020-06-15T17:46:12Z","abstract_excerpt":"Malware classification is a difficult problem, to which machine learning methods have been applied for decades. Yet progress has often been slow, in part due to a number of unique difficulties with the task that occur through all stages of the developing a machine learning system: data collection, labeling, feature creation and selection, model selection, and evaluation. In this survey we will review a number of the current methods and challenges related to malware classification, including data collection, feature extraction, and model construction, and evaluation. Our discussion will include"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09271","kind":"arxiv","version":2},"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/2006.09271/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":"2006.09271","created_at":"2026-07-05T01:51:42.633526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09271v2","created_at":"2026-07-05T01:51:42.633526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09271","created_at":"2026-07-05T01:51:42.633526+00:00"},{"alias_kind":"pith_short_12","alias_value":"CR3LI26CCIBO","created_at":"2026-07-05T01:51:42.633526+00:00"},{"alias_kind":"pith_short_16","alias_value":"CR3LI26CCIBOQDVE","created_at":"2026-07-05T01:51:42.633526+00:00"},{"alias_kind":"pith_short_8","alias_value":"CR3LI26C","created_at":"2026-07-05T01:51:42.633526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04372","citing_title":"Adaptive Malware Detection using Sequential Feature Selection: A Dueling Double Deep Q-Network (D3QN) Framework for Intelligent Classification","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD","json":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD.json","graph_json":"https://pith.science/api/pith-number/CR3LI26CCIBOQDVEBW72JOZGGD/graph.json","events_json":"https://pith.science/api/pith-number/CR3LI26CCIBOQDVEBW72JOZGGD/events.json","paper":"https://pith.science/paper/CR3LI26C"},"agent_actions":{"view_html":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD","download_json":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD.json","view_paper":"https://pith.science/paper/CR3LI26C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09271&json=true","fetch_graph":"https://pith.science/api/pith-number/CR3LI26CCIBOQDVEBW72JOZGGD/graph.json","fetch_events":"https://pith.science/api/pith-number/CR3LI26CCIBOQDVEBW72JOZGGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD/action/storage_attestation","attest_author":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD/action/author_attestation","sign_citation":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD/action/citation_signature","submit_replication":"https://pith.science/pith/CR3LI26CCIBOQDVEBW72JOZGGD/action/replication_record"}},"created_at":"2026-07-05T01:51:42.633526+00:00","updated_at":"2026-07-05T01:51:42.633526+00:00"}