{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IVTAI3E6SWCW6RFE6L2QI4II4K","short_pith_number":"pith:IVTAI3E6","schema_version":"1.0","canonical_sha256":"4566046c9e95856f44a4f2f5047108e2bad45cc2ac09b0dfe105ad726731149f","source":{"kind":"arxiv","id":"2012.07634","version":1},"attestation_state":"computed","paper":{"title":"SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Ethan M. Rudd, Richard Harang","submitted_at":"2020-12-14T15:22:37Z","abstract_excerpt":"In this paper we describe the SOREL-20M (Sophos/ReversingLabs-20 Million) dataset: a large-scale dataset consisting of nearly 20 million files with pre-extracted features and metadata, high-quality labels derived from multiple sources, information about vendor detections of the malware samples at the time of collection, and additional ``tags'' related to each malware sample to serve as additional targets. In addition to features and metadata, we also provide approximately 10 million ``disarmed'' malware samples -- samples with both the optional\\_headers.subsystem and file\\_header.machine flags"},"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":"2012.07634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-12-14T15:22:37Z","cross_cats_sorted":[],"title_canon_sha256":"b66e098965b68ca7c15542c1edc9855d111406b7db792832311e27e2ea575710","abstract_canon_sha256":"43cc9f591d85d045f53e44bc8f011f6e4c11ac0bbc364e85d3eb01d45142c238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:22.833462Z","signature_b64":"HAoe7BlpiozvBx719chbequkCfccIF2sWeTOe/42Yus/o93bdp8pA5/44K6YVCx567rxzKasiktJ7cO1A/D+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4566046c9e95856f44a4f2f5047108e2bad45cc2ac09b0dfe105ad726731149f","last_reissued_at":"2026-07-05T01:59:22.833035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:22.833035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Ethan M. Rudd, Richard Harang","submitted_at":"2020-12-14T15:22:37Z","abstract_excerpt":"In this paper we describe the SOREL-20M (Sophos/ReversingLabs-20 Million) dataset: a large-scale dataset consisting of nearly 20 million files with pre-extracted features and metadata, high-quality labels derived from multiple sources, information about vendor detections of the malware samples at the time of collection, and additional ``tags'' related to each malware sample to serve as additional targets. In addition to features and metadata, we also provide approximately 10 million ``disarmed'' malware samples -- samples with both the optional\\_headers.subsystem and file\\_header.machine flags"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07634","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/2012.07634/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":"2012.07634","created_at":"2026-07-05T01:59:22.833090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.07634v1","created_at":"2026-07-05T01:59:22.833090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07634","created_at":"2026-07-05T01:59:22.833090+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVTAI3E6SWCW","created_at":"2026-07-05T01:59:22.833090+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVTAI3E6SWCW6RFE","created_at":"2026-07-05T01:59:22.833090+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVTAI3E6","created_at":"2026-07-05T01:59:22.833090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28929","citing_title":"Cybersecurity is the True Frontier for Generative AI Success or Failure","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05807","citing_title":"LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00297","citing_title":"Trident: Improving Malware Detection with LLMs and Behavioral Features","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K","json":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K.json","graph_json":"https://pith.science/api/pith-number/IVTAI3E6SWCW6RFE6L2QI4II4K/graph.json","events_json":"https://pith.science/api/pith-number/IVTAI3E6SWCW6RFE6L2QI4II4K/events.json","paper":"https://pith.science/paper/IVTAI3E6"},"agent_actions":{"view_html":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K","download_json":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K.json","view_paper":"https://pith.science/paper/IVTAI3E6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.07634&json=true","fetch_graph":"https://pith.science/api/pith-number/IVTAI3E6SWCW6RFE6L2QI4II4K/graph.json","fetch_events":"https://pith.science/api/pith-number/IVTAI3E6SWCW6RFE6L2QI4II4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/action/storage_attestation","attest_author":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/action/author_attestation","sign_citation":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/action/citation_signature","submit_replication":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/action/replication_record"}},"created_at":"2026-07-05T01:59:22.833090+00:00","updated_at":"2026-07-05T01:59:22.833090+00:00"}