{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IVTAI3E6SWCW6RFE6L2QI4II4K","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"43cc9f591d85d045f53e44bc8f011f6e4c11ac0bbc364e85d3eb01d45142c238","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-12-14T15:22:37Z","title_canon_sha256":"b66e098965b68ca7c15542c1edc9855d111406b7db792832311e27e2ea575710"},"schema_version":"1.0","source":{"id":"2012.07634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.07634","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"arxiv_version","alias_value":"2012.07634v1","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.07634","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_12","alias_value":"IVTAI3E6SWCW","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_16","alias_value":"IVTAI3E6SWCW6RFE","created_at":"2026-07-05T01:59:22Z"},{"alias_kind":"pith_short_8","alias_value":"IVTAI3E6","created_at":"2026-07-05T01:59:22Z"}],"graph_snapshots":[{"event_id":"sha256:430d7473f96627580cff99f4ce7274830145c8f8694332d36a9c28bb1cb64eff","target":"graph","created_at":"2026-07-05T01:59:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.07634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ethan M. Rudd, Richard Harang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-12-14T15:22:37Z","title":"SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.07634","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:49be8ddb0025100d35df20292cb0b9d2f04028679173fb23671069d323500f82","target":"record","created_at":"2026-07-05T01:59:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"43cc9f591d85d045f53e44bc8f011f6e4c11ac0bbc364e85d3eb01d45142c238","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-12-14T15:22:37Z","title_canon_sha256":"b66e098965b68ca7c15542c1edc9855d111406b7db792832311e27e2ea575710"},"schema_version":"1.0","source":{"id":"2012.07634","kind":"arxiv","version":1}},"canonical_sha256":"4566046c9e95856f44a4f2f5047108e2bad45cc2ac09b0dfe105ad726731149f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4566046c9e95856f44a4f2f5047108e2bad45cc2ac09b0dfe105ad726731149f","first_computed_at":"2026-07-05T01:59:22.833035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:22.833035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HAoe7BlpiozvBx719chbequkCfccIF2sWeTOe/42Yus/o93bdp8pA5/44K6YVCx567rxzKasiktJ7cO1A/D+CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:22.833462Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.07634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49be8ddb0025100d35df20292cb0b9d2f04028679173fb23671069d323500f82","sha256:430d7473f96627580cff99f4ce7274830145c8f8694332d36a9c28bb1cb64eff"],"state_sha256":"cced4a078fb8cc85a6be042c7ddf2f276993eb7b0167756c74a99f529ffa78bc"}