{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IVTAI3E6SWCW6RFE6L2QI4II4K","short_pith_number":"pith:IVTAI3E6","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"},"canonical_sha256":"4566046c9e95856f44a4f2f5047108e2bad45cc2ac09b0dfe105ad726731149f","source":{"kind":"arxiv","id":"2012.07634","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IVTAI3E6SWCW6RFE6L2QI4II4K","target":"record","payload":{"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"},"canonical_sha256":"4566046c9e95856f44a4f2f5047108e2bad45cc2ac09b0dfe105ad726731149f","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"},"source_kind":"arxiv","source_id":"2012.07634","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cZo0BHz3kH8v5PSGrclxEsCjsLDwFA5tJ2YLT0PSdOYUPd/Ly2EhTEa0gV/5aWCmUfQBX220b9fXm0G+qtFUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:43:54.229272Z"},"content_sha256":"49be8ddb0025100d35df20292cb0b9d2f04028679173fb23671069d323500f82","schema_version":"1.0","event_id":"sha256:49be8ddb0025100d35df20292cb0b9d2f04028679173fb23671069d323500f82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IVTAI3E6SWCW6RFE6L2QI4II4K","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:59:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGiGdztrraY/DEoQxNoS8NgnJ68rI1EdI0GMDculgdh6FCZALj0RRYDx8EVxFFJaXez/yBkPKBc57Mp7pkI+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:43:54.229771Z"},"content_sha256":"430d7473f96627580cff99f4ce7274830145c8f8694332d36a9c28bb1cb64eff","schema_version":"1.0","event_id":"sha256:430d7473f96627580cff99f4ce7274830145c8f8694332d36a9c28bb1cb64eff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/bundle.json","state_url":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T07:43:54Z","links":{"resolver":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K","bundle":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/bundle.json","state":"https://pith.science/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVTAI3E6SWCW6RFE6L2QI4II4K/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxE/yGA6bxYZe/4VoFlqmeWCF1SPjcxdt1Lbwh2E44uO+n1qQZYwGI58a54gCQn79I6B/iFAQbbbizH5rFQdCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:43:54.233457Z","bundle_sha256":"c45bdcd56b8f82cb38f30853911261d932222dcb0174bf7dc1e11cada110151a"}}