{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U2U7XRSH3HX7RCCO2GCQDOBY7M","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":"afcf740cd58837ba1fa7e6d7989c2a9e4f07197fc3e516be934014ca3e4f145b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-06-09T19:53:40Z","title_canon_sha256":"4a65a04971f3c8fd68f13876aa76756b7475cf1f13737a90c158fe320bc49a70"},"schema_version":"1.0","source":{"id":"2306.06228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.06228","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.06228v1","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06228","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"U2U7XRSH3HX7","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"U2U7XRSH3HX7RCCO","created_at":"2026-07-05T06:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"U2U7XRSH","created_at":"2026-07-05T06:19:22Z"}],"graph_snapshots":[{"event_id":"sha256:15b5fad460558fb5ffebf089e5a553413c79a825350dd886f598db1d2f237661","target":"graph","created_at":"2026-07-05T06:19:22Z","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/2306.06228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When investigating a malicious file, searching for related files is a common task that malware analysts must perform. Given that production malware corpora may contain over a billion files and consume petabytes of storage, many feature extraction and similarity search approaches are computationally infeasible. Our work explores the potential of antivirus (AV) scan data as a scalable source of features for malware. This is possible because AV scan reports are widely available through services such as VirusTotal and are ~100x smaller than the average malware sample. The information within an AV ","authors_text":"Charles Nicholas, Edward Raff, Robert J. Joyce, Tirth Patel","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-06-09T19:53:40Z","title":"AVScan2Vec: Feature Learning on Antivirus Scan Data for Production-Scale Malware Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06228","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:ac19f08da3d6778e71c8c01c85ba16c7d2a3c8e2c3ab75609af68ac270354ce1","target":"record","created_at":"2026-07-05T06:19:22Z","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":"afcf740cd58837ba1fa7e6d7989c2a9e4f07197fc3e516be934014ca3e4f145b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-06-09T19:53:40Z","title_canon_sha256":"4a65a04971f3c8fd68f13876aa76756b7475cf1f13737a90c158fe320bc49a70"},"schema_version":"1.0","source":{"id":"2306.06228","kind":"arxiv","version":1}},"canonical_sha256":"a6a9fbc647d9eff8884ed18501b838fb12f176040a76886bef684fa47d87546d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6a9fbc647d9eff8884ed18501b838fb12f176040a76886bef684fa47d87546d","first_computed_at":"2026-07-05T06:19:22.209020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:22.209020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0fnk4WPbDhKGpxXTnPgzMxNGkKlewtNtcgYiv+vbQpXVb88YzPa/W+6LQkOF84TD4S1mOlElJ46uH+CSvZBVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:22.209370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.06228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac19f08da3d6778e71c8c01c85ba16c7d2a3c8e2c3ab75609af68ac270354ce1","sha256:15b5fad460558fb5ffebf089e5a553413c79a825350dd886f598db1d2f237661"],"state_sha256":"cf93c64380bae2453948dadbc7f82ad7f3b9721381066940930729805e70a8ab"}