{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AA4XHDVG573MHM63LUX4CSIQ55","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":"062c2339afb35c61b3c1ce70cb37410c5ae4a111542f223ae1bc50abf14d02ed","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2019-08-01T03:58:11Z","title_canon_sha256":"fa3f6610bd911a74816bcaa2aa2598cae9bce602e2e5778aa741e734a722d7ed"},"schema_version":"1.0","source":{"id":"1908.00200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.00200","created_at":"2026-07-04T23:50:57Z"},{"alias_kind":"arxiv_version","alias_value":"1908.00200v1","created_at":"2026-07-04T23:50:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.00200","created_at":"2026-07-04T23:50:57Z"},{"alias_kind":"pith_short_12","alias_value":"AA4XHDVG573M","created_at":"2026-07-04T23:50:57Z"},{"alias_kind":"pith_short_16","alias_value":"AA4XHDVG573MHM63","created_at":"2026-07-04T23:50:57Z"},{"alias_kind":"pith_short_8","alias_value":"AA4XHDVG","created_at":"2026-07-04T23:50:57Z"}],"graph_snapshots":[{"event_id":"sha256:6f5fcb21b9875587df6a9909fd72d6edf419f6da14f1a0a5f8230761b90f158b","target":"graph","created_at":"2026-07-04T23:50:57Z","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/1908.00200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"N-grams have been a common tool for information retrieval and machine learning applications for decades. In nearly all previous works, only a few values of $n$ are tested, with $n > 6$ being exceedingly rare. Larger values of $n$ are not tested due to computational burden or the fear of overfitting. In this work, we present a method to find the top-$k$ most frequent $n$-grams that is 60$\\times$ faster for small $n$, and can tackle large $n\\geq1024$. Despite the unprecedented size of $n$ considered, we show how these features still have predictive ability for malware classification tasks. More ","authors_text":"Bill Finlayson, Charles Nicholas, Edward Raff, Hyrum Anderson, Mark McLean, Richard Zak, William Fleming","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2019-08-01T03:58:11Z","title":"KiloGrams: Very Large N-Grams for Malware Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.00200","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:e0da6be736c2191e292d80965bae3ca8e3c4819ee6b541b963d77db2dcb63c69","target":"record","created_at":"2026-07-04T23:50:57Z","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":"062c2339afb35c61b3c1ce70cb37410c5ae4a111542f223ae1bc50abf14d02ed","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2019-08-01T03:58:11Z","title_canon_sha256":"fa3f6610bd911a74816bcaa2aa2598cae9bce602e2e5778aa741e734a722d7ed"},"schema_version":"1.0","source":{"id":"1908.00200","kind":"arxiv","version":1}},"canonical_sha256":"0039738ea6eff6c3b3db5d2fc14910ef6b9558870d135e62caae6452b6c61090","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0039738ea6eff6c3b3db5d2fc14910ef6b9558870d135e62caae6452b6c61090","first_computed_at":"2026-07-04T23:50:57.924161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:50:57.924161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"63TPcUjQqAJlRqHmdOQKUo1DsTFL5BMff7WfeU99ahlqeAum+mFTx6UbF6qv426jGnfitutXXIc5AXidQMHaCg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:50:57.924561Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.00200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0da6be736c2191e292d80965bae3ca8e3c4819ee6b541b963d77db2dcb63c69","sha256:6f5fcb21b9875587df6a9909fd72d6edf419f6da14f1a0a5f8230761b90f158b"],"state_sha256":"127f9206923a031c0a9d2008f0a303ec3040eae6c0de8c27a6391e3cd3456ae4"}