{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:64DUUF2J356GTWQRURZAD2JIEM","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":"611b359fa94eaa91a335ff1016fd9c93885e86cf840d5bb385df44c59ff6ab50","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-06T07:34:16Z","title_canon_sha256":"49b6f48a74667c87829e1bc1bd5fd74586a89f0abcffdac3a17abd1b09571001"},"schema_version":"1.0","source":{"id":"2107.02438","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.02438","created_at":"2026-07-05T04:38:10Z"},{"alias_kind":"arxiv_version","alias_value":"2107.02438v3","created_at":"2026-07-05T04:38:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02438","created_at":"2026-07-05T04:38:10Z"},{"alias_kind":"pith_short_12","alias_value":"64DUUF2J356G","created_at":"2026-07-05T04:38:10Z"},{"alias_kind":"pith_short_16","alias_value":"64DUUF2J356GTWQR","created_at":"2026-07-05T04:38:10Z"},{"alias_kind":"pith_short_8","alias_value":"64DUUF2J","created_at":"2026-07-05T04:38:10Z"}],"graph_snapshots":[{"event_id":"sha256:fbd0369bfcfe5bb37cf3b069bfd351e6c7de56115db822f6a4ffc3e8070eed3e","target":"graph","created_at":"2026-07-05T04:38:10Z","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/2107.02438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this article, we present a Shell Language Preprocessing (SLP) library, which implements tokenization and encoding directed at parsing Unix and Linux shell commands. We describe the rationale behind the need for a new approach with specific examples of when conventional Natural Language Processing (NLP) pipelines fail. Furthermore, we evaluate our methodology on a security classification task against widely accepted information and communications technology (ICT) tokenization techniques and achieve significant improvement of an F1 score from 0.392 to 0.874.","authors_text":"Dmitrijs Trizna","cross_cats":["cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-06T07:34:16Z","title":"Shell Language Processing: Unix command parsing for Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02438","kind":"arxiv","version":3},"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":"sha256:9794aea0b22589274a15ba16aac7d3d883aa1d587dcb7e24e47f3d37ccfd3645","target":"record","created_at":"2026-07-05T04:38:10Z","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":"611b359fa94eaa91a335ff1016fd9c93885e86cf840d5bb385df44c59ff6ab50","cross_cats_sorted":["cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-06T07:34:16Z","title_canon_sha256":"49b6f48a74667c87829e1bc1bd5fd74586a89f0abcffdac3a17abd1b09571001"},"schema_version":"1.0","source":{"id":"2107.02438","kind":"arxiv","version":3}},"canonical_sha256":"f7074a1749df7c69da11a47201e9282338cd0a14503a134aa30abff3286ae97b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7074a1749df7c69da11a47201e9282338cd0a14503a134aa30abff3286ae97b","first_computed_at":"2026-07-05T04:38:10.971832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:10.971832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BUxJuROJPbc836MIRmWaq4OJaSGLJ5BKYdpXoengicRsKFVmdPyyz5JmEIcPyJ11uFRTVRlw1yk9R2A70SEfBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:10.972261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.02438","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9794aea0b22589274a15ba16aac7d3d883aa1d587dcb7e24e47f3d37ccfd3645","sha256:fbd0369bfcfe5bb37cf3b069bfd351e6c7de56115db822f6a4ffc3e8070eed3e"],"state_sha256":"d98e0a0292ca1c6438146e01ccfffec6dce5cae0690afafaa885fbddb2d9b81f"}