{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:64DUUF2J356GTWQRURZAD2JIEM","short_pith_number":"pith:64DUUF2J","schema_version":"1.0","canonical_sha256":"f7074a1749df7c69da11a47201e9282338cd0a14503a134aa30abff3286ae97b","source":{"kind":"arxiv","id":"2107.02438","version":3},"attestation_state":"computed","paper":{"title":"Shell Language Processing: Unix command parsing for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Dmitrijs Trizna","submitted_at":"2021-07-06T07:34:16Z","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."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2107.02438","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-06T07:34:16Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"49b6f48a74667c87829e1bc1bd5fd74586a89f0abcffdac3a17abd1b09571001","abstract_canon_sha256":"611b359fa94eaa91a335ff1016fd9c93885e86cf840d5bb385df44c59ff6ab50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:10.972261Z","signature_b64":"BUxJuROJPbc836MIRmWaq4OJaSGLJ5BKYdpXoengicRsKFVmdPyyz5JmEIcPyJ11uFRTVRlw1yk9R2A70SEfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7074a1749df7c69da11a47201e9282338cd0a14503a134aa30abff3286ae97b","last_reissued_at":"2026-07-05T04:38:10.971832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:10.971832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shell Language Processing: Unix command parsing for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Dmitrijs Trizna","submitted_at":"2021-07-06T07:34:16Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02438","kind":"arxiv","version":3},"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/2107.02438/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2107.02438","created_at":"2026-07-05T04:38:10.971888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.02438v3","created_at":"2026-07-05T04:38:10.971888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02438","created_at":"2026-07-05T04:38:10.971888+00:00"},{"alias_kind":"pith_short_12","alias_value":"64DUUF2J356G","created_at":"2026-07-05T04:38:10.971888+00:00"},{"alias_kind":"pith_short_16","alias_value":"64DUUF2J356GTWQR","created_at":"2026-07-05T04:38:10.971888+00:00"},{"alias_kind":"pith_short_8","alias_value":"64DUUF2J","created_at":"2026-07-05T04:38:10.971888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM","json":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM.json","graph_json":"https://pith.science/api/pith-number/64DUUF2J356GTWQRURZAD2JIEM/graph.json","events_json":"https://pith.science/api/pith-number/64DUUF2J356GTWQRURZAD2JIEM/events.json","paper":"https://pith.science/paper/64DUUF2J"},"agent_actions":{"view_html":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM","download_json":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM.json","view_paper":"https://pith.science/paper/64DUUF2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.02438&json=true","fetch_graph":"https://pith.science/api/pith-number/64DUUF2J356GTWQRURZAD2JIEM/graph.json","fetch_events":"https://pith.science/api/pith-number/64DUUF2J356GTWQRURZAD2JIEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/action/storage_attestation","attest_author":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/action/author_attestation","sign_citation":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/action/citation_signature","submit_replication":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/action/replication_record"}},"created_at":"2026-07-05T04:38:10.971888+00:00","updated_at":"2026-07-05T04:38:10.971888+00:00"}