{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:64DUUF2J356GTWQRURZAD2JIEM","short_pith_number":"pith:64DUUF2J","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"},"canonical_sha256":"f7074a1749df7c69da11a47201e9282338cd0a14503a134aa30abff3286ae97b","source":{"kind":"arxiv","id":"2107.02438","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:64DUUF2J356GTWQRURZAD2JIEM","target":"record","payload":{"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"},"canonical_sha256":"f7074a1749df7c69da11a47201e9282338cd0a14503a134aa30abff3286ae97b","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"},"source_kind":"arxiv","source_id":"2107.02438","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:38:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f4vDe/944c06r0I6/xZ9L0SetfHyjUsDLCWGXXTfvWSjib5kyB87Ph4umnHyxv/l3E37PS4ReEsdjzJMLo2aBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:33:44.189853Z"},"content_sha256":"9794aea0b22589274a15ba16aac7d3d883aa1d587dcb7e24e47f3d37ccfd3645","schema_version":"1.0","event_id":"sha256:9794aea0b22589274a15ba16aac7d3d883aa1d587dcb7e24e47f3d37ccfd3645"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:64DUUF2J356GTWQRURZAD2JIEM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:38:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"viS+Dq6Y4tdAHqBxYiyt3xOMwMuF+Mf4yqZ8HYRgiDTkmVKDzhZWN0ldEujxNveFoN8jQsXI8Z7wIcBQUIIIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:33:44.190397Z"},"content_sha256":"fbd0369bfcfe5bb37cf3b069bfd351e6c7de56115db822f6a4ffc3e8070eed3e","schema_version":"1.0","event_id":"sha256:fbd0369bfcfe5bb37cf3b069bfd351e6c7de56115db822f6a4ffc3e8070eed3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/bundle.json","state_url":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/64DUUF2J356GTWQRURZAD2JIEM/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":"2026-08-05T10:33:44Z","links":{"resolver":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM","bundle":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/bundle.json","state":"https://pith.science/pith/64DUUF2J356GTWQRURZAD2JIEM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/64DUUF2J356GTWQRURZAD2JIEM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fLFDRz0zH/ND9vw3k9dT+og7LHNOwILHAQNIrZrf7LvUB9tEbNgDKqObZNGdSFVVDu8TQVqaYweLkRdwCazxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:33:44.194199Z","bundle_sha256":"371a5a28ce197f367742d36dc3cb66e514f5a0c8cf96e516f631a9c313de377d"}}