{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6A7FOUJ3CIGMIQKFHTD32TC7SY","short_pith_number":"pith:6A7FOUJ3","schema_version":"1.0","canonical_sha256":"f03e57513b120cc441453cc7bd4c5f9638a5e36820e5defa55de7bcf41cbef1f","source":{"kind":"arxiv","id":"2606.04957","version":1},"attestation_state":"computed","paper":{"title":"NLLog: Lightweight, Explainable SOC Anomaly Detection via Log-to-Language Rewriting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CR","authors_text":"Daisuke Inoue, Samuel Ndichu, Seiichi Ozawa, Takeshi Takahashi, Tao Ban","submitted_at":"2026-06-03T14:45:29Z","abstract_excerpt":"System-generated logs underpin security monitoring, yet their rigid template-based format hinders both automated analysis and human comprehension. We present NLLog (Natural-Language Log), a lightweight pipeline that deterministically rewrites parsed templates into WHO-WHAT-SEVERITY sentences, pools them with term-frequency-inverse-document-frequency weighting, classifies sessions with tree ensembles, and back-projects evidence with TreeSHAP for analyst review. On Hadoop Distributed File System (HDFS) and Blue Gene/L (BGL) corpora, NLLog exceeds two reproduced matched-protocol baselines; across"},"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":"2606.04957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-06-03T14:45:29Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"bdd675d1e1845cc43338095271f862a0b7a9fc9d4bd040a6b48995cd64f4e6a0","abstract_canon_sha256":"3730315b6b5e1bf5cc446632f6b26bd58d2ac4dbcafef50f7353c07988d6f224"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:58.084003Z","signature_b64":"YdVtyBsiW8B4y0LVpYfi1mBwd1ju8th2cV52feIHYY7nNFGp4DkEvzT+AgUrp03Y0DT1qiC2ZQ3BSGPsSwh6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f03e57513b120cc441453cc7bd4c5f9638a5e36820e5defa55de7bcf41cbef1f","last_reissued_at":"2026-06-04T01:09:58.083157Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:58.083157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NLLog: Lightweight, Explainable SOC Anomaly Detection via Log-to-Language Rewriting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CR","authors_text":"Daisuke Inoue, Samuel Ndichu, Seiichi Ozawa, Takeshi Takahashi, Tao Ban","submitted_at":"2026-06-03T14:45:29Z","abstract_excerpt":"System-generated logs underpin security monitoring, yet their rigid template-based format hinders both automated analysis and human comprehension. We present NLLog (Natural-Language Log), a lightweight pipeline that deterministically rewrites parsed templates into WHO-WHAT-SEVERITY sentences, pools them with term-frequency-inverse-document-frequency weighting, classifies sessions with tree ensembles, and back-projects evidence with TreeSHAP for analyst review. On Hadoop Distributed File System (HDFS) and Blue Gene/L (BGL) corpora, NLLog exceeds two reproduced matched-protocol baselines; across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04957","kind":"arxiv","version":1},"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/2606.04957/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":"2606.04957","created_at":"2026-06-04T01:09:58.083306+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04957v1","created_at":"2026-06-04T01:09:58.083306+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04957","created_at":"2026-06-04T01:09:58.083306+00:00"},{"alias_kind":"pith_short_12","alias_value":"6A7FOUJ3CIGM","created_at":"2026-06-04T01:09:58.083306+00:00"},{"alias_kind":"pith_short_16","alias_value":"6A7FOUJ3CIGMIQKF","created_at":"2026-06-04T01:09:58.083306+00:00"},{"alias_kind":"pith_short_8","alias_value":"6A7FOUJ3","created_at":"2026-06-04T01:09:58.083306+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/6A7FOUJ3CIGMIQKFHTD32TC7SY","json":"https://pith.science/pith/6A7FOUJ3CIGMIQKFHTD32TC7SY.json","graph_json":"https://pith.science/api/pith-number/6A7FOUJ3CIGMIQKFHTD32TC7SY/graph.json","events_json":"https://pith.science/api/pith-number/6A7FOUJ3CIGMIQKFHTD32TC7SY/events.json","paper":"https://pith.science/paper/6A7FOUJ3"},"agent_actions":{"view_html":"https://pith.science/pith/6A7FOUJ3CIGMIQKFHTD32TC7SY","download_json":"https://pith.science/pith/6A7FOUJ3CIGMIQKFHTD32TC7SY.json","view_paper":"https://pith.science/paper/6A7FOUJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04957&json=true","fetch_graph":"https://pith.science/api/pith-number/6A7FOUJ3CIGMIQKFHTD32TC7SY/graph.json","fetch_events":"https://pith.science/api/pith-number/6A7FOUJ3CIGMIQKFHTD32TC7SY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6A7FOUJ3CIGMIQKFHTD32TC7SY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6A7FOUJ3CIGMIQKFHTD32TC7SY/action/storage_attestation","attest_author":"https://pith.science/pith/6A7FOUJ3CIGMIQKFHTD32TC7SY/action/author_attestation","sign_citation":"https://pith.science/pith/6A7FOUJ3CIGMIQKFHTD32TC7SY/action/citation_signature","submit_replication":"https://pith.science/pith/6A7FOUJ3CIGMIQKFHTD32TC7SY/action/replication_record"}},"created_at":"2026-06-04T01:09:58.083306+00:00","updated_at":"2026-06-04T01:09:58.083306+00:00"}