{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5P2OU43GQHUMAQ5HJNAIQ5AE2C","short_pith_number":"pith:5P2OU43G","schema_version":"1.0","canonical_sha256":"ebf4ea736681e8c043a74b40887404d0912fc2a72441f05d95c9f6f9fd4503cf","source":{"kind":"arxiv","id":"2605.21773","version":1},"attestation_state":"computed","paper":{"title":"HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Danyu Sun, Jinghuai Zhang, Yuan Tian, Zhou Li","submitted_at":"2026-05-20T22:07:12Z","abstract_excerpt":"Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion detection from system logs, remains unexplored. In this work, we present a new benchmark to assess LLMs' capabilities in supporting host-based intrusion detection systems (HIDS). This task requires fine-grained reasoning over large-scale, noisy, and highly imbalanced system logs, where complex interactions between benign and malicious activities make reliable"},"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":"2605.21773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-20T22:07:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9c9db102c073ac9cd7e0da546668d6b8ffeb20499a2f44a4cd2ddd0c6e640f5e","abstract_canon_sha256":"60e5a039b565ea96f5af00da528f70e225884dfd0bd7d67b98640f2c3608d755"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:31.299763Z","signature_b64":"r59YSA/nV0qdi3L86gRN/0hXaYvNsZ7MBTc80k24sEq/Phd2Dyl84BdZKoA8KEZQvotIe1LZmdV4AIRWFCr2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf4ea736681e8c043a74b40887404d0912fc2a72441f05d95c9f6f9fd4503cf","last_reissued_at":"2026-05-22T01:03:31.299168Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:31.299168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Danyu Sun, Jinghuai Zhang, Yuan Tian, Zhou Li","submitted_at":"2026-05-20T22:07:12Z","abstract_excerpt":"Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion detection from system logs, remains unexplored. In this work, we present a new benchmark to assess LLMs' capabilities in supporting host-based intrusion detection systems (HIDS). This task requires fine-grained reasoning over large-scale, noisy, and highly imbalanced system logs, where complex interactions between benign and malicious activities make reliable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21773","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/2605.21773/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":"2605.21773","created_at":"2026-05-22T01:03:31.299282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21773v1","created_at":"2026-05-22T01:03:31.299282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21773","created_at":"2026-05-22T01:03:31.299282+00:00"},{"alias_kind":"pith_short_12","alias_value":"5P2OU43GQHUM","created_at":"2026-05-22T01:03:31.299282+00:00"},{"alias_kind":"pith_short_16","alias_value":"5P2OU43GQHUMAQ5H","created_at":"2026-05-22T01:03:31.299282+00:00"},{"alias_kind":"pith_short_8","alias_value":"5P2OU43G","created_at":"2026-05-22T01:03:31.299282+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/5P2OU43GQHUMAQ5HJNAIQ5AE2C","json":"https://pith.science/pith/5P2OU43GQHUMAQ5HJNAIQ5AE2C.json","graph_json":"https://pith.science/api/pith-number/5P2OU43GQHUMAQ5HJNAIQ5AE2C/graph.json","events_json":"https://pith.science/api/pith-number/5P2OU43GQHUMAQ5HJNAIQ5AE2C/events.json","paper":"https://pith.science/paper/5P2OU43G"},"agent_actions":{"view_html":"https://pith.science/pith/5P2OU43GQHUMAQ5HJNAIQ5AE2C","download_json":"https://pith.science/pith/5P2OU43GQHUMAQ5HJNAIQ5AE2C.json","view_paper":"https://pith.science/paper/5P2OU43G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21773&json=true","fetch_graph":"https://pith.science/api/pith-number/5P2OU43GQHUMAQ5HJNAIQ5AE2C/graph.json","fetch_events":"https://pith.science/api/pith-number/5P2OU43GQHUMAQ5HJNAIQ5AE2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5P2OU43GQHUMAQ5HJNAIQ5AE2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5P2OU43GQHUMAQ5HJNAIQ5AE2C/action/storage_attestation","attest_author":"https://pith.science/pith/5P2OU43GQHUMAQ5HJNAIQ5AE2C/action/author_attestation","sign_citation":"https://pith.science/pith/5P2OU43GQHUMAQ5HJNAIQ5AE2C/action/citation_signature","submit_replication":"https://pith.science/pith/5P2OU43GQHUMAQ5HJNAIQ5AE2C/action/replication_record"}},"created_at":"2026-05-22T01:03:31.299282+00:00","updated_at":"2026-05-22T01:03:31.299282+00:00"}