{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VI3I7OFLUOVNOB3D3XSTTVTVGP","short_pith_number":"pith:VI3I7OFL","schema_version":"1.0","canonical_sha256":"aa368fb8aba3aad70763dde539d67533c896ad35c762d92fd7d65f19b2016000","source":{"kind":"arxiv","id":"2503.03108","version":4},"attestation_state":"computed","paper":{"title":"OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Jian-Ping Mei, Jiaobo Jin, Mingjun Ma, Shunan Jing, Tiantian Zhu, Wenrui Cheng, Zhengqiu Weng","submitted_at":"2025-03-05T02:08:12Z","abstract_excerpt":"Recently, Provenance-based Intrusion Detection Systems (PIDSes) have been widely used for endpoint threat analysis. These studies can be broadly categorized into rule-based detection systems and learning-based detection systems. Among these, due to the evolution of attack techniques, rules cannot dynamically model all the characteristics of attackers. As a result, such systems often face false negatives. Learning-based detection systems are further divided into supervised learning and anomaly detection. The scarcity of attack samples hinders the usability and effectiveness of supervised learni"},"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":"2503.03108","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-05T02:08:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85734fa3b2504e23e9fbcad73454d89a13b295e66aebbc4ed6d6e87445d5c885","abstract_canon_sha256":"61cfe5436344d92626ab565a124448685eb5c88cf12b3fd02eaed420d6beadce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:52.781634Z","signature_b64":"NzsOFD2mjL9Tf2b0Tor+X3EGuoC5ZPlLb9iK2B5VkuJKtF+5tnCv1cQLZKIKDqCLFs8MfHnLvMLhZQcA3+vLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa368fb8aba3aad70763dde539d67533c896ad35c762d92fd7d65f19b2016000","last_reissued_at":"2026-07-05T11:40:52.781148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:52.781148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Jian-Ping Mei, Jiaobo Jin, Mingjun Ma, Shunan Jing, Tiantian Zhu, Wenrui Cheng, Zhengqiu Weng","submitted_at":"2025-03-05T02:08:12Z","abstract_excerpt":"Recently, Provenance-based Intrusion Detection Systems (PIDSes) have been widely used for endpoint threat analysis. These studies can be broadly categorized into rule-based detection systems and learning-based detection systems. Among these, due to the evolution of attack techniques, rules cannot dynamically model all the characteristics of attackers. As a result, such systems often face false negatives. Learning-based detection systems are further divided into supervised learning and anomaly detection. The scarcity of attack samples hinders the usability and effectiveness of supervised learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03108","kind":"arxiv","version":4},"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/2503.03108/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":"2503.03108","created_at":"2026-07-05T11:40:52.781207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03108v4","created_at":"2026-07-05T11:40:52.781207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03108","created_at":"2026-07-05T11:40:52.781207+00:00"},{"alias_kind":"pith_short_12","alias_value":"VI3I7OFLUOVN","created_at":"2026-07-05T11:40:52.781207+00:00"},{"alias_kind":"pith_short_16","alias_value":"VI3I7OFLUOVNOB3D","created_at":"2026-07-05T11:40:52.781207+00:00"},{"alias_kind":"pith_short_8","alias_value":"VI3I7OFL","created_at":"2026-07-05T11:40:52.781207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00440","citing_title":"Minos: A Multi-Agent Collaborative Framework for Provenance-Based Backward Tracking","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21773","citing_title":"HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP","json":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP.json","graph_json":"https://pith.science/api/pith-number/VI3I7OFLUOVNOB3D3XSTTVTVGP/graph.json","events_json":"https://pith.science/api/pith-number/VI3I7OFLUOVNOB3D3XSTTVTVGP/events.json","paper":"https://pith.science/paper/VI3I7OFL"},"agent_actions":{"view_html":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP","download_json":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP.json","view_paper":"https://pith.science/paper/VI3I7OFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03108&json=true","fetch_graph":"https://pith.science/api/pith-number/VI3I7OFLUOVNOB3D3XSTTVTVGP/graph.json","fetch_events":"https://pith.science/api/pith-number/VI3I7OFLUOVNOB3D3XSTTVTVGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP/action/storage_attestation","attest_author":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP/action/author_attestation","sign_citation":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP/action/citation_signature","submit_replication":"https://pith.science/pith/VI3I7OFLUOVNOB3D3XSTTVTVGP/action/replication_record"}},"created_at":"2026-07-05T11:40:52.781207+00:00","updated_at":"2026-07-05T11:40:52.781207+00:00"}