{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DRQGUZDCIMDCOB6QL2KVV2U4OA","short_pith_number":"pith:DRQGUZDC","schema_version":"1.0","canonical_sha256":"1c606a646243062707d05e955aea9c7001f53fd07d322d460d587686f6ee9c7d","source":{"kind":"arxiv","id":"2410.21060","version":2},"attestation_state":"computed","paper":{"title":"CTINexus: Automatic Cyber Threat Intelligence Knowledge Graph Construction Using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Dawn Song, Osama Bajaber, Peng Gao, Saimon Amanuel Tsegai, Yutong Cheng","submitted_at":"2024-10-28T14:18:32Z","abstract_excerpt":"Textual descriptions in cyber threat intelligence (CTI) reports, such as security articles and news, are rich sources of knowledge about cyber threats, crucial for organizations to stay informed about the rapidly evolving threat landscape. However, current CTI knowledge extraction methods lack flexibility and generalizability, often resulting in inaccurate and incomplete knowledge extraction. Syntax parsing relies on fixed rules and dictionaries, while model fine-tuning requires large annotated datasets, making both paradigms challenging to adapt to new threats and ontologies. To bridge the ga"},"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":"2410.21060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-28T14:18:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e5c6e6881c94459dd801c4e6bc6adffe3097f95e375ba993303ba67c0b01899c","abstract_canon_sha256":"ee5a15f67d6a1bf9dca86b1e8185083e3c3b73a4904d0cd4dae6a95db3189e54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:27.538755Z","signature_b64":"oS620sNP5Do8HxyPOd8MjvvdWYikIA3oS6EnvMjyHEGDDEhxpGP9E9rDFPBdvNqbJkJ7vW6HfpMXCqBTldtMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c606a646243062707d05e955aea9c7001f53fd07d322d460d587686f6ee9c7d","last_reissued_at":"2026-07-05T10:51:27.538259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:27.538259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CTINexus: Automatic Cyber Threat Intelligence Knowledge Graph Construction Using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Dawn Song, Osama Bajaber, Peng Gao, Saimon Amanuel Tsegai, Yutong Cheng","submitted_at":"2024-10-28T14:18:32Z","abstract_excerpt":"Textual descriptions in cyber threat intelligence (CTI) reports, such as security articles and news, are rich sources of knowledge about cyber threats, crucial for organizations to stay informed about the rapidly evolving threat landscape. However, current CTI knowledge extraction methods lack flexibility and generalizability, often resulting in inaccurate and incomplete knowledge extraction. Syntax parsing relies on fixed rules and dictionaries, while model fine-tuning requires large annotated datasets, making both paradigms challenging to adapt to new threats and ontologies. To bridge the ga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21060","kind":"arxiv","version":2},"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/2410.21060/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":"2410.21060","created_at":"2026-07-05T10:51:27.538325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21060v2","created_at":"2026-07-05T10:51:27.538325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21060","created_at":"2026-07-05T10:51:27.538325+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRQGUZDCIMDC","created_at":"2026-07-05T10:51:27.538325+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRQGUZDCIMDCOB6Q","created_at":"2026-07-05T10:51:27.538325+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRQGUZDC","created_at":"2026-07-05T10:51:27.538325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21059","citing_title":"DEFENGRAPH: Knowledge Graph-Enhanced LLMs for Blue Team Cyber Defense","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06921","citing_title":"Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09115","citing_title":"AI Native Asset Intelligence","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09115","citing_title":"AI Native Asset Intelligence","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07470","citing_title":"Beyond Single Reports: Evaluating Automated ATT&CK Technique Extraction in Multi-Report Campaign Settings","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA","json":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA.json","graph_json":"https://pith.science/api/pith-number/DRQGUZDCIMDCOB6QL2KVV2U4OA/graph.json","events_json":"https://pith.science/api/pith-number/DRQGUZDCIMDCOB6QL2KVV2U4OA/events.json","paper":"https://pith.science/paper/DRQGUZDC"},"agent_actions":{"view_html":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA","download_json":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA.json","view_paper":"https://pith.science/paper/DRQGUZDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21060&json=true","fetch_graph":"https://pith.science/api/pith-number/DRQGUZDCIMDCOB6QL2KVV2U4OA/graph.json","fetch_events":"https://pith.science/api/pith-number/DRQGUZDCIMDCOB6QL2KVV2U4OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA/action/storage_attestation","attest_author":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA/action/author_attestation","sign_citation":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA/action/citation_signature","submit_replication":"https://pith.science/pith/DRQGUZDCIMDCOB6QL2KVV2U4OA/action/replication_record"}},"created_at":"2026-07-05T10:51:27.538325+00:00","updated_at":"2026-07-05T10:51:27.538325+00:00"}