{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:25BIJMSOOIRFUM7LOVET7HNJEG","short_pith_number":"pith:25BIJMSO","schema_version":"1.0","canonical_sha256":"d74284b24e72225a33eb75493f9da921bc32822a604d3f773912ad17f54db3de","source":{"kind":"arxiv","id":"2306.14062","version":2},"attestation_state":"computed","paper":{"title":"On the Uses of Large Language Models to Interpret Ambiguous Cyberattack Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.AI","authors_text":"Reza Fayyazi, Shanchieh Jay Yang","submitted_at":"2023-06-24T21:08:15Z","abstract_excerpt":"The volume, variety, and velocity of change in vulnerabilities and exploits have made incident threat analysis challenging with human expertise and experience along. Tactics, Techniques, and Procedures (TTPs) are to describe how and why attackers exploit vulnerabilities. However, a TTP description written by one security professional can be interpreted very differently by another, leading to confusion in cybersecurity operations or even business, policy, and legal decisions. Meanwhile, advancements in AI have led to the increasing use of Natural Language Processing (NLP) algorithms to assist t"},"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":"2306.14062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-06-24T21:08:15Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"d29794e6ed4fe1e259009784fdb3534fd9693a37464f87a0a279ed5f5ac907b8","abstract_canon_sha256":"28676f642911fea4eced6e70e94904dcf27aa2a74b8165152a037211d8dda7f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:50.144570Z","signature_b64":"Hv3dISzlAZl6OOOXayFVtMyoYqPQA85Oe46PKRc5qPYEwAuMJn4TnRlMAVYOaElJ+xtN9fSGZB4M/swZC815AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d74284b24e72225a33eb75493f9da921bc32822a604d3f773912ad17f54db3de","last_reissued_at":"2026-07-05T06:43:50.144081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:50.144081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Uses of Large Language Models to Interpret Ambiguous Cyberattack Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.AI","authors_text":"Reza Fayyazi, Shanchieh Jay Yang","submitted_at":"2023-06-24T21:08:15Z","abstract_excerpt":"The volume, variety, and velocity of change in vulnerabilities and exploits have made incident threat analysis challenging with human expertise and experience along. Tactics, Techniques, and Procedures (TTPs) are to describe how and why attackers exploit vulnerabilities. However, a TTP description written by one security professional can be interpreted very differently by another, leading to confusion in cybersecurity operations or even business, policy, and legal decisions. Meanwhile, advancements in AI have led to the increasing use of Natural Language Processing (NLP) algorithms to assist t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14062","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/2306.14062/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":"2306.14062","created_at":"2026-07-05T06:43:50.144139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14062v2","created_at":"2026-07-05T06:43:50.144139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14062","created_at":"2026-07-05T06:43:50.144139+00:00"},{"alias_kind":"pith_short_12","alias_value":"25BIJMSOOIRF","created_at":"2026-07-05T06:43:50.144139+00:00"},{"alias_kind":"pith_short_16","alias_value":"25BIJMSOOIRFUM7L","created_at":"2026-07-05T06:43:50.144139+00:00"},{"alias_kind":"pith_short_8","alias_value":"25BIJMSO","created_at":"2026-07-05T06:43:50.144139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16852","citing_title":"SynthCTI: LLM-Driven Synthetic CTI Generation to enhance MITRE Technique Mapping","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG","json":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG.json","graph_json":"https://pith.science/api/pith-number/25BIJMSOOIRFUM7LOVET7HNJEG/graph.json","events_json":"https://pith.science/api/pith-number/25BIJMSOOIRFUM7LOVET7HNJEG/events.json","paper":"https://pith.science/paper/25BIJMSO"},"agent_actions":{"view_html":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG","download_json":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG.json","view_paper":"https://pith.science/paper/25BIJMSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14062&json=true","fetch_graph":"https://pith.science/api/pith-number/25BIJMSOOIRFUM7LOVET7HNJEG/graph.json","fetch_events":"https://pith.science/api/pith-number/25BIJMSOOIRFUM7LOVET7HNJEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG/action/storage_attestation","attest_author":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG/action/author_attestation","sign_citation":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG/action/citation_signature","submit_replication":"https://pith.science/pith/25BIJMSOOIRFUM7LOVET7HNJEG/action/replication_record"}},"created_at":"2026-07-05T06:43:50.144139+00:00","updated_at":"2026-07-05T06:43:50.144139+00:00"}