{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:423OX5M2I5MRQF22UBNRIGHS77","short_pith_number":"pith:423OX5M2","schema_version":"1.0","canonical_sha256":"e6b6ebf59a475918175aa05b1418f2ffd077baf52fc91b81f74c142809dba970","source":{"kind":"arxiv","id":"2507.16852","version":1},"attestation_state":"computed","paper":{"title":"SynthCTI: LLM-Driven Synthetic CTI Generation to enhance MITRE Technique Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"\\'Alvaro Ruiz-R\\'odenas, Daniel Garc\\'ia-Algora, Jaime Pujante S\\'aez, Jorge Blasco, Jos\\'e Luis Hern\\'andez-Ramos, Mario Rodr\\'iguez B\\'ejar","submitted_at":"2025-07-21T09:22:39Z","abstract_excerpt":"Cyber Threat Intelligence (CTI) mining involves extracting structured insights from unstructured threat data, enabling organizations to understand and respond to evolving adversarial behavior. A key task in CTI mining is mapping threat descriptions to MITRE ATT\\&CK techniques. However, this process is often performed manually, requiring expert knowledge and substantial effort. Automated approaches face two major challenges: the scarcity of high-quality labeled CTI data and class imbalance, where many techniques have very few examples. While domain-specific Large Language Models (LLMs) such as "},"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":"2507.16852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-21T09:22:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7d7ed8c1d1d5b71737918fe5a6bb4d66da8b70a7a2c402bdc2aaa3b69f0c8ce3","abstract_canon_sha256":"9981ca1821de651ad1b2f00efd3908fd1332a41bfe127211a15adac23216ddb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:57.152866Z","signature_b64":"WVSuHUk6lFUwvxhRs+xfvvSB5U8YdRAxo4a2li1LcCdK91OzB5SJfZyrLJ2E5PIsaC2SB3up0btMsHIypK3SAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6b6ebf59a475918175aa05b1418f2ffd077baf52fc91b81f74c142809dba970","last_reissued_at":"2026-07-05T11:41:57.152405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:57.152405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynthCTI: LLM-Driven Synthetic CTI Generation to enhance MITRE Technique Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"\\'Alvaro Ruiz-R\\'odenas, Daniel Garc\\'ia-Algora, Jaime Pujante S\\'aez, Jorge Blasco, Jos\\'e Luis Hern\\'andez-Ramos, Mario Rodr\\'iguez B\\'ejar","submitted_at":"2025-07-21T09:22:39Z","abstract_excerpt":"Cyber Threat Intelligence (CTI) mining involves extracting structured insights from unstructured threat data, enabling organizations to understand and respond to evolving adversarial behavior. A key task in CTI mining is mapping threat descriptions to MITRE ATT\\&CK techniques. However, this process is often performed manually, requiring expert knowledge and substantial effort. Automated approaches face two major challenges: the scarcity of high-quality labeled CTI data and class imbalance, where many techniques have very few examples. While domain-specific Large Language Models (LLMs) such as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16852","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/2507.16852/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":"2507.16852","created_at":"2026-07-05T11:41:57.152464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16852v1","created_at":"2026-07-05T11:41:57.152464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16852","created_at":"2026-07-05T11:41:57.152464+00:00"},{"alias_kind":"pith_short_12","alias_value":"423OX5M2I5MR","created_at":"2026-07-05T11:41:57.152464+00:00"},{"alias_kind":"pith_short_16","alias_value":"423OX5M2I5MRQF22","created_at":"2026-07-05T11:41:57.152464+00:00"},{"alias_kind":"pith_short_8","alias_value":"423OX5M2","created_at":"2026-07-05T11:41:57.152464+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/423OX5M2I5MRQF22UBNRIGHS77","json":"https://pith.science/pith/423OX5M2I5MRQF22UBNRIGHS77.json","graph_json":"https://pith.science/api/pith-number/423OX5M2I5MRQF22UBNRIGHS77/graph.json","events_json":"https://pith.science/api/pith-number/423OX5M2I5MRQF22UBNRIGHS77/events.json","paper":"https://pith.science/paper/423OX5M2"},"agent_actions":{"view_html":"https://pith.science/pith/423OX5M2I5MRQF22UBNRIGHS77","download_json":"https://pith.science/pith/423OX5M2I5MRQF22UBNRIGHS77.json","view_paper":"https://pith.science/paper/423OX5M2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16852&json=true","fetch_graph":"https://pith.science/api/pith-number/423OX5M2I5MRQF22UBNRIGHS77/graph.json","fetch_events":"https://pith.science/api/pith-number/423OX5M2I5MRQF22UBNRIGHS77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/423OX5M2I5MRQF22UBNRIGHS77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/423OX5M2I5MRQF22UBNRIGHS77/action/storage_attestation","attest_author":"https://pith.science/pith/423OX5M2I5MRQF22UBNRIGHS77/action/author_attestation","sign_citation":"https://pith.science/pith/423OX5M2I5MRQF22UBNRIGHS77/action/citation_signature","submit_replication":"https://pith.science/pith/423OX5M2I5MRQF22UBNRIGHS77/action/replication_record"}},"created_at":"2026-07-05T11:41:57.152464+00:00","updated_at":"2026-07-05T11:41:57.152464+00:00"}