{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6SHB3DFVBCPVBPW7CZQRKCY3A2","short_pith_number":"pith:6SHB3DFV","schema_version":"1.0","canonical_sha256":"f48e1d8cb5089f50bedf1661150b1b06910d462a5523cc3dd55f3771fd2be8f5","source":{"kind":"arxiv","id":"2504.21039","version":1},"attestation_state":"computed","paper":{"title":"Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Adam Swanda, Alexander Chen, Aman Priyanshu, Amin Karbasi, Amy Chang, Anu Vellore, Avi Zohary, Baturay Saglam, Blaine Nelson, Dhruv Kedia, Fraser Burch, Hyrum Anderson, Kojin Oshiba, Massimo Aufiero, Omar Santos, Paul Kassianik, Sajana Weerawardhena, Yaron Singer","submitted_at":"2025-04-28T08:41:12Z","abstract_excerpt":"As transformer-based large language models (LLMs) increasingly permeate society, they have revolutionized domains such as software engineering, creative writing, and digital arts. However, their adoption in cybersecurity remains limited due to challenges like scarcity of specialized training data and complexity of representing cybersecurity-specific knowledge. To address these gaps, we present Foundation-Sec-8B, a cybersecurity-focused LLM built on the Llama 3.1 architecture and enhanced through continued pretraining on a carefully curated cybersecurity corpus. We evaluate Foundation-Sec-8B ac"},"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":"2504.21039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-04-28T08:41:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"023cf5e910e5ef0ce14706e8356ec63869e5017c2b61e9afb07c0c2cb2be4cfa","abstract_canon_sha256":"4ec62e84980ac5f417557a32691c04e802bf3a6f81640bda69f410fd496ec196"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:55.608792Z","signature_b64":"cRggXG7ARoLGmPaiR5Gwd53bllzrohoywxAVKgDDdWaEx4wTS3ADqcgQnAe9UaNjrDsVZfuCnz68QNX2UBPICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f48e1d8cb5089f50bedf1661150b1b06910d462a5523cc3dd55f3771fd2be8f5","last_reissued_at":"2026-07-05T10:55:55.608298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:55.608298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Adam Swanda, Alexander Chen, Aman Priyanshu, Amin Karbasi, Amy Chang, Anu Vellore, Avi Zohary, Baturay Saglam, Blaine Nelson, Dhruv Kedia, Fraser Burch, Hyrum Anderson, Kojin Oshiba, Massimo Aufiero, Omar Santos, Paul Kassianik, Sajana Weerawardhena, Yaron Singer","submitted_at":"2025-04-28T08:41:12Z","abstract_excerpt":"As transformer-based large language models (LLMs) increasingly permeate society, they have revolutionized domains such as software engineering, creative writing, and digital arts. However, their adoption in cybersecurity remains limited due to challenges like scarcity of specialized training data and complexity of representing cybersecurity-specific knowledge. To address these gaps, we present Foundation-Sec-8B, a cybersecurity-focused LLM built on the Llama 3.1 architecture and enhanced through continued pretraining on a carefully curated cybersecurity corpus. We evaluate Foundation-Sec-8B ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21039","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/2504.21039/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":"2504.21039","created_at":"2026-07-05T10:55:55.608369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21039v1","created_at":"2026-07-05T10:55:55.608369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21039","created_at":"2026-07-05T10:55:55.608369+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SHB3DFVBCPV","created_at":"2026-07-05T10:55:55.608369+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SHB3DFVBCPVBPW7","created_at":"2026-07-05T10:55:55.608369+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SHB3DFV","created_at":"2026-07-05T10:55:55.608369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27091","citing_title":"Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17986","citing_title":"ShellGames: Speculative LLM-Driven SSH Deception","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08168","citing_title":"Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04730","citing_title":"Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04295","citing_title":"LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20571","citing_title":"Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28146","citing_title":"Cybersecurity AI (CAI) Dataset","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17075","citing_title":"A Red Teaming Framework for Evaluating Robustness of AI-enabled Security Orchestration, Automation, and Response Systems","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10808","citing_title":"Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00072","citing_title":"XekRung Technical Report","ref_index":160,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2","json":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2.json","graph_json":"https://pith.science/api/pith-number/6SHB3DFVBCPVBPW7CZQRKCY3A2/graph.json","events_json":"https://pith.science/api/pith-number/6SHB3DFVBCPVBPW7CZQRKCY3A2/events.json","paper":"https://pith.science/paper/6SHB3DFV"},"agent_actions":{"view_html":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2","download_json":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2.json","view_paper":"https://pith.science/paper/6SHB3DFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21039&json=true","fetch_graph":"https://pith.science/api/pith-number/6SHB3DFVBCPVBPW7CZQRKCY3A2/graph.json","fetch_events":"https://pith.science/api/pith-number/6SHB3DFVBCPVBPW7CZQRKCY3A2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2/action/storage_attestation","attest_author":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2/action/author_attestation","sign_citation":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2/action/citation_signature","submit_replication":"https://pith.science/pith/6SHB3DFVBCPVBPW7CZQRKCY3A2/action/replication_record"}},"created_at":"2026-07-05T10:55:55.608369+00:00","updated_at":"2026-07-05T10:55:55.608369+00:00"}