{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E3NRRWYT2OUCX54IMOYTEYHIW5","short_pith_number":"pith:E3NRRWYT","schema_version":"1.0","canonical_sha256":"26db18db13d3a82bf78863b13260e8b761e4c7b97a825de94f3ef82ef8897edc","source":{"kind":"arxiv","id":"2205.12424","version":1},"attestation_state":"computed","paper":{"title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Hazim Hanif, Sergio Maffeis","submitted_at":"2022-05-25T00:56:43Z","abstract_excerpt":"This paper presents VulBERTa, a deep learning approach to detect security vulnerabilities in source code. Our approach pre-trains a RoBERTa model with a custom tokenisation pipeline on real-world code from open-source C/C++ projects. The model learns a deep knowledge representation of the code syntax and semantics, which we leverage to train vulnerability detection classifiers. We evaluate our approach on binary and multi-class vulnerability detection tasks across several datasets (Vuldeepecker, Draper, REVEAL and muVuldeepecker) and benchmarks (CodeXGLUE and D2A). The evaluation results show "},"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":"2205.12424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2022-05-25T00:56:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"557c7fdc9ea5a57f5a12795384b99822c532500379fec41f7a3c2fabee56231f","abstract_canon_sha256":"4a8b41c577e74e4fa43dd23378b66d056c6062ac08cb897d7db07db99770e4ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:47.255959Z","signature_b64":"e41fbPycZlZR08fmptUCzVUB98pf9ll5pX99wn1Yf+mpP4IzY0CxaQzUhOKg1zdBzpIU6vXCPhBHovKmHZaACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26db18db13d3a82bf78863b13260e8b761e4c7b97a825de94f3ef82ef8897edc","last_reissued_at":"2026-07-05T06:21:47.255439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:47.255439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Hazim Hanif, Sergio Maffeis","submitted_at":"2022-05-25T00:56:43Z","abstract_excerpt":"This paper presents VulBERTa, a deep learning approach to detect security vulnerabilities in source code. Our approach pre-trains a RoBERTa model with a custom tokenisation pipeline on real-world code from open-source C/C++ projects. The model learns a deep knowledge representation of the code syntax and semantics, which we leverage to train vulnerability detection classifiers. We evaluate our approach on binary and multi-class vulnerability detection tasks across several datasets (Vuldeepecker, Draper, REVEAL and muVuldeepecker) and benchmarks (CodeXGLUE and D2A). The evaluation results show "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.12424","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/2205.12424/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":"2205.12424","created_at":"2026-07-05T06:21:47.255512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.12424v1","created_at":"2026-07-05T06:21:47.255512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.12424","created_at":"2026-07-05T06:21:47.255512+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3NRRWYT2OUC","created_at":"2026-07-05T06:21:47.255512+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3NRRWYT2OUCX54I","created_at":"2026-07-05T06:21:47.255512+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3NRRWYT","created_at":"2026-07-05T06:21:47.255512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16585","citing_title":"LLMxCPG: Context-Aware Vulnerability Detection Through Code Property Graph-Guided Large Language Models","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5","json":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5.json","graph_json":"https://pith.science/api/pith-number/E3NRRWYT2OUCX54IMOYTEYHIW5/graph.json","events_json":"https://pith.science/api/pith-number/E3NRRWYT2OUCX54IMOYTEYHIW5/events.json","paper":"https://pith.science/paper/E3NRRWYT"},"agent_actions":{"view_html":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5","download_json":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5.json","view_paper":"https://pith.science/paper/E3NRRWYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.12424&json=true","fetch_graph":"https://pith.science/api/pith-number/E3NRRWYT2OUCX54IMOYTEYHIW5/graph.json","fetch_events":"https://pith.science/api/pith-number/E3NRRWYT2OUCX54IMOYTEYHIW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5/action/storage_attestation","attest_author":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5/action/author_attestation","sign_citation":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5/action/citation_signature","submit_replication":"https://pith.science/pith/E3NRRWYT2OUCX54IMOYTEYHIW5/action/replication_record"}},"created_at":"2026-07-05T06:21:47.255512+00:00","updated_at":"2026-07-05T06:21:47.255512+00:00"}