{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LX4NPWFDEFVRRJLDHWCYV7XMFQ","short_pith_number":"pith:LX4NPWFD","schema_version":"1.0","canonical_sha256":"5df8d7d8a3216b18a5633d858afeec2c34ead0603c7e9686777c9582815ee3a9","source":{"kind":"arxiv","id":"2404.17110","version":1},"attestation_state":"computed","paper":{"title":"Software Vulnerability Prediction in Low-Resource Languages: An Empirical Study of CodeBERT and ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.SE","authors_text":"M. Ali Babar, Triet H. M. Le, Tung Hoang Thai","submitted_at":"2024-04-26T01:57:12Z","abstract_excerpt":"Background: Software Vulnerability (SV) prediction in emerging languages is increasingly important to ensure software security in modern systems. However, these languages usually have limited SV data for developing high-performing prediction models. Aims: We conduct an empirical study to evaluate the impact of SV data scarcity in emerging languages on the state-of-the-art SV prediction model and investigate potential solutions to enhance the performance. Method: We train and test the state-of-the-art model based on CodeBERT with and without data sampling techniques for function-level and line-"},"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":"2404.17110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-04-26T01:57:12Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"03d9562ea20033ff7e30f209129b58df1fc1892dad5818daf1b90728c505e8e9","abstract_canon_sha256":"4e26c09656b9ab54261f27a7b9df557f430ec2b8d44b9110504080f990c7104d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:32.973274Z","signature_b64":"XF3ndI9SMx+biMmGiM3Y4gu6QSXIUKM2hC0MlXbUM+7fdJKyNNp5Z76zG+XUBKZI5ceczM0h+hM0yCe0+9mJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5df8d7d8a3216b18a5633d858afeec2c34ead0603c7e9686777c9582815ee3a9","last_reissued_at":"2026-07-05T08:12:32.972846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:32.972846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Software Vulnerability Prediction in Low-Resource Languages: An Empirical Study of CodeBERT and ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.SE","authors_text":"M. Ali Babar, Triet H. M. Le, Tung Hoang Thai","submitted_at":"2024-04-26T01:57:12Z","abstract_excerpt":"Background: Software Vulnerability (SV) prediction in emerging languages is increasingly important to ensure software security in modern systems. However, these languages usually have limited SV data for developing high-performing prediction models. Aims: We conduct an empirical study to evaluate the impact of SV data scarcity in emerging languages on the state-of-the-art SV prediction model and investigate potential solutions to enhance the performance. Method: We train and test the state-of-the-art model based on CodeBERT with and without data sampling techniques for function-level and line-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17110","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/2404.17110/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":"2404.17110","created_at":"2026-07-05T08:12:32.972900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17110v1","created_at":"2026-07-05T08:12:32.972900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17110","created_at":"2026-07-05T08:12:32.972900+00:00"},{"alias_kind":"pith_short_12","alias_value":"LX4NPWFDEFVR","created_at":"2026-07-05T08:12:32.972900+00:00"},{"alias_kind":"pith_short_16","alias_value":"LX4NPWFDEFVRRJLD","created_at":"2026-07-05T08:12:32.972900+00:00"},{"alias_kind":"pith_short_8","alias_value":"LX4NPWFD","created_at":"2026-07-05T08:12:32.972900+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/LX4NPWFDEFVRRJLDHWCYV7XMFQ","json":"https://pith.science/pith/LX4NPWFDEFVRRJLDHWCYV7XMFQ.json","graph_json":"https://pith.science/api/pith-number/LX4NPWFDEFVRRJLDHWCYV7XMFQ/graph.json","events_json":"https://pith.science/api/pith-number/LX4NPWFDEFVRRJLDHWCYV7XMFQ/events.json","paper":"https://pith.science/paper/LX4NPWFD"},"agent_actions":{"view_html":"https://pith.science/pith/LX4NPWFDEFVRRJLDHWCYV7XMFQ","download_json":"https://pith.science/pith/LX4NPWFDEFVRRJLDHWCYV7XMFQ.json","view_paper":"https://pith.science/paper/LX4NPWFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17110&json=true","fetch_graph":"https://pith.science/api/pith-number/LX4NPWFDEFVRRJLDHWCYV7XMFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LX4NPWFDEFVRRJLDHWCYV7XMFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LX4NPWFDEFVRRJLDHWCYV7XMFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LX4NPWFDEFVRRJLDHWCYV7XMFQ/action/storage_attestation","attest_author":"https://pith.science/pith/LX4NPWFDEFVRRJLDHWCYV7XMFQ/action/author_attestation","sign_citation":"https://pith.science/pith/LX4NPWFDEFVRRJLDHWCYV7XMFQ/action/citation_signature","submit_replication":"https://pith.science/pith/LX4NPWFDEFVRRJLDHWCYV7XMFQ/action/replication_record"}},"created_at":"2026-07-05T08:12:32.972900+00:00","updated_at":"2026-07-05T08:12:32.972900+00:00"}