{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YQQOZON7UQ3YHGGZOCYTL2S3HV","short_pith_number":"pith:YQQOZON7","schema_version":"1.0","canonical_sha256":"c420ecb9bfa4378398d970b135ea5b3d71a91dd70a9766ebad20b5b30b894b62","source":{"kind":"arxiv","id":"2407.10722","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Data Imbalance for Software Vulnerability Assessment: Does Data Augmentation Help?","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","submitted_at":"2024-07-15T13:47:55Z","abstract_excerpt":"Background: Software Vulnerability (SV) assessment is increasingly adopted to address the ever-increasing volume and complexity of SVs. Data-driven approaches have been widely used to automate SV assessment tasks, particularly the prediction of the Common Vulnerability Scoring System (CVSS) metrics such as exploitability, impact, and severity. SV assessment suffers from the imbalanced distributions of the CVSS classes, but such data imbalance has been hardly understood and addressed in the literature. Aims: We conduct a large-scale study to quantify the impacts of data imbalance and mitigate 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":"2407.10722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-15T13:47:55Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"7ae15380dda43f7ad896438b73f7670e9fe74c234b7726b5b427b1171f269e86","abstract_canon_sha256":"be5104180d86b446b0e3c9b15d0f40b0d35bd4f3ecef9c24326c70c1556955b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:03.261450Z","signature_b64":"6/JSUq9Hmorf2uBEDWlevCUT8Q9zX1I0BPRGtvXPyQXGgmXSPIEYj1AFbQXmnRT3v/bwzS9eQwyCm7zRFnYvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c420ecb9bfa4378398d970b135ea5b3d71a91dd70a9766ebad20b5b30b894b62","last_reissued_at":"2026-07-05T08:44:03.261056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:03.261056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Data Imbalance for Software Vulnerability Assessment: Does Data Augmentation Help?","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","submitted_at":"2024-07-15T13:47:55Z","abstract_excerpt":"Background: Software Vulnerability (SV) assessment is increasingly adopted to address the ever-increasing volume and complexity of SVs. Data-driven approaches have been widely used to automate SV assessment tasks, particularly the prediction of the Common Vulnerability Scoring System (CVSS) metrics such as exploitability, impact, and severity. SV assessment suffers from the imbalanced distributions of the CVSS classes, but such data imbalance has been hardly understood and addressed in the literature. Aims: We conduct a large-scale study to quantify the impacts of data imbalance and mitigate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10722","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/2407.10722/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":"2407.10722","created_at":"2026-07-05T08:44:03.261113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10722v1","created_at":"2026-07-05T08:44:03.261113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10722","created_at":"2026-07-05T08:44:03.261113+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQQOZON7UQ3Y","created_at":"2026-07-05T08:44:03.261113+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQQOZON7UQ3YHGGZ","created_at":"2026-07-05T08:44:03.261113+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQQOZON7","created_at":"2026-07-05T08:44:03.261113+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/YQQOZON7UQ3YHGGZOCYTL2S3HV","json":"https://pith.science/pith/YQQOZON7UQ3YHGGZOCYTL2S3HV.json","graph_json":"https://pith.science/api/pith-number/YQQOZON7UQ3YHGGZOCYTL2S3HV/graph.json","events_json":"https://pith.science/api/pith-number/YQQOZON7UQ3YHGGZOCYTL2S3HV/events.json","paper":"https://pith.science/paper/YQQOZON7"},"agent_actions":{"view_html":"https://pith.science/pith/YQQOZON7UQ3YHGGZOCYTL2S3HV","download_json":"https://pith.science/pith/YQQOZON7UQ3YHGGZOCYTL2S3HV.json","view_paper":"https://pith.science/paper/YQQOZON7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10722&json=true","fetch_graph":"https://pith.science/api/pith-number/YQQOZON7UQ3YHGGZOCYTL2S3HV/graph.json","fetch_events":"https://pith.science/api/pith-number/YQQOZON7UQ3YHGGZOCYTL2S3HV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQQOZON7UQ3YHGGZOCYTL2S3HV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQQOZON7UQ3YHGGZOCYTL2S3HV/action/storage_attestation","attest_author":"https://pith.science/pith/YQQOZON7UQ3YHGGZOCYTL2S3HV/action/author_attestation","sign_citation":"https://pith.science/pith/YQQOZON7UQ3YHGGZOCYTL2S3HV/action/citation_signature","submit_replication":"https://pith.science/pith/YQQOZON7UQ3YHGGZOCYTL2S3HV/action/replication_record"}},"created_at":"2026-07-05T08:44:03.261113+00:00","updated_at":"2026-07-05T08:44:03.261113+00:00"}