{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TVUABN3XYTPMNJM3SGEMYKVJIR","short_pith_number":"pith:TVUABN3X","schema_version":"1.0","canonical_sha256":"9d6800b777c4dec6a59b9188cc2aa9444f3213361363ff5f1418b0309bfbd9fc","source":{"kind":"arxiv","id":"2407.17803","version":1},"attestation_state":"computed","paper":{"title":"Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?","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":"2024-07-25T06:22:25Z","abstract_excerpt":"Background: Software Vulnerability (SV) prediction needs large-sized and high-quality data to perform well. Current SV datasets mostly require expensive labeling efforts by experts (human-labeled) and thus are limited in size. Meanwhile, there are growing efforts in automatic SV labeling at scale. However, the fitness of auto-labeled data for SV prediction is still largely unknown. Aims: We quantitatively and qualitatively study the quality and use of the state-of-the-art auto-labeled SV data, D2A, for SV prediction. Method: Using multiple sources and manual validation, we curate clean SV data"},"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":"2407.17803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-25T06:22:25Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"6eca2fc234d0da912a4b37107eb77af3ca6cdc5e0a3e6c1a47d191f8edf8ebc1","abstract_canon_sha256":"0aad7a820659d064849888fc8ac8fcd1936f09113f88ca14ffed43660efd5e4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:21.777440Z","signature_b64":"ky2qGT17tSNq248NuFqc2OhiDqG/qOq3/gGgheQSGKnPPU1SHFVtWrAbNALjFPc24YrgeNqJvK/DtuStWsExDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d6800b777c4dec6a59b9188cc2aa9444f3213361363ff5f1418b0309bfbd9fc","last_reissued_at":"2026-07-05T08:48:21.777002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:21.777002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?","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":"2024-07-25T06:22:25Z","abstract_excerpt":"Background: Software Vulnerability (SV) prediction needs large-sized and high-quality data to perform well. Current SV datasets mostly require expensive labeling efforts by experts (human-labeled) and thus are limited in size. Meanwhile, there are growing efforts in automatic SV labeling at scale. However, the fitness of auto-labeled data for SV prediction is still largely unknown. Aims: We quantitatively and qualitatively study the quality and use of the state-of-the-art auto-labeled SV data, D2A, for SV prediction. Method: Using multiple sources and manual validation, we curate clean SV data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17803","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/2407.17803/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":"2407.17803","created_at":"2026-07-05T08:48:21.777070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17803v1","created_at":"2026-07-05T08:48:21.777070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17803","created_at":"2026-07-05T08:48:21.777070+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVUABN3XYTPM","created_at":"2026-07-05T08:48:21.777070+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVUABN3XYTPMNJM3","created_at":"2026-07-05T08:48:21.777070+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVUABN3X","created_at":"2026-07-05T08:48:21.777070+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/TVUABN3XYTPMNJM3SGEMYKVJIR","json":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR.json","graph_json":"https://pith.science/api/pith-number/TVUABN3XYTPMNJM3SGEMYKVJIR/graph.json","events_json":"https://pith.science/api/pith-number/TVUABN3XYTPMNJM3SGEMYKVJIR/events.json","paper":"https://pith.science/paper/TVUABN3X"},"agent_actions":{"view_html":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR","download_json":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR.json","view_paper":"https://pith.science/paper/TVUABN3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17803&json=true","fetch_graph":"https://pith.science/api/pith-number/TVUABN3XYTPMNJM3SGEMYKVJIR/graph.json","fetch_events":"https://pith.science/api/pith-number/TVUABN3XYTPMNJM3SGEMYKVJIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/action/storage_attestation","attest_author":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/action/author_attestation","sign_citation":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/action/citation_signature","submit_replication":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/action/replication_record"}},"created_at":"2026-07-05T08:48:21.777070+00:00","updated_at":"2026-07-05T08:48:21.777070+00:00"}