{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3YXJGKXMLKCVQTYBMCPORDGBJC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f6f52eced5fe524f2d11b287ad0429042ff103ed8450003a436cbd72f072162e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-08T13:31:29Z","title_canon_sha256":"8b720aeca8c9e5fef340f0c4edce516c8d7747ec00695fc3689331b9a6085c52"},"schema_version":"1.0","source":{"id":"2410.06030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06030","created_at":"2026-07-05T09:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06030v1","created_at":"2026-07-05T09:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06030","created_at":"2026-07-05T09:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"3YXJGKXMLKCV","created_at":"2026-07-05T09:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"3YXJGKXMLKCVQTYB","created_at":"2026-07-05T09:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"3YXJGKXM","created_at":"2026-07-05T09:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:1b33a6c26e8cd2d612712d8281c85af17a1c0c1f73f970ec207cb0bede6116b5","target":"graph","created_at":"2026-07-05T09:17:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.06030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vulnerability detection is a crucial yet challenging task to identify potential weaknesses in software for cyber security. Recently, deep learning (DL) has made great progress in automating the detection process. Due to the complex multi-layer structure and a large number of parameters, a DL model requires massive labeled (vulnerable or secure) source code to gain knowledge to effectively distinguish between vulnerable and secure code. In the literature, many datasets have been created to train DL models for this purpose. However, these datasets suffer from several issues that will lead to low","authors_text":"Seifeddine Bettaieb, Yuejun Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-08T13:31:29Z","title":"Data Quality Issues in Vulnerability Detection Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06030","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:473566d73af7966d59732dcf42e57ebc4a8437a0c79383f9ccff290e1e78b0a5","target":"record","created_at":"2026-07-05T09:17:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f6f52eced5fe524f2d11b287ad0429042ff103ed8450003a436cbd72f072162e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-08T13:31:29Z","title_canon_sha256":"8b720aeca8c9e5fef340f0c4edce516c8d7747ec00695fc3689331b9a6085c52"},"schema_version":"1.0","source":{"id":"2410.06030","kind":"arxiv","version":1}},"canonical_sha256":"de2e932aec5a85584f01609ee88cc148905f5a293df3bd9c4d44f1676c5d4db8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de2e932aec5a85584f01609ee88cc148905f5a293df3bd9c4d44f1676c5d4db8","first_computed_at":"2026-07-05T09:17:54.803432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:54.803432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pcRoS6eTl0XQdzuBVMwBZ3gDEKAypC4o72pz82PsymcO78GOT49BnT5648W8WB63j5J++0Htx34JaA46s2ZPDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:54.804007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:473566d73af7966d59732dcf42e57ebc4a8437a0c79383f9ccff290e1e78b0a5","sha256:1b33a6c26e8cd2d612712d8281c85af17a1c0c1f73f970ec207cb0bede6116b5"],"state_sha256":"d5e573877960eb3cbf102dfd5ef8e9bfc0a119a6b82a11e4c1c92e9550917e4d"}