{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:54UPOPDPON2EDTCV2GRTKMFJVV","short_pith_number":"pith:54UPOPDP","canonical_record":{"source":{"id":"2301.05456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-13T09:49:30Z","cross_cats_sorted":[],"title_canon_sha256":"1ee88a4548ce4853614e4be883529d27a29c05dac18f30da4dbc902d8de2ac20","abstract_canon_sha256":"b1a65318fbd46a69036d5003822ab4b0011f0c99a7a03a68970dbb7ad0d5cb27"},"schema_version":"1.0"},"canonical_sha256":"ef28f73c6f737441cc55d1a33530a9ad67e07f7bd80af0e7bf5d53d9c240c282","source":{"kind":"arxiv","id":"2301.05456","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05456","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05456v1","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05456","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"pith_short_12","alias_value":"54UPOPDPON2E","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"54UPOPDPON2EDTCV","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"54UPOPDP","created_at":"2026-07-05T05:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:54UPOPDPON2EDTCV2GRTKMFJVV","target":"record","payload":{"canonical_record":{"source":{"id":"2301.05456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-13T09:49:30Z","cross_cats_sorted":[],"title_canon_sha256":"1ee88a4548ce4853614e4be883529d27a29c05dac18f30da4dbc902d8de2ac20","abstract_canon_sha256":"b1a65318fbd46a69036d5003822ab4b0011f0c99a7a03a68970dbb7ad0d5cb27"},"schema_version":"1.0"},"canonical_sha256":"ef28f73c6f737441cc55d1a33530a9ad67e07f7bd80af0e7bf5d53d9c240c282","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:53.178359Z","signature_b64":"f6Uk60uVyyaXxvbuDLzyPnxnst9Vu82vDN/3P1fU3BRaz2kbRw2YyARRcT2WMHpiBcuEh2irLi0Qj5zC3LcFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef28f73c6f737441cc55d1a33530a9ad67e07f7bd80af0e7bf5d53d9c240c282","last_reissued_at":"2026-07-05T05:32:53.177912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:53.177912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.05456","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:32:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qskHrvGrjBCE0hdYLScgHhkD/10ZeuKw1ssZUOTTIWQhNt2ronFVo+L5eLCSJL/JJT/WrqNP4fpX6xLn/WyHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:38:11.700305Z"},"content_sha256":"584c3a0a12a1ccd04d4f2d713f6f8d06c91a920ec596a95e0be33c7c9f53e083","schema_version":"1.0","event_id":"sha256:584c3a0a12a1ccd04d4f2d713f6f8d06c91a920ec596a95e0be33c7c9f53e083"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:54UPOPDPON2EDTCV2GRTKMFJVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Quality for Software Vulnerability Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"M. Ali Babar, Mehdi Kholoosi, Roland Croft","submitted_at":"2023-01-13T09:49:30Z","abstract_excerpt":"The use of learning-based techniques to achieve automated software vulnerability detection has been of longstanding interest within the software security domain. These data-driven solutions are enabled by large software vulnerability datasets used for training and benchmarking. However, we observe that the quality of the data powering these solutions is currently ill-considered, hindering the reliability and value of produced outcomes. Whilst awareness of software vulnerability data preparation challenges is growing, there has been little investigation into the potential negative impacts of so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05456","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/2301.05456/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:32:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/GK0mAFZJnNV4ikF03t9Xh9jlR3v5GTsnFwtd8oTXI50vsBwTKtWJfOgcUUGKpNz/+Qd/eZjfd1xGIhFzAgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:38:11.700693Z"},"content_sha256":"af465748b1786db69f52f5a3e5b5e79e5cf1564ad38fe2e80225d5f67c5a2d6d","schema_version":"1.0","event_id":"sha256:af465748b1786db69f52f5a3e5b5e79e5cf1564ad38fe2e80225d5f67c5a2d6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54UPOPDPON2EDTCV2GRTKMFJVV/bundle.json","state_url":"https://pith.science/pith/54UPOPDPON2EDTCV2GRTKMFJVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54UPOPDPON2EDTCV2GRTKMFJVV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T18:38:11Z","links":{"resolver":"https://pith.science/pith/54UPOPDPON2EDTCV2GRTKMFJVV","bundle":"https://pith.science/pith/54UPOPDPON2EDTCV2GRTKMFJVV/bundle.json","state":"https://pith.science/pith/54UPOPDPON2EDTCV2GRTKMFJVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54UPOPDPON2EDTCV2GRTKMFJVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:54UPOPDPON2EDTCV2GRTKMFJVV","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":"b1a65318fbd46a69036d5003822ab4b0011f0c99a7a03a68970dbb7ad0d5cb27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-13T09:49:30Z","title_canon_sha256":"1ee88a4548ce4853614e4be883529d27a29c05dac18f30da4dbc902d8de2ac20"},"schema_version":"1.0","source":{"id":"2301.05456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05456","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05456v1","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05456","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"pith_short_12","alias_value":"54UPOPDPON2E","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"54UPOPDPON2EDTCV","created_at":"2026-07-05T05:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"54UPOPDP","created_at":"2026-07-05T05:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:af465748b1786db69f52f5a3e5b5e79e5cf1564ad38fe2e80225d5f67c5a2d6d","target":"graph","created_at":"2026-07-05T05:32:53Z","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/2301.05456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of learning-based techniques to achieve automated software vulnerability detection has been of longstanding interest within the software security domain. These data-driven solutions are enabled by large software vulnerability datasets used for training and benchmarking. However, we observe that the quality of the data powering these solutions is currently ill-considered, hindering the reliability and value of produced outcomes. Whilst awareness of software vulnerability data preparation challenges is growing, there has been little investigation into the potential negative impacts of so","authors_text":"M. Ali Babar, Mehdi Kholoosi, Roland Croft","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-13T09:49:30Z","title":"Data Quality for Software Vulnerability Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05456","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":"sha256:584c3a0a12a1ccd04d4f2d713f6f8d06c91a920ec596a95e0be33c7c9f53e083","target":"record","created_at":"2026-07-05T05:32:53Z","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":"b1a65318fbd46a69036d5003822ab4b0011f0c99a7a03a68970dbb7ad0d5cb27","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-01-13T09:49:30Z","title_canon_sha256":"1ee88a4548ce4853614e4be883529d27a29c05dac18f30da4dbc902d8de2ac20"},"schema_version":"1.0","source":{"id":"2301.05456","kind":"arxiv","version":1}},"canonical_sha256":"ef28f73c6f737441cc55d1a33530a9ad67e07f7bd80af0e7bf5d53d9c240c282","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef28f73c6f737441cc55d1a33530a9ad67e07f7bd80af0e7bf5d53d9c240c282","first_computed_at":"2026-07-05T05:32:53.177912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:32:53.177912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f6Uk60uVyyaXxvbuDLzyPnxnst9Vu82vDN/3P1fU3BRaz2kbRw2YyARRcT2WMHpiBcuEh2irLi0Qj5zC3LcFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:32:53.178359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.05456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:584c3a0a12a1ccd04d4f2d713f6f8d06c91a920ec596a95e0be33c7c9f53e083","sha256:af465748b1786db69f52f5a3e5b5e79e5cf1564ad38fe2e80225d5f67c5a2d6d"],"state_sha256":"3ae3021ee26acb6a0ee5a1704c01e4c89b4a120393bf162fedcf172598ab16fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3rohO+38qFwY1OihAvJLKv5ugSfpNotrec4t8DMhiUxWaO/NW01hN/OGQhvfZ90/z0Tt8SJT/c1wEcgEa+8iDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T18:38:11.702724Z","bundle_sha256":"961118dd6015a364435e4462b11bf512686b4ae76852936d9d891b9a1b4a7630"}}