{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TVUABN3XYTPMNJM3SGEMYKVJIR","short_pith_number":"pith:TVUABN3X","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"},"canonical_sha256":"9d6800b777c4dec6a59b9188cc2aa9444f3213361363ff5f1418b0309bfbd9fc","source":{"kind":"arxiv","id":"2407.17803","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17803","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17803v1","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17803","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"pith_short_12","alias_value":"TVUABN3XYTPM","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"pith_short_16","alias_value":"TVUABN3XYTPMNJM3","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"pith_short_8","alias_value":"TVUABN3X","created_at":"2026-07-05T08:48:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TVUABN3XYTPMNJM3SGEMYKVJIR","target":"record","payload":{"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"},"canonical_sha256":"9d6800b777c4dec6a59b9188cc2aa9444f3213361363ff5f1418b0309bfbd9fc","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"},"source_kind":"arxiv","source_id":"2407.17803","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":"2026-07-05T08:48:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vd9WfSqXOcZbOdcDP88jyhmXrYOtrifbZX/AnlwCrt3eulhs/ABbU5n9UOVFqCyzKqFIn47t4/5wl74lq6RIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:13:00.485424Z"},"content_sha256":"ce52fb7fe94a35c89f822ccfc2d9c1e54e0f989f6b7450b0294d5f07a49f446e","schema_version":"1.0","event_id":"sha256:ce52fb7fe94a35c89f822ccfc2d9c1e54e0f989f6b7450b0294d5f07a49f446e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TVUABN3XYTPMNJM3SGEMYKVJIR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:48:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZNB40b2e4321PfydMPRIrEBnokw+UHWWIcvi5TLtYWyeJf1BmHKfX1BZLRYmgPmrNbMVG3Dus4e8yDaxI9DDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:13:00.486013Z"},"content_sha256":"a48a1609944e712dda19f882fa579027e2355c4966e1c4b67623614bdf8c55c5","schema_version":"1.0","event_id":"sha256:a48a1609944e712dda19f882fa579027e2355c4966e1c4b67623614bdf8c55c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/bundle.json","state_url":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/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":"2026-08-11T18:13:00Z","links":{"resolver":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR","bundle":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/bundle.json","state":"https://pith.science/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TVUABN3XYTPMNJM3SGEMYKVJIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TVUABN3XYTPMNJM3SGEMYKVJIR","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":"0aad7a820659d064849888fc8ac8fcd1936f09113f88ca14ffed43660efd5e4e","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-25T06:22:25Z","title_canon_sha256":"6eca2fc234d0da912a4b37107eb77af3ca6cdc5e0a3e6c1a47d191f8edf8ebc1"},"schema_version":"1.0","source":{"id":"2407.17803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17803","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17803v1","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17803","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"pith_short_12","alias_value":"TVUABN3XYTPM","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"pith_short_16","alias_value":"TVUABN3XYTPMNJM3","created_at":"2026-07-05T08:48:21Z"},{"alias_kind":"pith_short_8","alias_value":"TVUABN3X","created_at":"2026-07-05T08:48:21Z"}],"graph_snapshots":[{"event_id":"sha256:a48a1609944e712dda19f882fa579027e2355c4966e1c4b67623614bdf8c55c5","target":"graph","created_at":"2026-07-05T08:48:21Z","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/2407.17803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"M. Ali Babar, Triet H. M. Le","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-25T06:22:25Z","title":"Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17803","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:ce52fb7fe94a35c89f822ccfc2d9c1e54e0f989f6b7450b0294d5f07a49f446e","target":"record","created_at":"2026-07-05T08:48:21Z","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":"0aad7a820659d064849888fc8ac8fcd1936f09113f88ca14ffed43660efd5e4e","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-25T06:22:25Z","title_canon_sha256":"6eca2fc234d0da912a4b37107eb77af3ca6cdc5e0a3e6c1a47d191f8edf8ebc1"},"schema_version":"1.0","source":{"id":"2407.17803","kind":"arxiv","version":1}},"canonical_sha256":"9d6800b777c4dec6a59b9188cc2aa9444f3213361363ff5f1418b0309bfbd9fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d6800b777c4dec6a59b9188cc2aa9444f3213361363ff5f1418b0309bfbd9fc","first_computed_at":"2026-07-05T08:48:21.777002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:21.777002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ky2qGT17tSNq248NuFqc2OhiDqG/qOq3/gGgheQSGKnPPU1SHFVtWrAbNALjFPc24YrgeNqJvK/DtuStWsExDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:21.777440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce52fb7fe94a35c89f822ccfc2d9c1e54e0f989f6b7450b0294d5f07a49f446e","sha256:a48a1609944e712dda19f882fa579027e2355c4966e1c4b67623614bdf8c55c5"],"state_sha256":"58aad8150a90164e11bb3da241b16e1490b18e4f5714bea3eb21a593c351510f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9KvcnYccv8thLNAxQqXG6sW79IHCnbEoDjadR1oVDiHrcPo76gO8anxScr7xIpiDSSrO2uUsuGfczLW+h3eqBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T18:13:00.490891Z","bundle_sha256":"074ed17db85e8a53d03e94acf634a86e325564bc2ef29e71c4588e60e75e0ba6"}}