{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LZP6PFHDS2PPXB7QXKHHV7HLNS","short_pith_number":"pith:LZP6PFHD","schema_version":"1.0","canonical_sha256":"5e5fe794e3969efb87f0ba8e7afceb6c9cd889e337b6095248a6c96c91c8e76c","source":{"kind":"arxiv","id":"2012.11701","version":3},"attestation_state":"computed","paper":{"title":"Learning from What We Know: How to Perform Vulnerability Prediction using Noisy Historical Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CR","authors_text":"Aayush Garg, Matthieu Jimenez, Maxime Cordy, Mike Papadakis, Renzo Degiovanni, Yves Le Traon","submitted_at":"2020-12-21T21:59:12Z","abstract_excerpt":"Vulnerability prediction refers to the problem of identifying system components that are most likely to be vulnerable. Typically, this problem is tackled by training binary classifiers on historical data. Unfortunately, recent research has shown that such approaches underperform due to the following two reasons: a) the imbalanced nature of the problem, and b) the inherently noisy historical data, i.e., most vulnerabilities are discovered much later than they are introduced. This misleads classifiers as they learn to recognize actual vulnerable components as non-vulnerable. To tackle these issu"},"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":"2012.11701","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2020-12-21T21:59:12Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"5c4ff3d2aee4e3d228f643b27d4ea6ae4de4c736880537201bf69807f69b3c07","abstract_canon_sha256":"5dd3ba05aef89f3136131e43ff1041349fe7c44e4b8a1c12abf60d656d106483"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:26.537287Z","signature_b64":"UWArKcYhx4WjeTD/Ethlq8NmtKm9LQw8NplpeWNyHswP1puv/Vsr08BOUURNv4HovMgagt/I0sSszCOLJdpgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e5fe794e3969efb87f0ba8e7afceb6c9cd889e337b6095248a6c96c91c8e76c","last_reissued_at":"2026-07-05T04:58:26.536832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:26.536832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from What We Know: How to Perform Vulnerability Prediction using Noisy Historical Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CR","authors_text":"Aayush Garg, Matthieu Jimenez, Maxime Cordy, Mike Papadakis, Renzo Degiovanni, Yves Le Traon","submitted_at":"2020-12-21T21:59:12Z","abstract_excerpt":"Vulnerability prediction refers to the problem of identifying system components that are most likely to be vulnerable. Typically, this problem is tackled by training binary classifiers on historical data. Unfortunately, recent research has shown that such approaches underperform due to the following two reasons: a) the imbalanced nature of the problem, and b) the inherently noisy historical data, i.e., most vulnerabilities are discovered much later than they are introduced. This misleads classifiers as they learn to recognize actual vulnerable components as non-vulnerable. To tackle these issu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11701","kind":"arxiv","version":3},"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/2012.11701/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":"2012.11701","created_at":"2026-07-05T04:58:26.536896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11701v3","created_at":"2026-07-05T04:58:26.536896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11701","created_at":"2026-07-05T04:58:26.536896+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZP6PFHDS2PP","created_at":"2026-07-05T04:58:26.536896+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZP6PFHDS2PPXB7Q","created_at":"2026-07-05T04:58:26.536896+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZP6PFHD","created_at":"2026-07-05T04:58:26.536896+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/LZP6PFHDS2PPXB7QXKHHV7HLNS","json":"https://pith.science/pith/LZP6PFHDS2PPXB7QXKHHV7HLNS.json","graph_json":"https://pith.science/api/pith-number/LZP6PFHDS2PPXB7QXKHHV7HLNS/graph.json","events_json":"https://pith.science/api/pith-number/LZP6PFHDS2PPXB7QXKHHV7HLNS/events.json","paper":"https://pith.science/paper/LZP6PFHD"},"agent_actions":{"view_html":"https://pith.science/pith/LZP6PFHDS2PPXB7QXKHHV7HLNS","download_json":"https://pith.science/pith/LZP6PFHDS2PPXB7QXKHHV7HLNS.json","view_paper":"https://pith.science/paper/LZP6PFHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11701&json=true","fetch_graph":"https://pith.science/api/pith-number/LZP6PFHDS2PPXB7QXKHHV7HLNS/graph.json","fetch_events":"https://pith.science/api/pith-number/LZP6PFHDS2PPXB7QXKHHV7HLNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZP6PFHDS2PPXB7QXKHHV7HLNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZP6PFHDS2PPXB7QXKHHV7HLNS/action/storage_attestation","attest_author":"https://pith.science/pith/LZP6PFHDS2PPXB7QXKHHV7HLNS/action/author_attestation","sign_citation":"https://pith.science/pith/LZP6PFHDS2PPXB7QXKHHV7HLNS/action/citation_signature","submit_replication":"https://pith.science/pith/LZP6PFHDS2PPXB7QXKHHV7HLNS/action/replication_record"}},"created_at":"2026-07-05T04:58:26.536896+00:00","updated_at":"2026-07-05T04:58:26.536896+00:00"}