{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YZX4EWAFJLLYH4M6R5BGFMF4QC","short_pith_number":"pith:YZX4EWAF","schema_version":"1.0","canonical_sha256":"c66fc258054ad783f19e8f4262b0bc80bf2052e3ca405df09f5836b56572028b","source":{"kind":"arxiv","id":"2602.03012","version":2},"attestation_state":"computed","paper":{"title":"CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chuan Xiao, Jingyuan Zhang, Qingfu Zhu, Rain Huang, Shiqi Zhou, Wanxiang Che, Wencong Zeng, Xianzhen Luo, Xing Yue, Yang Yue, Zhiyuan Ma","submitted_at":"2026-02-03T02:27:16Z","abstract_excerpt":"Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fully executable agentic tasks. Cross-validation against human expert reproductions shows that CVE-Factory achieves 95\\% solution correctness and 96\\% environment fidelity, confirming its expert-level q"},"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":"2602.03012","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-02-03T02:27:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0ab9097c6c05c46dcc09dc39df0859be91072d4579a42e991a186d7bdac80053","abstract_canon_sha256":"e9bafa8ed32f970c2e2f0bdff9c820aad6371c3d0688dec8206ee8f61ac77c79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:04.406067Z","signature_b64":"6IL69xEQN3oX8JdsXr/aeHNXYMm3wvTZwC3zcxbFlMsJw0f/tcnTOkxiDwhRJukMpxdSXdbR2tE1/ptoO2yoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c66fc258054ad783f19e8f4262b0bc80bf2052e3ca405df09f5836b56572028b","last_reissued_at":"2026-05-20T00:03:04.405310Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:04.405310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CVE-Factory: Scaling Expert-Level Agentic Tasks for Code Security Vulnerability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Chuan Xiao, Jingyuan Zhang, Qingfu Zhu, Rain Huang, Shiqi Zhou, Wanxiang Che, Wencong Zeng, Xianzhen Luo, Xing Yue, Yang Yue, Zhiyuan Ma","submitted_at":"2026-02-03T02:27:16Z","abstract_excerpt":"Evaluating and improving the security capabilities of code agents requires high-quality, executable vulnerability tasks. However, existing works rely on costly, unscalable manual reproduction and suffer from outdated data distributions. To address these, we present CVE-Factory, the first multi-agent framework to achieve expert-level quality in automatically transforming sparse CVE metadata into fully executable agentic tasks. Cross-validation against human expert reproductions shows that CVE-Factory achieves 95\\% solution correctness and 96\\% environment fidelity, confirming its expert-level q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03012","kind":"arxiv","version":2},"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/2602.03012/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":"2602.03012","created_at":"2026-05-20T00:03:04.405445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.03012v2","created_at":"2026-05-20T00:03:04.405445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03012","created_at":"2026-05-20T00:03:04.405445+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZX4EWAFJLLY","created_at":"2026-05-20T00:03:04.405445+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZX4EWAFJLLYH4M6","created_at":"2026-05-20T00:03:04.405445+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZX4EWAF","created_at":"2026-05-20T00:03:04.405445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.03453","citing_title":"FORGE: Multi-Agent Graduated Exploitation and Detection Engineering","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC","json":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC.json","graph_json":"https://pith.science/api/pith-number/YZX4EWAFJLLYH4M6R5BGFMF4QC/graph.json","events_json":"https://pith.science/api/pith-number/YZX4EWAFJLLYH4M6R5BGFMF4QC/events.json","paper":"https://pith.science/paper/YZX4EWAF"},"agent_actions":{"view_html":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC","download_json":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC.json","view_paper":"https://pith.science/paper/YZX4EWAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.03012&json=true","fetch_graph":"https://pith.science/api/pith-number/YZX4EWAFJLLYH4M6R5BGFMF4QC/graph.json","fetch_events":"https://pith.science/api/pith-number/YZX4EWAFJLLYH4M6R5BGFMF4QC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC/action/storage_attestation","attest_author":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC/action/author_attestation","sign_citation":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC/action/citation_signature","submit_replication":"https://pith.science/pith/YZX4EWAFJLLYH4M6R5BGFMF4QC/action/replication_record"}},"created_at":"2026-05-20T00:03:04.405445+00:00","updated_at":"2026-05-20T00:03:04.405445+00:00"}