{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G57Q6GTYMR7AF7NGSVS7FW5QMR","short_pith_number":"pith:G57Q6GTY","schema_version":"1.0","canonical_sha256":"377f0f1a78647e02fda69565f2dbb064697509776c0fa853448e317d6cad169e","source":{"kind":"arxiv","id":"2608.02407","version":1},"attestation_state":"computed","paper":{"title":"Antares: Foundation Models for Agentic Vulnerability Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Aman Priyanshu, Amin Karbasi, Arthur Goldblatt, Baturay Saglam, Didier Chapoteau, Fraser Burch, Jianliang He, Kimia Majd, Supriti Vijay, Takahiro Matsumoto, Zhuoran Yang","submitted_at":"2026-08-03T15:49:14Z","abstract_excerpt":"Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We present Antares, a family of compact language models (350M, 1B, and 3B parameters) for agentic vulnerability localization. Based on IBM Granite base models, Antares is trained through a two-stage pipeline that combines supervised fine-tuning on cybersecurity reasoning and repository exploration data with reinforcement learning from verifiable rewards over vulnerable repositories. Across extensive evaluations, Antares-3B a"},"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":"2608.02407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-03T15:49:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19ad5bbf37e2b0af1613675de9d220b0de58240a715fe945c65fc763abb50084","abstract_canon_sha256":"a4c77d988162011cae297e3585fa306629e59d34362221b136d32b28ef1bb707"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:12:09.556453Z","signature_b64":"KOYvv+zGjYy1NIDFH5hTf04i9OFHHkmlawZfjkvp0Oy98GZfjjg939QTCDA8KgxOgaXhfvK6VdPbmUTW1Xh0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"377f0f1a78647e02fda69565f2dbb064697509776c0fa853448e317d6cad169e","last_reissued_at":"2026-08-04T02:12:09.554607Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:12:09.554607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Antares: Foundation Models for Agentic Vulnerability Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Aman Priyanshu, Amin Karbasi, Arthur Goldblatt, Baturay Saglam, Didier Chapoteau, Fraser Burch, Jianliang He, Kimia Majd, Supriti Vijay, Takahiro Matsumoto, Zhuoran Yang","submitted_at":"2026-08-03T15:49:14Z","abstract_excerpt":"Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We present Antares, a family of compact language models (350M, 1B, and 3B parameters) for agentic vulnerability localization. Based on IBM Granite base models, Antares is trained through a two-stage pipeline that combines supervised fine-tuning on cybersecurity reasoning and repository exploration data with reinforcement learning from verifiable rewards over vulnerable repositories. Across extensive evaluations, Antares-3B a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02407","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/2608.02407/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":"2608.02407","created_at":"2026-08-04T02:12:09.556378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02407v1","created_at":"2026-08-04T02:12:09.556378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02407","created_at":"2026-08-04T02:12:09.556378+00:00"},{"alias_kind":"pith_short_12","alias_value":"G57Q6GTYMR7A","created_at":"2026-08-04T02:12:09.556378+00:00"},{"alias_kind":"pith_short_16","alias_value":"G57Q6GTYMR7AF7NG","created_at":"2026-08-04T02:12:09.556378+00:00"},{"alias_kind":"pith_short_8","alias_value":"G57Q6GTY","created_at":"2026-08-04T02:12:09.556378+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/G57Q6GTYMR7AF7NGSVS7FW5QMR","json":"https://pith.science/pith/G57Q6GTYMR7AF7NGSVS7FW5QMR.json","graph_json":"https://pith.science/api/pith-number/G57Q6GTYMR7AF7NGSVS7FW5QMR/graph.json","events_json":"https://pith.science/api/pith-number/G57Q6GTYMR7AF7NGSVS7FW5QMR/events.json","paper":"https://pith.science/paper/G57Q6GTY"},"agent_actions":{"view_html":"https://pith.science/pith/G57Q6GTYMR7AF7NGSVS7FW5QMR","download_json":"https://pith.science/pith/G57Q6GTYMR7AF7NGSVS7FW5QMR.json","view_paper":"https://pith.science/paper/G57Q6GTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02407&json=true","fetch_graph":"https://pith.science/api/pith-number/G57Q6GTYMR7AF7NGSVS7FW5QMR/graph.json","fetch_events":"https://pith.science/api/pith-number/G57Q6GTYMR7AF7NGSVS7FW5QMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G57Q6GTYMR7AF7NGSVS7FW5QMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G57Q6GTYMR7AF7NGSVS7FW5QMR/action/storage_attestation","attest_author":"https://pith.science/pith/G57Q6GTYMR7AF7NGSVS7FW5QMR/action/author_attestation","sign_citation":"https://pith.science/pith/G57Q6GTYMR7AF7NGSVS7FW5QMR/action/citation_signature","submit_replication":"https://pith.science/pith/G57Q6GTYMR7AF7NGSVS7FW5QMR/action/replication_record"}},"created_at":"2026-08-04T02:12:09.556378+00:00","updated_at":"2026-08-04T02:12:09.556378+00:00"}