{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2JZWUMUO4DVJCEIPRF5LMPI2FV","short_pith_number":"pith:2JZWUMUO","schema_version":"1.0","canonical_sha256":"d2736a328ee0ea91110f897ab63d1a2d524f4ea5d30209c3452c9f933f4a8998","source":{"kind":"arxiv","id":"2608.11469","version":1},"attestation_state":"computed","paper":{"title":"The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CR","authors_text":"Guannan Wei, Jeremy Spence, Jinhao Zhu, Nicholas Assaderaghi, Nikil Ravi, Raluca Ada Popa, Yangruibo Ding, Zhuo Zhang","submitted_at":"2026-08-11T22:14:57Z","abstract_excerpt":"AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequential to cybersecurity, including malware, firmware, and proprietary applications, is available only as binaries. Analyzing such software requires reverse engineering(RE): recovering program semantics before the analysis can be meaningfully performed. However, evaluating agentic RE poses a fundamental challenge: benchmark instances must be unseen as source code in the LLMs' training data to prevent models from taking shortcuts by recognizing them r"},"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":"2608.11469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-11T22:14:57Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"7fecd4ca67024e8f2c72ef9ef0a5bba8e2a8426eca69b24ebf7f1fe139fdc7a6","abstract_canon_sha256":"e5f5f600846831f68d4123897836c5ac8519e1e940721ce3a2e68d84656f0e95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:21:58.871247Z","signature_b64":"008BcULiA6KvNki6dOwNuWU0ycjw5jL++gSCR+gSQWdqZSRcwFKpJlgBEGu4I5n3KimpE8Dss2E1GT+7+acqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2736a328ee0ea91110f897ab63d1a2d524f4ea5d30209c3452c9f933f4a8998","last_reissued_at":"2026-08-13T00:21:58.869775Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:21:58.869775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CR","authors_text":"Guannan Wei, Jeremy Spence, Jinhao Zhu, Nicholas Assaderaghi, Nikil Ravi, Raluca Ada Popa, Yangruibo Ding, Zhuo Zhang","submitted_at":"2026-08-11T22:14:57Z","abstract_excerpt":"AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequential to cybersecurity, including malware, firmware, and proprietary applications, is available only as binaries. Analyzing such software requires reverse engineering(RE): recovering program semantics before the analysis can be meaningfully performed. However, evaluating agentic RE poses a fundamental challenge: benchmark instances must be unseen as source code in the LLMs' training data to prevent models from taking shortcuts by recognizing them r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11469","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/2608.11469/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":"2608.11469","created_at":"2026-08-13T00:21:58.870057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11469v1","created_at":"2026-08-13T00:21:58.870057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11469","created_at":"2026-08-13T00:21:58.870057+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JZWUMUO4DVJ","created_at":"2026-08-13T00:21:58.870057+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JZWUMUO4DVJCEIP","created_at":"2026-08-13T00:21:58.870057+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JZWUMUO","created_at":"2026-08-13T00:21:58.870057+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/2JZWUMUO4DVJCEIPRF5LMPI2FV","json":"https://pith.science/pith/2JZWUMUO4DVJCEIPRF5LMPI2FV.json","graph_json":"https://pith.science/api/pith-number/2JZWUMUO4DVJCEIPRF5LMPI2FV/graph.json","events_json":"https://pith.science/api/pith-number/2JZWUMUO4DVJCEIPRF5LMPI2FV/events.json","paper":"https://pith.science/paper/2JZWUMUO"},"agent_actions":{"view_html":"https://pith.science/pith/2JZWUMUO4DVJCEIPRF5LMPI2FV","download_json":"https://pith.science/pith/2JZWUMUO4DVJCEIPRF5LMPI2FV.json","view_paper":"https://pith.science/paper/2JZWUMUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11469&json=true","fetch_graph":"https://pith.science/api/pith-number/2JZWUMUO4DVJCEIPRF5LMPI2FV/graph.json","fetch_events":"https://pith.science/api/pith-number/2JZWUMUO4DVJCEIPRF5LMPI2FV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JZWUMUO4DVJCEIPRF5LMPI2FV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JZWUMUO4DVJCEIPRF5LMPI2FV/action/storage_attestation","attest_author":"https://pith.science/pith/2JZWUMUO4DVJCEIPRF5LMPI2FV/action/author_attestation","sign_citation":"https://pith.science/pith/2JZWUMUO4DVJCEIPRF5LMPI2FV/action/citation_signature","submit_replication":"https://pith.science/pith/2JZWUMUO4DVJCEIPRF5LMPI2FV/action/replication_record"}},"created_at":"2026-08-13T00:21:58.870057+00:00","updated_at":"2026-08-13T00:21:58.870057+00:00"}