{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EZBQV4RVTG6BID4DQJ2B437DBG","short_pith_number":"pith:EZBQV4RV","schema_version":"1.0","canonical_sha256":"26430af23599bc140f8382741e6fe309bf822ac081b4017c3d70599029dae54d","source":{"kind":"arxiv","id":"2411.04981","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Ana Nunez, Dylan Manuel, Elias Bou-Harb, Joseph Khoury, Nafis Tanveer Islam, Peyman Najafirad","submitted_at":"2024-11-07T18:54:31Z","abstract_excerpt":"Security experts reverse engineer (decompile) binary code to identify critical security vulnerabilities. The limited access to source code in vital systems - such as firmware, drivers, and proprietary software used in Critical Infrastructures (CI) - makes this analysis even more crucial on the binary level. Even with available source code, a semantic gap persists after compilation between the source and the binary code executed by the processor. This gap may hinder the detection of vulnerabilities in source code. That being said, current research on Large Language Models (LLMs) overlooks the s"},"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":"2411.04981","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-11-07T18:54:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2f04dbf8a14d8e8dd1f55ee793606a74f98f4d5c5e9a13b6598585a3ff4335d","abstract_canon_sha256":"e5ee13819f4706195bef6c59adb03cbe30421ee1087e6537c0c589fff485999b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:37.229305Z","signature_b64":"D4SAYIcDaI0BkcjFzAbnem1eS9620s+3mXxc5ko28qXt7B8Tvt9m2dGtlYcecVxNkncK0mWtvmDDol01IwTVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26430af23599bc140f8382741e6fe309bf822ac081b4017c3d70599029dae54d","last_reissued_at":"2026-07-05T09:32:37.228820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:37.228820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Ana Nunez, Dylan Manuel, Elias Bou-Harb, Joseph Khoury, Nafis Tanveer Islam, Peyman Najafirad","submitted_at":"2024-11-07T18:54:31Z","abstract_excerpt":"Security experts reverse engineer (decompile) binary code to identify critical security vulnerabilities. The limited access to source code in vital systems - such as firmware, drivers, and proprietary software used in Critical Infrastructures (CI) - makes this analysis even more crucial on the binary level. Even with available source code, a semantic gap persists after compilation between the source and the binary code executed by the processor. This gap may hinder the detection of vulnerabilities in source code. That being said, current research on Large Language Models (LLMs) overlooks the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04981","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/2411.04981/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":"2411.04981","created_at":"2026-07-05T09:32:37.228878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04981v1","created_at":"2026-07-05T09:32:37.228878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04981","created_at":"2026-07-05T09:32:37.228878+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZBQV4RVTG6B","created_at":"2026-07-05T09:32:37.228878+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZBQV4RVTG6BID4D","created_at":"2026-07-05T09:32:37.228878+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZBQV4RV","created_at":"2026-07-05T09:32:37.228878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06125","citing_title":"Evaluating Fine-Tuning and Metrics for Neural Decompilation of Dart AOT Binaries","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15390","citing_title":"Analyzing Chain of Thought (CoT) Approaches in Control Flow Code Deobfuscation Tasks","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG","json":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG.json","graph_json":"https://pith.science/api/pith-number/EZBQV4RVTG6BID4DQJ2B437DBG/graph.json","events_json":"https://pith.science/api/pith-number/EZBQV4RVTG6BID4DQJ2B437DBG/events.json","paper":"https://pith.science/paper/EZBQV4RV"},"agent_actions":{"view_html":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG","download_json":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG.json","view_paper":"https://pith.science/paper/EZBQV4RV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04981&json=true","fetch_graph":"https://pith.science/api/pith-number/EZBQV4RVTG6BID4DQJ2B437DBG/graph.json","fetch_events":"https://pith.science/api/pith-number/EZBQV4RVTG6BID4DQJ2B437DBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG/action/storage_attestation","attest_author":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG/action/author_attestation","sign_citation":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG/action/citation_signature","submit_replication":"https://pith.science/pith/EZBQV4RVTG6BID4DQJ2B437DBG/action/replication_record"}},"created_at":"2026-07-05T09:32:37.228878+00:00","updated_at":"2026-07-05T09:32:37.228878+00:00"}