{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IJANPCTCSS7GAVMWTIB6TA4ACG","short_pith_number":"pith:IJANPCTC","schema_version":"1.0","canonical_sha256":"4240d78a6294be6055969a03e9838011a4e94de7722417d33d2ec0c0f16709d8","source":{"kind":"arxiv","id":"2505.07360","version":1},"attestation_state":"computed","paper":{"title":"BinMetric: A Comprehensive Binary Analysis Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Benlong Wu, Gangyang Li, Guoqiang Chen, Li Hu, Nenghai Yu, Shaoyin Cheng, Weiming Zhang, Xiuwei Shang","submitted_at":"2025-05-12T08:54:07Z","abstract_excerpt":"Binary analysis remains pivotal in software security, offering insights into compiled programs without source code access. As large language models (LLMs) continue to excel in diverse language understanding and generation tasks, their potential in decoding complex binary data structures becomes evident. However, the lack of standardized benchmarks in this domain limits the assessment and comparison of LLM's capabilities in binary analysis and hinders the progress of research and practical applications. To bridge this gap, we introduce BinMetric, a comprehensive benchmark designed specifically "},"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":"2505.07360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-12T08:54:07Z","cross_cats_sorted":[],"title_canon_sha256":"cac54127d483fc0d09be2cc3d16adda5cb5e3f67e65f50a3d223ab8bb023f82a","abstract_canon_sha256":"535d20c6d6102ca6779b1f1d087bdaccdeed36c410f8d747d1d0c02b6ce8a5ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:46.686618Z","signature_b64":"aqT+7X1WHV/8yWxlMSv3Ymjq2xFnmSvHZBdENzY70w34bsSgd/WZUcZuR94Tmq6ytcPlz2HYvwz8XLMTwpKBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4240d78a6294be6055969a03e9838011a4e94de7722417d33d2ec0c0f16709d8","last_reissued_at":"2026-07-05T11:01:46.686107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:46.686107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BinMetric: A Comprehensive Binary Analysis Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Benlong Wu, Gangyang Li, Guoqiang Chen, Li Hu, Nenghai Yu, Shaoyin Cheng, Weiming Zhang, Xiuwei Shang","submitted_at":"2025-05-12T08:54:07Z","abstract_excerpt":"Binary analysis remains pivotal in software security, offering insights into compiled programs without source code access. As large language models (LLMs) continue to excel in diverse language understanding and generation tasks, their potential in decoding complex binary data structures becomes evident. However, the lack of standardized benchmarks in this domain limits the assessment and comparison of LLM's capabilities in binary analysis and hinders the progress of research and practical applications. To bridge this gap, we introduce BinMetric, a comprehensive benchmark designed specifically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07360","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/2505.07360/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":"2505.07360","created_at":"2026-07-05T11:01:46.686168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07360v1","created_at":"2026-07-05T11:01:46.686168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07360","created_at":"2026-07-05T11:01:46.686168+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJANPCTCSS7G","created_at":"2026-07-05T11:01:46.686168+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJANPCTCSS7GAVMW","created_at":"2026-07-05T11:01:46.686168+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJANPCTC","created_at":"2026-07-05T11:01:46.686168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.01763","citing_title":"Context-Guided Decompilation: A Step Towards Re-executability","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15097","citing_title":"Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08083","citing_title":"Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14317","citing_title":"Challenges and Future Directions in Agentic Reverse Engineering Systems","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG","json":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG.json","graph_json":"https://pith.science/api/pith-number/IJANPCTCSS7GAVMWTIB6TA4ACG/graph.json","events_json":"https://pith.science/api/pith-number/IJANPCTCSS7GAVMWTIB6TA4ACG/events.json","paper":"https://pith.science/paper/IJANPCTC"},"agent_actions":{"view_html":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG","download_json":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG.json","view_paper":"https://pith.science/paper/IJANPCTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07360&json=true","fetch_graph":"https://pith.science/api/pith-number/IJANPCTCSS7GAVMWTIB6TA4ACG/graph.json","fetch_events":"https://pith.science/api/pith-number/IJANPCTCSS7GAVMWTIB6TA4ACG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG/action/storage_attestation","attest_author":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG/action/author_attestation","sign_citation":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG/action/citation_signature","submit_replication":"https://pith.science/pith/IJANPCTCSS7GAVMWTIB6TA4ACG/action/replication_record"}},"created_at":"2026-07-05T11:01:46.686168+00:00","updated_at":"2026-07-05T11:01:46.686168+00:00"}