{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QDEQBASN3CLQT4BRKNK5AJZADK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7206cb59c333ac9fe0adb7131cee5bd1d9dc5b3e01ad84c15a3916d29310012a","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-28T10:31:58Z","title_canon_sha256":"6e354fc31bb312ef46e314d1d4aa6ca8977c945c03b4ac7d9fa25268e5f0c598"},"schema_version":"1.0","source":{"id":"2603.27224","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.27224","created_at":"2026-06-02T02:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2603.27224v4","created_at":"2026-06-02T02:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27224","created_at":"2026-06-02T02:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"QDEQBASN3CLQ","created_at":"2026-06-02T02:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"QDEQBASN3CLQT4BR","created_at":"2026-06-02T02:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"QDEQBASN","created_at":"2026-06-02T02:04:16Z"}],"graph_snapshots":[{"event_id":"sha256:fde22e3e3f32c6a1204782f47d4610f628fcc8f5072e2eaec5ecc4f8fbefb8ab","target":"graph","created_at":"2026-06-02T02:04:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"On seven real-world C/C++ projects totaling over 3.4M lines of code, MemHint detects 52 unique memory leaks (49 confirmed/fixed, 4 CVEs submitted) at approximately $1.7 per detected bug, compared to 19 by vanilla CodeQL and 3 by vanilla Infer."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The LLM produces accurate classifications of custom memory functions and ownership semantics, and Z3 correctly identifies feasible versus infeasible paths without missing real leaks or introducing excessive false negatives."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MemHint combines LLM classification of custom memory functions with Z3 path validation to augment CodeQL and Infer, detecting 52 memory leaks (49 confirmed) across 3.4M LOC versus 19 and 3 by vanilla tools."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MemHint augments static analyzers with LLMs and Z3 to detect 52 memory leaks in 3.4 million lines of C/C++ code."}],"snapshot_sha256":"7eaf3af722be0d46e0951cfc04b05c97e072b80eae6dc997ed31262f2935fac6"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.27224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Memory leaks remain prevalent in real-world C/C++ software. Static analyzers such as CodeQL provide scalable program analysis but frequently miss such bugs because they cannot recognize project-specific custom memory-management functions and lack path-sensitive control-flow modeling. We present MemHint, a neuro-symbolic pipeline that addresses both limitations by combining LLMs' semantic understanding of code with Z3-based symbolic reasoning. MemHint parses the target codebase and applies an LLM to classify each function as a memory allocator, deallocator, or neither, producing function summar","authors_text":"Bo Wang, David Lo, Huihui Huang, Jieke Shi, Zhou Yang","cross_cats":["cs.CR"],"headline":"MemHint augments static analyzers with LLMs and Z3 to detect 52 memory leaks in 3.4 million lines of C/C++ code.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-28T10:31:58Z","title":"Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.27224","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-14T22:30:44.761213Z","id":"ffb8e92b-abbd-4bb6-b0ee-ac8a3e6f8473","model_set":{"reader":"grok-4.3"},"one_line_summary":"MemHint combines LLM classification of custom memory functions with Z3 path validation to augment CodeQL and Infer, detecting 52 memory leaks (49 confirmed) across 3.4M LOC versus 19 and 3 by vanilla tools.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MemHint augments static analyzers with LLMs and Z3 to detect 52 memory leaks in 3.4 million lines of C/C++ code.","strongest_claim":"On seven real-world C/C++ projects totaling over 3.4M lines of code, MemHint detects 52 unique memory leaks (49 confirmed/fixed, 4 CVEs submitted) at approximately $1.7 per detected bug, compared to 19 by vanilla CodeQL and 3 by vanilla Infer.","weakest_assumption":"The LLM produces accurate classifications of custom memory functions and ownership semantics, and Z3 correctly identifies feasible versus infeasible paths without missing real leaks or introducing excessive false negatives."}},"verdict_id":"ffb8e92b-abbd-4bb6-b0ee-ac8a3e6f8473"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:59436b0ac7f1d9bca1c93200d73461adc5ccf1faa595864184cc4865f6837101","target":"record","created_at":"2026-06-02T02:04:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7206cb59c333ac9fe0adb7131cee5bd1d9dc5b3e01ad84c15a3916d29310012a","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-28T10:31:58Z","title_canon_sha256":"6e354fc31bb312ef46e314d1d4aa6ca8977c945c03b4ac7d9fa25268e5f0c598"},"schema_version":"1.0","source":{"id":"2603.27224","kind":"arxiv","version":4}},"canonical_sha256":"80c900824dd89709f0315355d027201ab19e80e503c97f7001bda5929611ea53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80c900824dd89709f0315355d027201ab19e80e503c97f7001bda5929611ea53","first_computed_at":"2026-06-02T02:04:16.760094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:16.760094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RqhT9Qpc9AJdoSNNrOEguxWXwiuGS1mtV9IS3D2kBGZGKjxqT9rH+cbExUNcIh4tKKue/gf2HHw4KFVlch7MCw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:16.760617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.27224","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59436b0ac7f1d9bca1c93200d73461adc5ccf1faa595864184cc4865f6837101","sha256:fde22e3e3f32c6a1204782f47d4610f628fcc8f5072e2eaec5ecc4f8fbefb8ab"],"state_sha256":"3eccbad0d22faeff8defe2f44a0c3e2c63f0dfcaa8714d7bd805a126f2118e02"}