{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XID6Z2NG6QL33CP5CHKEHRGDC7","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":"204ff1f822c31cb1eb602a14020aa05c2c5dfd187d6255339060daf412f03453","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-29T11:59:53Z","title_canon_sha256":"725924dfe6c3bca06e12b9cb5a8658b63be033314db1ab4580234fd891c9833f"},"schema_version":"1.0","source":{"id":"2604.26578","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.26578","created_at":"2026-05-20T00:01:42Z"},{"alias_kind":"arxiv_version","alias_value":"2604.26578v2","created_at":"2026-05-20T00:01:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.26578","created_at":"2026-05-20T00:01:42Z"},{"alias_kind":"pith_short_12","alias_value":"XID6Z2NG6QL3","created_at":"2026-05-20T00:01:42Z"},{"alias_kind":"pith_short_16","alias_value":"XID6Z2NG6QL33CP5","created_at":"2026-05-20T00:01:42Z"},{"alias_kind":"pith_short_8","alias_value":"XID6Z2NG","created_at":"2026-05-20T00:01:42Z"}],"graph_snapshots":[{"event_id":"sha256:ba1d893cc9f6dfa2ac8d5e1b5e0cfe44a85b8fbe0ca99224848c173213e73ba7","target":"graph","created_at":"2026-05-20T00:01:42Z","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":"Our results show that consistent graph representations can be constructed across different languages and annotation styles. This work provides a practical basis for future steps in semantic enrichment and approximate graph matching for scalable verification artefact reuse."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That combining AST parsing with semantic embeddings from SentenceTransformer and CodeBERT produces graph representations that capture both structural relationships and semantic context sufficiently well to enable future approximate graph matching for verification reuse."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A pipeline converts programs with annotations into typed attributed graphs using AST parsing and neural embeddings to support verification artefact reuse across languages."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A pipeline builds consistent typed and attributed graphs from imperative programs across C, Java, and Dafny by combining abstract syntax tree parsing with neural embeddings."}],"snapshot_sha256":"e298ce2e60772be3f39e9fc949ba936b53be36d7a828aa34a291b93f587cc29f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T20:02:18.715015Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.26578/integrity.json","findings":[],"snapshot_sha256":"9046142fc165d7e42b96c9cdfa0d448f0e6ca8212db409447e347d89c0dd4340","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reusing verification artefacts requires identifying structural and semantic similarities across programs and their specifications. In this paper, we focus on graph construction as a foundational step toward this goal. We present a pipeline that converts imperative programs and their annotations into typed, attributed graphs. Our experiments cover datasets including C with ACSL, Java with JML, and Dafny for C\\#. The pipeline integrates abstract syntax tree parsing with semantic embeddings derived from models such as SentenceTransformer and CodeBERT. This enables the generation of graph represen","authors_text":"Arshad Beg, Diarmuid O'Donoghue, Rosemary Monahan","cross_cats":["cs.AI"],"headline":"A pipeline builds consistent typed and attributed graphs from imperative programs across C, Java, and Dafny by combining abstract syntax tree parsing with neural embeddings.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-29T11:59:53Z","title":"Graph Construction and Matching for Imperative Programs using Neural and Structural Methods"},"references":{"count":15,"internal_anchors":1,"resolved_work":15,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"In: International Conference on Computational Creativity (ICCC)","work_id":"da3b06e3-fe81-4793-8967-0bbe24531f79","year":2021},{"cited_arxiv_id":"","doi":"10.1007/978-3-031-75872-0_16","is_internal_anchor":false,"ref_index":2,"title":"Ali SJ, Naganathan V, Bork D (2024) Establishing traceability between natural language requirements and software artifacts by combining RAG and llms. In: Maass W, Han H, Yasar H, Multari NJ (eds) Conc","work_id":"9e2fdac2-7a3f-455f-af1f-81da217c489e","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Beg A, O’Donoghue D, Monahan R (2026) Learning-infused formal reason- ing: From contract synthesis to artifact reuse and formal semantics. URL https://arxiv.org/abs/2602.02881, vERIF AI-2026: The Inte","work_id":"ade690e8-48e8-472d-b21d-a153696ed5a5","year":2026},{"cited_arxiv_id":"2604.12747","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Short Version of VERIFAI2026 Paper -- Learning Infused Formal Reasoning: Contract Synthesis, Artefact Reuse and Semantic Foundations","work_id":"b21f9688-0e7f-4425-8ff8-e3e1ee1495ad","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"In: Kosmatov N, Graph Construction and Matching for Imperative Programs 19 Kovács L (eds) Integrated Formal Methods, Springer Nature Switzerland, Cham, pp 307–325","work_id":"785e30a6-cdd5-4baf-a61c-b0304641885f","year":2025}],"snapshot_sha256":"df51cf27cc1312562ecdbac26168e69aeac5bea503be6f418a0e88d4fc5f7126"},"source":{"id":"2604.26578","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-19T17:31:52.861662Z","id":"9942b0a0-5036-4c95-84a6-7db43e172027","model_set":{"reader":"grok-4.3"},"one_line_summary":"A pipeline converts programs with annotations into typed attributed graphs using AST parsing and neural embeddings to support verification artefact reuse across languages.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A pipeline builds consistent typed and attributed graphs from imperative programs across C, Java, and Dafny by combining abstract syntax tree parsing with neural embeddings.","strongest_claim":"Our results show that consistent graph representations can be constructed across different languages and annotation styles. This work provides a practical basis for future steps in semantic enrichment and approximate graph matching for scalable verification artefact reuse.","weakest_assumption":"That combining AST parsing with semantic embeddings from SentenceTransformer and CodeBERT produces graph representations that capture both structural relationships and semantic context sufficiently well to enable future approximate graph matching for verification reuse."}},"verdict_id":"9942b0a0-5036-4c95-84a6-7db43e172027"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:68715a8bbb2bdf29d1d0971fc6ba1b4efe37f46b92df8f0ea93f81bc43b9253c","target":"record","created_at":"2026-05-20T00:01:42Z","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":"204ff1f822c31cb1eb602a14020aa05c2c5dfd187d6255339060daf412f03453","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-29T11:59:53Z","title_canon_sha256":"725924dfe6c3bca06e12b9cb5a8658b63be033314db1ab4580234fd891c9833f"},"schema_version":"1.0","source":{"id":"2604.26578","kind":"arxiv","version":2}},"canonical_sha256":"ba07ece9a6f417bd89fd11d443c4c317edbc0ba348574893bbb412bb37f5aef3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba07ece9a6f417bd89fd11d443c4c317edbc0ba348574893bbb412bb37f5aef3","first_computed_at":"2026-05-20T00:01:42.159417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:42.159417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7B+hdjZNX9DaqFcq1WV6bsJbJ5h5+bMa/CWvZThHPGWX4cDiyaCDgraUYMOMF93hyL+uYeZsd4fB0Fg7BkV1BQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:42.160141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.26578","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68715a8bbb2bdf29d1d0971fc6ba1b4efe37f46b92df8f0ea93f81bc43b9253c","sha256:ba1d893cc9f6dfa2ac8d5e1b5e0cfe44a85b8fbe0ca99224848c173213e73ba7"],"state_sha256":"8272dcdd19f65bd5741268615304dd6d79e4887a1401243a2bd5b569fcf86ec0"}