{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ESCK4ZUGXZHOYSJFHKFYKB2VD","short_pith_number":"pith:2ESCK4ZU","schema_version":"1.0","canonical_sha256":"d12425733435f277624929d45c283aa8f38e54ff2794bf87ac4ca596020c8b99","source":{"kind":"arxiv","id":"2506.14470","version":1},"attestation_state":"computed","paper":{"title":"AST-Enhanced or AST-Overloaded? The Surprising Impact of Hybrid Graph Representations on Code Clone Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Takfarinas Saber, Zixian Zhang","submitted_at":"2025-06-17T12:35:17Z","abstract_excerpt":"As one of the most detrimental code smells, code clones significantly increase software maintenance costs and heighten vulnerability risks, making their detection a critical challenge in software engineering. Abstract Syntax Trees (ASTs) dominate deep learning-based code clone detection due to their precise syntactic structure representation, but they inherently lack semantic depth. Recent studies address this by enriching AST-based representations with semantic graphs, such as Control Flow Graphs (CFGs) and Data Flow Graphs (DFGs). However, the effectiveness of various enriched AST-based repr"},"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":"2506.14470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-17T12:35:17Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"ff4a688c61794423a3cb28b20bebf461fcd47ebfe7d9876ee14221b4c30c2f19","abstract_canon_sha256":"9b4167fe23066910178edc5b98ff43072e0bd8a5ec7db6a7ca19741de8b73437"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:57.165654Z","signature_b64":"6xb+UMizV8ZjO5mBDQiwsP8MXKvb2656atzUi5zQzB8GYA7zaMCJvLsbFQEVKyO5Gs6UvMw82r2ebtpSuwvOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d12425733435f277624929d45c283aa8f38e54ff2794bf87ac4ca596020c8b99","last_reissued_at":"2026-07-05T11:22:57.165149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:57.165149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AST-Enhanced or AST-Overloaded? The Surprising Impact of Hybrid Graph Representations on Code Clone Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Takfarinas Saber, Zixian Zhang","submitted_at":"2025-06-17T12:35:17Z","abstract_excerpt":"As one of the most detrimental code smells, code clones significantly increase software maintenance costs and heighten vulnerability risks, making their detection a critical challenge in software engineering. Abstract Syntax Trees (ASTs) dominate deep learning-based code clone detection due to their precise syntactic structure representation, but they inherently lack semantic depth. Recent studies address this by enriching AST-based representations with semantic graphs, such as Control Flow Graphs (CFGs) and Data Flow Graphs (DFGs). However, the effectiveness of various enriched AST-based repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14470","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/2506.14470/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":"2506.14470","created_at":"2026-07-05T11:22:57.165207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14470v1","created_at":"2026-07-05T11:22:57.165207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14470","created_at":"2026-07-05T11:22:57.165207+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ESCK4ZUGXZH","created_at":"2026-07-05T11:22:57.165207+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ESCK4ZUGXZHOYSJ","created_at":"2026-07-05T11:22:57.165207+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ESCK4ZU","created_at":"2026-07-05T11:22:57.165207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07788","citing_title":"Bridging the Programming Language Gap: Constructing a Multilingual Shared Semantic Space through AST Unification and Graph Matching","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD","json":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD.json","graph_json":"https://pith.science/api/pith-number/2ESCK4ZUGXZHOYSJFHKFYKB2VD/graph.json","events_json":"https://pith.science/api/pith-number/2ESCK4ZUGXZHOYSJFHKFYKB2VD/events.json","paper":"https://pith.science/paper/2ESCK4ZU"},"agent_actions":{"view_html":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD","download_json":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD.json","view_paper":"https://pith.science/paper/2ESCK4ZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14470&json=true","fetch_graph":"https://pith.science/api/pith-number/2ESCK4ZUGXZHOYSJFHKFYKB2VD/graph.json","fetch_events":"https://pith.science/api/pith-number/2ESCK4ZUGXZHOYSJFHKFYKB2VD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD/action/storage_attestation","attest_author":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD/action/author_attestation","sign_citation":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD/action/citation_signature","submit_replication":"https://pith.science/pith/2ESCK4ZUGXZHOYSJFHKFYKB2VD/action/replication_record"}},"created_at":"2026-07-05T11:22:57.165207+00:00","updated_at":"2026-07-05T11:22:57.165207+00:00"}