{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MGQASGIIMSW5GPKBWEQAWSPSYB","short_pith_number":"pith:MGQASGII","schema_version":"1.0","canonical_sha256":"61a009190864add33d41b1200b49f2c0525f39ea1ebd66a8036297aa9766ecc9","source":{"kind":"arxiv","id":"2606.25272","version":1},"attestation_state":"computed","paper":{"title":"Semantic Code Clone Detection: Are We There Yet?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hai Wan, Jiabao Gao, Tian Qiu, Weixian Deng, Xiaolin Peng, Xibin Zhao, Xuyang Liu, Zhiwei Xu","submitted_at":"2026-06-24T01:11:40Z","abstract_excerpt":"Code clone detection has been extensively studied for decades, and recent approaches have begun reporting remarkably high performance for semantic (Type-4) clones on benchmark datasets. However, it remains unclear whether these results reflect a genuine ability to capture semantic equivalence between programs, or simply an ability to exploit dataset-specific patterns.\n  In this paper, we present the first systematic empirical study investigating the generalizability of state-of-the-art (SOTA) semantic code clone detectors beyond benchmark evaluation settings. Inspired by the inherent inclusion"},"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":"2606.25272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-24T01:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"790db933c4f75f4ef48ddb7606a9cedc25e2bd60cdc67f717d66c7df5823693e","abstract_canon_sha256":"f9a40a09ef9cfdaef29d3315e456c0afc04ca0f7030b2b812612a1b2fe5435b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:22.700517Z","signature_b64":"at5DsBYdgP70+NNja9Pc7zVCn2QhCTl0DL17ekw4w60KV/3VfQRB724oIN8Ev22RLc6+5IPTq7IX2ueRgqp3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61a009190864add33d41b1200b49f2c0525f39ea1ebd66a8036297aa9766ecc9","last_reissued_at":"2026-06-25T00:18:22.700116Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:22.700116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Code Clone Detection: Are We There Yet?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Hai Wan, Jiabao Gao, Tian Qiu, Weixian Deng, Xiaolin Peng, Xibin Zhao, Xuyang Liu, Zhiwei Xu","submitted_at":"2026-06-24T01:11:40Z","abstract_excerpt":"Code clone detection has been extensively studied for decades, and recent approaches have begun reporting remarkably high performance for semantic (Type-4) clones on benchmark datasets. However, it remains unclear whether these results reflect a genuine ability to capture semantic equivalence between programs, or simply an ability to exploit dataset-specific patterns.\n  In this paper, we present the first systematic empirical study investigating the generalizability of state-of-the-art (SOTA) semantic code clone detectors beyond benchmark evaluation settings. Inspired by the inherent inclusion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25272","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/2606.25272/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":"2606.25272","created_at":"2026-06-25T00:18:22.700172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25272v1","created_at":"2026-06-25T00:18:22.700172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25272","created_at":"2026-06-25T00:18:22.700172+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGQASGIIMSW5","created_at":"2026-06-25T00:18:22.700172+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGQASGIIMSW5GPKB","created_at":"2026-06-25T00:18:22.700172+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGQASGII","created_at":"2026-06-25T00:18:22.700172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB","json":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB.json","graph_json":"https://pith.science/api/pith-number/MGQASGIIMSW5GPKBWEQAWSPSYB/graph.json","events_json":"https://pith.science/api/pith-number/MGQASGIIMSW5GPKBWEQAWSPSYB/events.json","paper":"https://pith.science/paper/MGQASGII"},"agent_actions":{"view_html":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB","download_json":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB.json","view_paper":"https://pith.science/paper/MGQASGII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25272&json=true","fetch_graph":"https://pith.science/api/pith-number/MGQASGIIMSW5GPKBWEQAWSPSYB/graph.json","fetch_events":"https://pith.science/api/pith-number/MGQASGIIMSW5GPKBWEQAWSPSYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB/action/storage_attestation","attest_author":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB/action/author_attestation","sign_citation":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB/action/citation_signature","submit_replication":"https://pith.science/pith/MGQASGIIMSW5GPKBWEQAWSPSYB/action/replication_record"}},"created_at":"2026-06-25T00:18:22.700172+00:00","updated_at":"2026-06-25T00:18:22.700172+00:00"}