{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2C55FQDQVU2PCRMYFN2FHBZ2NC","short_pith_number":"pith:2C55FQDQ","schema_version":"1.0","canonical_sha256":"d0bbd2c070ad34f145982b7453873a68a927df1101abe8bf0166e5b43f535da4","source":{"kind":"arxiv","id":"2408.04430","version":3},"attestation_state":"computed","paper":{"title":"The Struggles of LLMs in Cross-lingual Code Clone Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Abdoul Kader Kabore, Jacques Klein, Micheline B\\'en\\'edicte Moumoula, Tegawend\\'e Bissyande","submitted_at":"2024-08-08T12:57:14Z","abstract_excerpt":"With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing various promising approaches. Inspired by the significant advances in machine learning in recent years, particularly Large Language Models (LLMs), which have demonstrated their ability to tackle various tasks, this paper revisits cross-lingual code clone detection. We evaluate the performance of five (05) LLMs and eight prompts (08) for the identification of c"},"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":"2408.04430","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-08-08T12:57:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4b94c25b53f4e07832f0db6eb1c8b20f0aa1289f82a831ea327f0bb1f84eaa0c","abstract_canon_sha256":"e80245bf05037a1a1ed74c8cc959b5f965e7ceecfe5117817848fa83a421c401"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:01.661113Z","signature_b64":"1j5WCAPDNeQ4mS/Q1U71jWNjFknIYQobsqtiN5CC25XqYW/AWrgSeaBc5s01qlqUwlRraZk/lRtmdNy2iMUBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0bbd2c070ad34f145982b7453873a68a927df1101abe8bf0166e5b43f535da4","last_reissued_at":"2026-07-05T10:59:01.660583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:01.660583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Struggles of LLMs in Cross-lingual Code Clone Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Abdoul Kader Kabore, Jacques Klein, Micheline B\\'en\\'edicte Moumoula, Tegawend\\'e Bissyande","submitted_at":"2024-08-08T12:57:14Z","abstract_excerpt":"With the involvement of multiple programming languages in modern software development, cross-lingual code clone detection has gained traction within the software engineering community. Numerous studies have explored this topic, proposing various promising approaches. Inspired by the significant advances in machine learning in recent years, particularly Large Language Models (LLMs), which have demonstrated their ability to tackle various tasks, this paper revisits cross-lingual code clone detection. We evaluate the performance of five (05) LLMs and eight prompts (08) for the identification of c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04430","kind":"arxiv","version":3},"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/2408.04430/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":"2408.04430","created_at":"2026-07-05T10:59:01.660646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04430v3","created_at":"2026-07-05T10:59:01.660646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04430","created_at":"2026-07-05T10:59:01.660646+00:00"},{"alias_kind":"pith_short_12","alias_value":"2C55FQDQVU2P","created_at":"2026-07-05T10:59:01.660646+00:00"},{"alias_kind":"pith_short_16","alias_value":"2C55FQDQVU2PCRMY","created_at":"2026-07-05T10:59:01.660646+00:00"},{"alias_kind":"pith_short_8","alias_value":"2C55FQDQ","created_at":"2026-07-05T10:59:01.660646+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02860","citing_title":"Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross--Language Code Clone Detection","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC","json":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC.json","graph_json":"https://pith.science/api/pith-number/2C55FQDQVU2PCRMYFN2FHBZ2NC/graph.json","events_json":"https://pith.science/api/pith-number/2C55FQDQVU2PCRMYFN2FHBZ2NC/events.json","paper":"https://pith.science/paper/2C55FQDQ"},"agent_actions":{"view_html":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC","download_json":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC.json","view_paper":"https://pith.science/paper/2C55FQDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04430&json=true","fetch_graph":"https://pith.science/api/pith-number/2C55FQDQVU2PCRMYFN2FHBZ2NC/graph.json","fetch_events":"https://pith.science/api/pith-number/2C55FQDQVU2PCRMYFN2FHBZ2NC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC/action/storage_attestation","attest_author":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC/action/author_attestation","sign_citation":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC/action/citation_signature","submit_replication":"https://pith.science/pith/2C55FQDQVU2PCRMYFN2FHBZ2NC/action/replication_record"}},"created_at":"2026-07-05T10:59:01.660646+00:00","updated_at":"2026-07-05T10:59:01.660646+00:00"}