{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VXFK5U5R4DLYVTHKD5T6PYNB3C","short_pith_number":"pith:VXFK5U5R","schema_version":"1.0","canonical_sha256":"adcaaed3b1e0d78accea1f67e7e1a1d8844922026d73a955f263ecaac7baa7ff","source":{"kind":"arxiv","id":"2405.00428","version":1},"attestation_state":"computed","paper":{"title":"CC2Vec: Combining Typed Tokens with Contrastive Learning for Effective Code Clone Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Haoxiang Jia, Shihan Dou, Yang Liu, Yan Liu, Yueming Wu, Yuhao Zhou","submitted_at":"2024-05-01T10:18:31Z","abstract_excerpt":"With the development of the open source community, the code is often copied, spread, and evolved in multiple software systems, which brings uncertainty and risk to the software system (e.g., bug propagation and copyright infringement). Therefore, it is important to conduct code clone detection to discover similar code pairs. Many approaches have been proposed to detect code clones where token-based tools can scale to big code. However, due to the lack of program details, they cannot handle more complicated code clones, i.e., semantic code clones. In this paper, we introduce CC2Vec, a novel cod"},"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":"2405.00428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-05-01T10:18:31Z","cross_cats_sorted":[],"title_canon_sha256":"81da3fb847f9df7ae5f490d1011a9dc835e2720e228e5ca371699b9db8fa7e6e","abstract_canon_sha256":"6caf6e7ed5c48f4c0899bb660e6bbaf925f4b32b0c7ee548d94708c5d687a18a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:12.739192Z","signature_b64":"W9/vQ3wRpmHARAa6u7f9RVGOrbwXchRRVnN+ZdfKl6U1RQ5d9kMS3agxj9k6m9FWViyENIE85om3Xx+CES35Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adcaaed3b1e0d78accea1f67e7e1a1d8844922026d73a955f263ecaac7baa7ff","last_reissued_at":"2026-07-05T08:14:12.738747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:12.738747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CC2Vec: Combining Typed Tokens with Contrastive Learning for Effective Code Clone Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Haoxiang Jia, Shihan Dou, Yang Liu, Yan Liu, Yueming Wu, Yuhao Zhou","submitted_at":"2024-05-01T10:18:31Z","abstract_excerpt":"With the development of the open source community, the code is often copied, spread, and evolved in multiple software systems, which brings uncertainty and risk to the software system (e.g., bug propagation and copyright infringement). Therefore, it is important to conduct code clone detection to discover similar code pairs. Many approaches have been proposed to detect code clones where token-based tools can scale to big code. However, due to the lack of program details, they cannot handle more complicated code clones, i.e., semantic code clones. In this paper, we introduce CC2Vec, a novel cod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00428","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/2405.00428/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":"2405.00428","created_at":"2026-07-05T08:14:12.738799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00428v1","created_at":"2026-07-05T08:14:12.738799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00428","created_at":"2026-07-05T08:14:12.738799+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXFK5U5R4DLY","created_at":"2026-07-05T08:14:12.738799+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXFK5U5R4DLYVTHK","created_at":"2026-07-05T08:14:12.738799+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXFK5U5R","created_at":"2026-07-05T08:14:12.738799+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/VXFK5U5R4DLYVTHKD5T6PYNB3C","json":"https://pith.science/pith/VXFK5U5R4DLYVTHKD5T6PYNB3C.json","graph_json":"https://pith.science/api/pith-number/VXFK5U5R4DLYVTHKD5T6PYNB3C/graph.json","events_json":"https://pith.science/api/pith-number/VXFK5U5R4DLYVTHKD5T6PYNB3C/events.json","paper":"https://pith.science/paper/VXFK5U5R"},"agent_actions":{"view_html":"https://pith.science/pith/VXFK5U5R4DLYVTHKD5T6PYNB3C","download_json":"https://pith.science/pith/VXFK5U5R4DLYVTHKD5T6PYNB3C.json","view_paper":"https://pith.science/paper/VXFK5U5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00428&json=true","fetch_graph":"https://pith.science/api/pith-number/VXFK5U5R4DLYVTHKD5T6PYNB3C/graph.json","fetch_events":"https://pith.science/api/pith-number/VXFK5U5R4DLYVTHKD5T6PYNB3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXFK5U5R4DLYVTHKD5T6PYNB3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXFK5U5R4DLYVTHKD5T6PYNB3C/action/storage_attestation","attest_author":"https://pith.science/pith/VXFK5U5R4DLYVTHKD5T6PYNB3C/action/author_attestation","sign_citation":"https://pith.science/pith/VXFK5U5R4DLYVTHKD5T6PYNB3C/action/citation_signature","submit_replication":"https://pith.science/pith/VXFK5U5R4DLYVTHKD5T6PYNB3C/action/replication_record"}},"created_at":"2026-07-05T08:14:12.738799+00:00","updated_at":"2026-07-05T08:14:12.738799+00:00"}