{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KE66CYMPQ2RBKX7VG6PWT62AS5","short_pith_number":"pith:KE66CYMP","schema_version":"1.0","canonical_sha256":"513de1618f86a2155ff5379f69fb40975bd0e3da8800658367e069dce1255eef","source":{"kind":"arxiv","id":"2402.07518","version":4},"attestation_state":"computed","paper":{"title":"Efficient and Universal Watermarking for LLM-Generated Code Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Boquan Li, Jun Sun, Mengdi Zhang, Peixin Zhang, Xingmei Wang, Zirui Fu","submitted_at":"2024-02-12T09:40:18Z","abstract_excerpt":"Large language models (LLMs) have significantly enhanced the usability of AI-generated code, providing effective assistance to programmers. This advancement also raises ethical and legal concerns, such as academic dishonesty or the generation of malicious code. For accountability, it is imperative to detect whether a piece of code is AI-generated. Watermarking is broadly considered a promising solution and has been successfully applied to identify LLM-generated text. However, existing efforts on code are far from ideal, suffering from limited universality and excessive time and memory consumpt"},"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":"2402.07518","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-12T09:40:18Z","cross_cats_sorted":[],"title_canon_sha256":"ddb2c7fc53a5bc7562320be001c053d08a94e480606a471ed87083fc0adeee4b","abstract_canon_sha256":"c9c37271d70620cbbada4e8b2095d64c6819fdefa86848183ce018b4db7c04ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:34.094230Z","signature_b64":"NKuN4MrIAH6j2IFEOX7hlZ7gzUbZbONf40kLqEmbQCEVh08yecz3qgT78uzjtNPMkSXC+NJajyY51mUaqlZ2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"513de1618f86a2155ff5379f69fb40975bd0e3da8800658367e069dce1255eef","last_reissued_at":"2026-07-05T11:46:34.093022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:34.093022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Universal Watermarking for LLM-Generated Code Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Boquan Li, Jun Sun, Mengdi Zhang, Peixin Zhang, Xingmei Wang, Zirui Fu","submitted_at":"2024-02-12T09:40:18Z","abstract_excerpt":"Large language models (LLMs) have significantly enhanced the usability of AI-generated code, providing effective assistance to programmers. This advancement also raises ethical and legal concerns, such as academic dishonesty or the generation of malicious code. For accountability, it is imperative to detect whether a piece of code is AI-generated. Watermarking is broadly considered a promising solution and has been successfully applied to identify LLM-generated text. However, existing efforts on code are far from ideal, suffering from limited universality and excessive time and memory consumpt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07518","kind":"arxiv","version":4},"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/2402.07518/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":"2402.07518","created_at":"2026-07-05T11:46:34.093703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07518v4","created_at":"2026-07-05T11:46:34.093703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07518","created_at":"2026-07-05T11:46:34.093703+00:00"},{"alias_kind":"pith_short_12","alias_value":"KE66CYMPQ2RB","created_at":"2026-07-05T11:46:34.093703+00:00"},{"alias_kind":"pith_short_16","alias_value":"KE66CYMPQ2RBKX7V","created_at":"2026-07-05T11:46:34.093703+00:00"},{"alias_kind":"pith_short_8","alias_value":"KE66CYMP","created_at":"2026-07-05T11:46:34.093703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.20835","citing_title":"PromptMark: A Prompt-Guided Iterative-Feedback Framework for Source Code Watermarking","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2601.02602","citing_title":"SWaRL: Safeguard Code Watermarking via Reinforcement Learning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10611","citing_title":"DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16001","citing_title":"MATRIX: Multi-Layer Code Watermarking via Dual-Channel Constrained Parity-Check Encoding","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5","json":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5.json","graph_json":"https://pith.science/api/pith-number/KE66CYMPQ2RBKX7VG6PWT62AS5/graph.json","events_json":"https://pith.science/api/pith-number/KE66CYMPQ2RBKX7VG6PWT62AS5/events.json","paper":"https://pith.science/paper/KE66CYMP"},"agent_actions":{"view_html":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5","download_json":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5.json","view_paper":"https://pith.science/paper/KE66CYMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07518&json=true","fetch_graph":"https://pith.science/api/pith-number/KE66CYMPQ2RBKX7VG6PWT62AS5/graph.json","fetch_events":"https://pith.science/api/pith-number/KE66CYMPQ2RBKX7VG6PWT62AS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5/action/storage_attestation","attest_author":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5/action/author_attestation","sign_citation":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5/action/citation_signature","submit_replication":"https://pith.science/pith/KE66CYMPQ2RBKX7VG6PWT62AS5/action/replication_record"}},"created_at":"2026-07-05T11:46:34.093703+00:00","updated_at":"2026-07-05T11:46:34.093703+00:00"}