{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3PSJZFMVSL3XIMYCO3CF26LOOV","short_pith_number":"pith:3PSJZFMV","schema_version":"1.0","canonical_sha256":"dbe49c959592f774330276c45d796e7564445357e4875975dda51b526f6268b8","source":{"kind":"arxiv","id":"2404.15639","version":3},"attestation_state":"computed","paper":{"title":"CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Batu Guan, Hongyu Zhang, Lichao Sun, Pan Zhou, Yao Wan, Zhangqian Bi, Zheng Wang","submitted_at":"2024-04-24T04:25:04Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable progress in code generation. It now becomes crucial to identify whether the code is AI-generated and to determine the specific model used, particularly for purposes such as protecting Intellectual Property (IP) in industry and preventing cheating in programming exercises. To this end, several attempts have been made to insert watermarks into machine-generated code. However, existing approaches are limited to inserting only a single bit of information. In this paper, we introduce CodeIP, a novel multi-bit watermarking technique that inserts "},"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":"2404.15639","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T04:25:04Z","cross_cats_sorted":[],"title_canon_sha256":"216c0c412775f6b27bd42164e077db1f9aae6378f52166b96b5efd1d89de515e","abstract_canon_sha256":"b9a75eaa97c53dee8b6d91d5a19efe1d448db99282ffcc60a22078a219039432"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:09.157718Z","signature_b64":"9Hw78nCqtglyV0QsvrnIdZeR5BId8Gf+obOGhYtk3DAOWhrhANUQWLX81pHylOsh+oMVIVzfLnuLAbrgHcOiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbe49c959592f774330276c45d796e7564445357e4875975dda51b526f6268b8","last_reissued_at":"2026-07-05T09:55:09.157229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:09.157229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Batu Guan, Hongyu Zhang, Lichao Sun, Pan Zhou, Yao Wan, Zhangqian Bi, Zheng Wang","submitted_at":"2024-04-24T04:25:04Z","abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable progress in code generation. It now becomes crucial to identify whether the code is AI-generated and to determine the specific model used, particularly for purposes such as protecting Intellectual Property (IP) in industry and preventing cheating in programming exercises. To this end, several attempts have been made to insert watermarks into machine-generated code. However, existing approaches are limited to inserting only a single bit of information. In this paper, we introduce CodeIP, a novel multi-bit watermarking technique that inserts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15639","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/2404.15639/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":"2404.15639","created_at":"2026-07-05T09:55:09.157286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15639v3","created_at":"2026-07-05T09:55:09.157286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15639","created_at":"2026-07-05T09:55:09.157286+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PSJZFMVSL3X","created_at":"2026-07-05T09:55:09.157286+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PSJZFMVSL3XIMYC","created_at":"2026-07-05T09:55:09.157286+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PSJZFMV","created_at":"2026-07-05T09:55:09.157286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16001","citing_title":"MATRIX: Multi-Layer Code Watermarking via Dual-Channel Constrained Parity-Check Encoding","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV","json":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV.json","graph_json":"https://pith.science/api/pith-number/3PSJZFMVSL3XIMYCO3CF26LOOV/graph.json","events_json":"https://pith.science/api/pith-number/3PSJZFMVSL3XIMYCO3CF26LOOV/events.json","paper":"https://pith.science/paper/3PSJZFMV"},"agent_actions":{"view_html":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV","download_json":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV.json","view_paper":"https://pith.science/paper/3PSJZFMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15639&json=true","fetch_graph":"https://pith.science/api/pith-number/3PSJZFMVSL3XIMYCO3CF26LOOV/graph.json","fetch_events":"https://pith.science/api/pith-number/3PSJZFMVSL3XIMYCO3CF26LOOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV/action/storage_attestation","attest_author":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV/action/author_attestation","sign_citation":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV/action/citation_signature","submit_replication":"https://pith.science/pith/3PSJZFMVSL3XIMYCO3CF26LOOV/action/replication_record"}},"created_at":"2026-07-05T09:55:09.157286+00:00","updated_at":"2026-07-05T09:55:09.157286+00:00"}