{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2QLM6JONXQJQXP4RAQMAM7KV7Y","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c5094c0c7e397be8def41e4c75fc045832972063aebfee986d7c8b4c2e4edcf3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-21T13:21:29Z","title_canon_sha256":"140908a63bc4e4099d8ad245a05ae42830e645d04d4367b750fda974040b851c"},"schema_version":"1.0","source":{"id":"2507.15599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15599","created_at":"2026-07-05T11:40:39Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15599v1","created_at":"2026-07-05T11:40:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15599","created_at":"2026-07-05T11:40:39Z"},{"alias_kind":"pith_short_12","alias_value":"2QLM6JONXQJQ","created_at":"2026-07-05T11:40:39Z"},{"alias_kind":"pith_short_16","alias_value":"2QLM6JONXQJQXP4R","created_at":"2026-07-05T11:40:39Z"},{"alias_kind":"pith_short_8","alias_value":"2QLM6JON","created_at":"2026-07-05T11:40:39Z"}],"graph_snapshots":[{"event_id":"sha256:8bc035c733d54e91786342b1988d4c0ab66475dd78be6e1bc37692955dd65cd8","target":"graph","created_at":"2026-07-05T11:40:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.15599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models for code (Code LLM) are increasingly utilized in programming environments. Despite their utility, the training datasets for top LLM remain undisclosed, raising concerns about potential copyright violations. Some models, such as Pleias and Comma put emphasis on data curation and licenses, however, with limited training data these models are not competitive and only serve as proof of concepts. To improve the utility of these models, we propose an application of the \"Chinese Wall\" technique, inspired by the reverse engineering technique of the same name -- a high quality mod","authors_text":"Manatsawin Hanmongkolchai","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-21T13:21:29Z","title":"Applying the Chinese Wall Reverse Engineering Technique to Large Language Model Code Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15599","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a18bf634f10b9de57f40bceae53d852b2b811e43b1c5fa3d0b5a82a005cf2031","target":"record","created_at":"2026-07-05T11:40:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c5094c0c7e397be8def41e4c75fc045832972063aebfee986d7c8b4c2e4edcf3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-21T13:21:29Z","title_canon_sha256":"140908a63bc4e4099d8ad245a05ae42830e645d04d4367b750fda974040b851c"},"schema_version":"1.0","source":{"id":"2507.15599","kind":"arxiv","version":1}},"canonical_sha256":"d416cf25cdbc130bbf910418067d55fe2c0634901e4d870eea3fa11fa3b4907e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d416cf25cdbc130bbf910418067d55fe2c0634901e4d870eea3fa11fa3b4907e","first_computed_at":"2026-07-05T11:40:39.818473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:39.818473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AE7DRFkE4v3FZiUStjBQazHjKMUJX4rCCKj/GI5ruAyI8Hh1VIFXsDQlxxixaBuRFuZ3sqjMYDa/QAGrW0DXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:39.818936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a18bf634f10b9de57f40bceae53d852b2b811e43b1c5fa3d0b5a82a005cf2031","sha256:8bc035c733d54e91786342b1988d4c0ab66475dd78be6e1bc37692955dd65cd8"],"state_sha256":"d089d8582a9ab6bfe7deb467275e1e23ec45dd53f95f5a87f97086a8016dc8a8"}