{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SY4S7XMZNKFKOGZH42GOVG5TKF","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":"40943b5edf5bac935aee8a843bab19025d63c0b0f132e50a1f2447f9da6903bd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-21T08:04:12Z","title_canon_sha256":"d08888175a25caa1de263758336ee55fbf93e661f2487ec5e3f240f9666c18c6"},"schema_version":"1.0","source":{"id":"2506.17627","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17627","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17627v1","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17627","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"pith_short_12","alias_value":"SY4S7XMZNKFK","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"pith_short_16","alias_value":"SY4S7XMZNKFKOGZH","created_at":"2026-07-05T11:25:20Z"},{"alias_kind":"pith_short_8","alias_value":"SY4S7XMZ","created_at":"2026-07-05T11:25:20Z"}],"graph_snapshots":[{"event_id":"sha256:153ff3fdce54a979fa877c74222ec881e43f1b94ec4ecd65ea6512f00c5fa4d7","target":"graph","created_at":"2026-07-05T11:25:20Z","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/2506.17627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Concerns about benchmark leakage in large language models for code (Code LLMs) have raised issues of data contamination and inflated evaluation metrics. The diversity and inaccessibility of many training datasets make it difficult to prevent data leakage entirely, even with time lag strategies. Consequently, generating new datasets through code perturbation has become essential. However, existing methods often fail to produce complex and diverse variations, struggle with complex cross-file dependencies, and lack support for multiple programming languages, which limits their effectiveness in en","authors_text":"Haoyu Wang, Hongzhou Rao, Ling Xiao, Meizhen Wang, Wenjie Zhu, Yanjie Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-21T08:04:12Z","title":"CodeMorph: Mitigating Data Leakage in Large Language Model Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17627","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:d3e1069ba7ec3acc391427dab4c1d221d469fdeec292ffc203bd35101c0167a1","target":"record","created_at":"2026-07-05T11:25:20Z","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":"40943b5edf5bac935aee8a843bab19025d63c0b0f132e50a1f2447f9da6903bd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-21T08:04:12Z","title_canon_sha256":"d08888175a25caa1de263758336ee55fbf93e661f2487ec5e3f240f9666c18c6"},"schema_version":"1.0","source":{"id":"2506.17627","kind":"arxiv","version":1}},"canonical_sha256":"96392fdd996a8aa71b27e68cea9bb351783f985b63e13df062d9c0522e8a49b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96392fdd996a8aa71b27e68cea9bb351783f985b63e13df062d9c0522e8a49b3","first_computed_at":"2026-07-05T11:25:20.674350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:20.674350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HB49n+Y4/kWnccPtyhrwCYrh4CHGGDqKiUCiXqbQZr6t+GklbQqi/qdJZve6G7k+yO++xEjocSJwZZTN7RbMAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:20.674837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17627","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3e1069ba7ec3acc391427dab4c1d221d469fdeec292ffc203bd35101c0167a1","sha256:153ff3fdce54a979fa877c74222ec881e43f1b94ec4ecd65ea6512f00c5fa4d7"],"state_sha256":"38ab2704c9be6b85cfeef2d0e4445ca9779b8b19ecc6ba44aef21457b5b811a7"}