{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3NYJQIF74FVZTJ3U7CPGW2X4QA","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":"31a00c2754d791302275d6e14ad7e7ed8f6d2352403352a5225aa67f82b21279","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T05:48:42Z","title_canon_sha256":"5df163fb9261a9c4ffab03cd7139ea6a55481742d326c56aa9701f0d86100290"},"schema_version":"1.0","source":{"id":"2606.29815","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29815","created_at":"2026-06-30T02:17:36Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29815v1","created_at":"2026-06-30T02:17:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29815","created_at":"2026-06-30T02:17:36Z"},{"alias_kind":"pith_short_12","alias_value":"3NYJQIF74FVZ","created_at":"2026-06-30T02:17:36Z"},{"alias_kind":"pith_short_16","alias_value":"3NYJQIF74FVZTJ3U","created_at":"2026-06-30T02:17:36Z"},{"alias_kind":"pith_short_8","alias_value":"3NYJQIF7","created_at":"2026-06-30T02:17:36Z"}],"graph_snapshots":[{"event_id":"sha256:e77f568c768ed61253ec0c1f48384257f7769269f0621575c85251f4d461a5c4","target":"graph","created_at":"2026-06-30T02:17:36Z","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/2606.29815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating code large language models (Code LLMs) requires reliable detection of data leakage, where benchmark performance is artificially inflated by exposure to benchmark data during pre-training. Existing approaches either assume access to proprietary training corpora, rely on brittle heuristics such as timestamp filtering, or use external reference sets with manually tuned, non-generalizable thresholds. To address these limitations, we introduce \\textbf{SrDetection}, a unified \\textbf{s}elf-\\textbf{r}eferential leakage detection framework for both gray-box (access to model logits) and blac","authors_text":"Chen Jason Zhang, Feiteng Fang, Hamid Alinejad-Rokny, Kun Jing, Liyang Fan, Min Yang, Shiwen Ni, Shuaimin Li, Yuanfeng Song, Yufang Lin, Zeyang Li, Zhuoyue Wan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T05:48:42Z","title":"SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29815","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":"sha256:28b7eb220f0f3bfa6aa299db4c30ea36080a5790e35400de578c0e5d33b0784c","target":"record","created_at":"2026-06-30T02:17:36Z","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":"31a00c2754d791302275d6e14ad7e7ed8f6d2352403352a5225aa67f82b21279","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T05:48:42Z","title_canon_sha256":"5df163fb9261a9c4ffab03cd7139ea6a55481742d326c56aa9701f0d86100290"},"schema_version":"1.0","source":{"id":"2606.29815","kind":"arxiv","version":1}},"canonical_sha256":"db709820bfe16b99a774f89e6b6afc800328515e49b7ae070e569f00ef2697e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db709820bfe16b99a774f89e6b6afc800328515e49b7ae070e569f00ef2697e7","first_computed_at":"2026-06-30T02:17:36.524460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:36.524460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mjSFMm8M9dfcBAdCgPCiFKLFGH8k7GlNCSRhYLmLVKV7fVtrGGfLshbfrkUszR4ZLruZlyQwHBsaQKv9638qCQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:36.524953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29815","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28b7eb220f0f3bfa6aa299db4c30ea36080a5790e35400de578c0e5d33b0784c","sha256:e77f568c768ed61253ec0c1f48384257f7769269f0621575c85251f4d461a5c4"],"state_sha256":"84e3e34be5ef260bb58ed28e4bec518a37c7a98df2c794408ce32352920f4d65"}