{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ESOMXAYLFKBDBGS5NT4QZ7PBSS","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":"f870a7b489b550a4e07dc7ab0e97d1bc816d9c5361e6a9bbc2a5e7d516cd9883","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-08T14:45:08Z","title_canon_sha256":"6ab95b6196547dc8c86f380e3f93916f2425ae593549b4f1137c10c2c740db8a"},"schema_version":"1.0","source":{"id":"2607.07481","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07481","created_at":"2026-07-09T01:20:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07481v1","created_at":"2026-07-09T01:20:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07481","created_at":"2026-07-09T01:20:26Z"},{"alias_kind":"pith_short_12","alias_value":"ESOMXAYLFKBD","created_at":"2026-07-09T01:20:26Z"},{"alias_kind":"pith_short_16","alias_value":"ESOMXAYLFKBDBGS5","created_at":"2026-07-09T01:20:26Z"},{"alias_kind":"pith_short_8","alias_value":"ESOMXAYL","created_at":"2026-07-09T01:20:26Z"}],"graph_snapshots":[{"event_id":"sha256:d0e738c0eb9ad68dbbbe6424ee1a22eb517049d900e16a47f42cf6956a3125a4","target":"graph","created_at":"2026-07-09T01:20:26Z","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/2607.07481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are increasingly used to evaluate and support software engineering tasks, yet the validity of these evaluations is often undermined by uncertainty about whether benchmark instances were seen during pretraining. This can lead to data contamination, which may inflate performance and result in misleading conclusions about model capability. Despite this, the training corpora of many modern models are only partially disclosed, making direct decontamination infeasible. This creates a need for practical methods that can detect a large language models' prior exposure to training ","authors_text":"Ali Al-Kaswan, Jonathan Katzy, Razvan Mihai Popescu, Zhou Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-08T14:45:08Z","title":"The Poisoned Chalice of LLM Evaluation Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07481","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:dc439386294b4938f235ffc9f439e25f92d63fb707c18d9b7aa44254334fcf03","target":"record","created_at":"2026-07-09T01:20:26Z","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":"f870a7b489b550a4e07dc7ab0e97d1bc816d9c5361e6a9bbc2a5e7d516cd9883","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-08T14:45:08Z","title_canon_sha256":"6ab95b6196547dc8c86f380e3f93916f2425ae593549b4f1137c10c2c740db8a"},"schema_version":"1.0","source":{"id":"2607.07481","kind":"arxiv","version":1}},"canonical_sha256":"249ccb830b2a82309a5d6cf90cfde194b2b702da7ecc8cd6b7b4612ce090b603","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"249ccb830b2a82309a5d6cf90cfde194b2b702da7ecc8cd6b7b4612ce090b603","first_computed_at":"2026-07-09T01:20:26.023937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:26.023937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dq0Q2htVjJM2n6K3YCg9FhgydhhXLaFrzM3YW/IPnFn+P+jUGzpKAajpnZ9UldGHZPXa67fj/KnJrOsMG36TAw==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:26.024293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07481","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc439386294b4938f235ffc9f439e25f92d63fb707c18d9b7aa44254334fcf03","sha256:d0e738c0eb9ad68dbbbe6424ee1a22eb517049d900e16a47f42cf6956a3125a4"],"state_sha256":"79d9072be6464129b84d1ca71aab980e99a3ec3dac7e0a7b9a6d4e34dca43ac2"}