{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AFK7QWKYC7JDLCTE6NLA3WXKO6","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":"986d02dfab5f14aa3ead705f1f7a7a1261ae3ab9b83b0ed3f0f7e1c214a89c0b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T15:37:03Z","title_canon_sha256":"3f41731359edaa3a9fc7a1c914e1c30b683a645a900775a4365ab4c0a4057664"},"schema_version":"1.0","source":{"id":"2608.07341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07341","created_at":"2026-08-10T01:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07341v1","created_at":"2026-08-10T01:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07341","created_at":"2026-08-10T01:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"AFK7QWKYC7JD","created_at":"2026-08-10T01:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"AFK7QWKYC7JDLCTE","created_at":"2026-08-10T01:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"AFK7QWKY","created_at":"2026-08-10T01:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:15854795e7ffe71eeb60e46bdfe0e65b7fd971f1e13a73fa04cae419b7e731c2","target":"graph","created_at":"2026-08-10T01:15:05Z","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/2608.07341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test data from public benchmarks inevitably leaks into pretraining corpora, inflating evaluation scores once memorized. \\textbf{Contamination mitigation evaluation} intervenes in the decoding process to suppress memorization and restore a contaminated model's genuine capability, but its prevailing metric, the \\textbf{G-AP} (\\textbf{G}ap of \\textbf{A}ggregate \\textbf{P}erformance), is flawed. Discrete correct/incorrect readouts cannot characterize per-question performance, averaging before differencing lets over- and under-suppression cancel out, and uniform per-question weighting invites strat","authors_text":"Ruijie Hou, Yingming Li, Yueyang Jiao, Zhao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T15:37:03Z","title":"Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07341","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":"sha256:99d9e5ba93915c1d402abe02749b4042a1f83bf70a37ad7719c7a879e10f1ca0","target":"record","created_at":"2026-08-10T01:15:05Z","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":"986d02dfab5f14aa3ead705f1f7a7a1261ae3ab9b83b0ed3f0f7e1c214a89c0b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T15:37:03Z","title_canon_sha256":"3f41731359edaa3a9fc7a1c914e1c30b683a645a900775a4365ab4c0a4057664"},"schema_version":"1.0","source":{"id":"2608.07341","kind":"arxiv","version":1}},"canonical_sha256":"0155f8595817d2358a64f3560ddaea7784f42fe6b2e7a456d25b44946baf7483","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0155f8595817d2358a64f3560ddaea7784f42fe6b2e7a456d25b44946baf7483","first_computed_at":"2026-08-10T01:15:05.216189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:15:05.216189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wgMgrRnVZD2K6pbeeD3vpLcjjuufA+afibyA+yN5m0bmWkMhlQm7unpNQKxztjt6grrFJLVdDcedAAQN69WmAg==","signature_status":"signed_v1","signed_at":"2026-08-10T01:15:05.220456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99d9e5ba93915c1d402abe02749b4042a1f83bf70a37ad7719c7a879e10f1ca0","sha256:15854795e7ffe71eeb60e46bdfe0e65b7fd971f1e13a73fa04cae419b7e731c2"],"state_sha256":"1324e873cdc92655f1b913da55859d5f2fee0cf0b39751135e5c946e477e0b1d"}