{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DQCYZ473ALPRJZCCVIRAACPJTA","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":"eea97664823be766f7902847648edfd452c913678ab65c57e1ec6acd3ad6f044","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-03T05:24:03Z","title_canon_sha256":"360246eeb7b54ab62ea35f02c61621857df96bac38fb4337ea33c9d532e4d797"},"schema_version":"1.0","source":{"id":"2608.01715","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01715","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01715v1","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01715","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"DQCYZ473ALPR","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"DQCYZ473ALPRJZCC","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"DQCYZ473","created_at":"2026-08-04T02:06:36Z"}],"graph_snapshots":[{"event_id":"sha256:7db8442fee75af38d8ad3bc3fbd081378ef08ca7b22050d40425d561d8a77478","target":"graph","created_at":"2026-08-04T02:06:36Z","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/2608.01715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Online-judge verdicts and the datasets and benchmarks built on them are treated as ground truth for evaluating and training large language models for code. Yet prior audits have sounded a warning: official suites accept buggy submissions. These audits, however, stop at the warning and offer no practical remedy. Our remedy has two parts: an off-the-shelf coding agent, serving as a test-suite auditor, both builds adversarial test suites to expose what official suites miss and supplies these suites where no official suite exists; a certification chain determines whether each agent-flagged submiss","authors_text":"Feng Zhu, Shuxiao Xie, Shuyang Xie, Wangmeng Zuo, Yanli Ji","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-03T05:24:03Z","title":"Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01715","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":"sha256:0d0ffec23070185268d41518434d54633d8267f4d9e2146b0d5a4546b57e6587","target":"record","created_at":"2026-08-04T02:06:36Z","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":"eea97664823be766f7902847648edfd452c913678ab65c57e1ec6acd3ad6f044","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-03T05:24:03Z","title_canon_sha256":"360246eeb7b54ab62ea35f02c61621857df96bac38fb4337ea33c9d532e4d797"},"schema_version":"1.0","source":{"id":"2608.01715","kind":"arxiv","version":1}},"canonical_sha256":"1c058cf3fb02df14e442aa220009e99826d66e3f6c14af324dfa79e608ae2744","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c058cf3fb02df14e442aa220009e99826d66e3f6c14af324dfa79e608ae2744","first_computed_at":"2026-08-04T02:06:36.841581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:06:36.841581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8uFpN0Zaze76Y4bYj8SiIEWFEe8w70l4vOpRJTp3LoEu7KRINY1wPl/YO7jM8S2FwMv0qk0nKeEyg0ykn03FBg==","signature_status":"signed_v1","signed_at":"2026-08-04T02:06:36.843024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01715","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d0ffec23070185268d41518434d54633d8267f4d9e2146b0d5a4546b57e6587","sha256:7db8442fee75af38d8ad3bc3fbd081378ef08ca7b22050d40425d561d8a77478"],"state_sha256":"42afd3f0242b32eed643257c575154aac48073230e8818f32caf2be34903d139"}