{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DQCYZ473ALPRJZCCVIRAACPJTA","short_pith_number":"pith:DQCYZ473","schema_version":"1.0","canonical_sha256":"1c058cf3fb02df14e442aa220009e99826d66e3f6c14af324dfa79e608ae2744","source":{"kind":"arxiv","id":"2608.01715","version":1},"attestation_state":"computed","paper":{"title":"Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Feng Zhu, Shuxiao Xie, Shuyang Xie, Wangmeng Zuo, Yanli Ji","submitted_at":"2026-08-03T05:24:03Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.01715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-03T05:24:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"360246eeb7b54ab62ea35f02c61621857df96bac38fb4337ea33c9d532e4d797","abstract_canon_sha256":"eea97664823be766f7902847648edfd452c913678ab65c57e1ec6acd3ad6f044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:06:36.843024Z","signature_b64":"8uFpN0Zaze76Y4bYj8SiIEWFEe8w70l4vOpRJTp3LoEu7KRINY1wPl/YO7jM8S2FwMv0qk0nKeEyg0ykn03FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c058cf3fb02df14e442aa220009e99826d66e3f6c14af324dfa79e608ae2744","last_reissued_at":"2026-08-04T02:06:36.841581Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:06:36.841581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Feng Zhu, Shuxiao Xie, Shuyang Xie, Wangmeng Zuo, Yanli Ji","submitted_at":"2026-08-03T05:24:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01715","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.01715/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.01715","created_at":"2026-08-04T02:06:36.843003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01715v1","created_at":"2026-08-04T02:06:36.843003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01715","created_at":"2026-08-04T02:06:36.843003+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQCYZ473ALPR","created_at":"2026-08-04T02:06:36.843003+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQCYZ473ALPRJZCC","created_at":"2026-08-04T02:06:36.843003+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQCYZ473","created_at":"2026-08-04T02:06:36.843003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA","json":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA.json","graph_json":"https://pith.science/api/pith-number/DQCYZ473ALPRJZCCVIRAACPJTA/graph.json","events_json":"https://pith.science/api/pith-number/DQCYZ473ALPRJZCCVIRAACPJTA/events.json","paper":"https://pith.science/paper/DQCYZ473"},"agent_actions":{"view_html":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA","download_json":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA.json","view_paper":"https://pith.science/paper/DQCYZ473","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01715&json=true","fetch_graph":"https://pith.science/api/pith-number/DQCYZ473ALPRJZCCVIRAACPJTA/graph.json","fetch_events":"https://pith.science/api/pith-number/DQCYZ473ALPRJZCCVIRAACPJTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA/action/storage_attestation","attest_author":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA/action/author_attestation","sign_citation":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA/action/citation_signature","submit_replication":"https://pith.science/pith/DQCYZ473ALPRJZCCVIRAACPJTA/action/replication_record"}},"created_at":"2026-08-04T02:06:36.843003+00:00","updated_at":"2026-08-04T02:06:36.843003+00:00"}