{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DR2FWU6AU6FOIYHJFCJJOREKEL","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":"d75776d08eb1c042eb326d607572a309fce01abffad9299345c4a3d9d0a814cd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-13T23:56:17Z","title_canon_sha256":"609ba75a5c4354fbdc50e503cb19f859897cbb65499c1884c39782a94214a665"},"schema_version":"1.0","source":{"id":"2506.12278","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12278","created_at":"2026-07-05T11:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12278v1","created_at":"2026-07-05T11:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12278","created_at":"2026-07-05T11:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"DR2FWU6AU6FO","created_at":"2026-07-05T11:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"DR2FWU6AU6FOIYHJ","created_at":"2026-07-05T11:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"DR2FWU6A","created_at":"2026-07-05T11:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:7eb806f97fb36937d76ff012196a21a5ac6132fc9f00ac113d5896cdb0ff1f4d","target":"graph","created_at":"2026-07-05T11:21:50Z","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/2506.12278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce TestCase-Eval, a new benchmark for systematic evaluation of LLMs in test-case generation. TestCase-Eval includes 500 algorithm problems and 100,000 human-crafted solutions from the Codeforces platform. It focuses on two pivotal tasks: (1) Fault Coverage, which measures how well LLM-generated test sets probe diverse input scenarios and cover a wide range of potential failure modes. (2) Fault Exposure, which evaluates whether LLMs can craft a tailored test input that reveals a specific incorrect code implementation. We provide a comprehensive assessment of 19 state-of-the-art open-s","authors_text":"Xue Xia, Yilun Zhao, Zexi Kuang, Zheyuan Yang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-13T23:56:17Z","title":"Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12278","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:ae04f932a98dc33a3d9181e708e1738a6f623381308b2321968302ae74e299de","target":"record","created_at":"2026-07-05T11:21:50Z","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":"d75776d08eb1c042eb326d607572a309fce01abffad9299345c4a3d9d0a814cd","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-13T23:56:17Z","title_canon_sha256":"609ba75a5c4354fbdc50e503cb19f859897cbb65499c1884c39782a94214a665"},"schema_version":"1.0","source":{"id":"2506.12278","kind":"arxiv","version":1}},"canonical_sha256":"1c745b53c0a78ae460e9289297448a22fe14f010b5ed72e0287b226183f035fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c745b53c0a78ae460e9289297448a22fe14f010b5ed72e0287b226183f035fc","first_computed_at":"2026-07-05T11:21:50.720928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:50.720928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+fGqtzDM4Q/9Ls4FnayvTH9hL1VY3Krsjd1CZvFLWk9bAMj7tQzOc8/vTHvBd2UmkyDCui16AErFrQ1H5iZDBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:50.721367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12278","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae04f932a98dc33a3d9181e708e1738a6f623381308b2321968302ae74e299de","sha256:7eb806f97fb36937d76ff012196a21a5ac6132fc9f00ac113d5896cdb0ff1f4d"],"state_sha256":"21dd5d474f6eb315beca67e586bfa1071003650d905d4b19ac21964bbd292eec"}