{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DR2FWU6AU6FOIYHJFCJJOREKEL","short_pith_number":"pith:DR2FWU6A","schema_version":"1.0","canonical_sha256":"1c745b53c0a78ae460e9289297448a22fe14f010b5ed72e0287b226183f035fc","source":{"kind":"arxiv","id":"2506.12278","version":1},"attestation_state":"computed","paper":{"title":"Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Xue Xia, Yilun Zhao, Zexi Kuang, Zheyuan Yang","submitted_at":"2025-06-13T23:56:17Z","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"},"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":"2506.12278","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-13T23:56:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"609ba75a5c4354fbdc50e503cb19f859897cbb65499c1884c39782a94214a665","abstract_canon_sha256":"d75776d08eb1c042eb326d607572a309fce01abffad9299345c4a3d9d0a814cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:50.721367Z","signature_b64":"+fGqtzDM4Q/9Ls4FnayvTH9hL1VY3Krsjd1CZvFLWk9bAMj7tQzOc8/vTHvBd2UmkyDCui16AErFrQ1H5iZDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c745b53c0a78ae460e9289297448a22fe14f010b5ed72e0287b226183f035fc","last_reissued_at":"2026-07-05T11:21:50.720928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:50.720928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Xue Xia, Yilun Zhao, Zexi Kuang, Zheyuan Yang","submitted_at":"2025-06-13T23:56:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12278","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/2506.12278/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":"2506.12278","created_at":"2026-07-05T11:21:50.720982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12278v1","created_at":"2026-07-05T11:21:50.720982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12278","created_at":"2026-07-05T11:21:50.720982+00:00"},{"alias_kind":"pith_short_12","alias_value":"DR2FWU6AU6FO","created_at":"2026-07-05T11:21:50.720982+00:00"},{"alias_kind":"pith_short_16","alias_value":"DR2FWU6AU6FOIYHJ","created_at":"2026-07-05T11:21:50.720982+00:00"},{"alias_kind":"pith_short_8","alias_value":"DR2FWU6A","created_at":"2026-07-05T11:21:50.720982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01715","citing_title":"Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL","json":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL.json","graph_json":"https://pith.science/api/pith-number/DR2FWU6AU6FOIYHJFCJJOREKEL/graph.json","events_json":"https://pith.science/api/pith-number/DR2FWU6AU6FOIYHJFCJJOREKEL/events.json","paper":"https://pith.science/paper/DR2FWU6A"},"agent_actions":{"view_html":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL","download_json":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL.json","view_paper":"https://pith.science/paper/DR2FWU6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12278&json=true","fetch_graph":"https://pith.science/api/pith-number/DR2FWU6AU6FOIYHJFCJJOREKEL/graph.json","fetch_events":"https://pith.science/api/pith-number/DR2FWU6AU6FOIYHJFCJJOREKEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL/action/storage_attestation","attest_author":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL/action/author_attestation","sign_citation":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL/action/citation_signature","submit_replication":"https://pith.science/pith/DR2FWU6AU6FOIYHJFCJJOREKEL/action/replication_record"}},"created_at":"2026-07-05T11:21:50.720982+00:00","updated_at":"2026-07-05T11:21:50.720982+00:00"}