{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PUXG74NBQ4HMZXWFEXWYFHAOEO","short_pith_number":"pith:PUXG74NB","schema_version":"1.0","canonical_sha256":"7d2e6ff1a1870eccdec525ed829c0e239420c9daadd21ed2f7fb13bb0177e85f","source":{"kind":"arxiv","id":"2404.13340","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models as Test Case Generators: Performance Evaluation and Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Kefan Li, Yuan Yuan","submitted_at":"2024-04-20T10:27:01Z","abstract_excerpt":"Code generation with Large Language Models (LLMs) has been extensively studied and achieved remarkable progress. As a complementary aspect to code generation, test case generation is of crucial importance in ensuring the quality and reliability of code. However, using LLMs as test case generators has been much less explored. Current research along this line primarily focuses on enhancing code generation with assistance from test cases generated by LLMs, while the performance of LLMs in test case generation alone has not been comprehensively examined. To bridge this gap, we conduct extensive ex"},"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":"2404.13340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-04-20T10:27:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e9984410e8a6469eef02c1ba0c0c22139c9e19026aa01282af03da87925363e","abstract_canon_sha256":"a1836d76b4a8e594625b55b453cffde3c514d9a9950e9120a327f0c6c305b2f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:30.610659Z","signature_b64":"ap9DxSeC5ZsmIOh0gGxuGz0onfPlgf3VuATkwM9PBsBath4EtETSpIfI5W/ZucrG+KZFV8uvkcc+5tNrhp4fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d2e6ff1a1870eccdec525ed829c0e239420c9daadd21ed2f7fb13bb0177e85f","last_reissued_at":"2026-07-05T08:10:30.610186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:30.610186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Test Case Generators: Performance Evaluation and Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Kefan Li, Yuan Yuan","submitted_at":"2024-04-20T10:27:01Z","abstract_excerpt":"Code generation with Large Language Models (LLMs) has been extensively studied and achieved remarkable progress. As a complementary aspect to code generation, test case generation is of crucial importance in ensuring the quality and reliability of code. However, using LLMs as test case generators has been much less explored. Current research along this line primarily focuses on enhancing code generation with assistance from test cases generated by LLMs, while the performance of LLMs in test case generation alone has not been comprehensively examined. To bridge this gap, we conduct extensive ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13340","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/2404.13340/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":"2404.13340","created_at":"2026-07-05T08:10:30.610244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13340v1","created_at":"2026-07-05T08:10:30.610244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13340","created_at":"2026-07-05T08:10:30.610244+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUXG74NBQ4HM","created_at":"2026-07-05T08:10:30.610244+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUXG74NBQ4HMZXWF","created_at":"2026-07-05T08:10:30.610244+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUXG74NB","created_at":"2026-07-05T08:10:30.610244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.18315","citing_title":"Effective LLM Code Refinement via Property-Oriented and Structurally Minimal Feedback","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27098","citing_title":"Ensemble-Based Uncertainty Estimation for Code Correctness Estimation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15270","citing_title":"Enhancing Large Language Models with Retrieval Augmented Generation for Software Testing and Inspection Automation","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO","json":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO.json","graph_json":"https://pith.science/api/pith-number/PUXG74NBQ4HMZXWFEXWYFHAOEO/graph.json","events_json":"https://pith.science/api/pith-number/PUXG74NBQ4HMZXWFEXWYFHAOEO/events.json","paper":"https://pith.science/paper/PUXG74NB"},"agent_actions":{"view_html":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO","download_json":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO.json","view_paper":"https://pith.science/paper/PUXG74NB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13340&json=true","fetch_graph":"https://pith.science/api/pith-number/PUXG74NBQ4HMZXWFEXWYFHAOEO/graph.json","fetch_events":"https://pith.science/api/pith-number/PUXG74NBQ4HMZXWFEXWYFHAOEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO/action/storage_attestation","attest_author":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO/action/author_attestation","sign_citation":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO/action/citation_signature","submit_replication":"https://pith.science/pith/PUXG74NBQ4HMZXWFEXWYFHAOEO/action/replication_record"}},"created_at":"2026-07-05T08:10:30.610244+00:00","updated_at":"2026-07-05T08:10:30.610244+00:00"}