{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RAG6USJOAXYP2UJC3CY4HUVI35","short_pith_number":"pith:RAG6USJO","schema_version":"1.0","canonical_sha256":"880dea492e05f0fd5122d8b1c3d2a8df4bbc27c57c668716325fa9b1b8607a54","source":{"kind":"arxiv","id":"2302.06527","version":4},"attestation_state":"computed","paper":{"title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Aryaz Eghbali, Frank Tip, Max Sch\\\"afer, Sarah Nadi","submitted_at":"2023-02-13T17:13:41Z","abstract_excerpt":"Unit tests play a key role in ensuring the correctness of software. However, manually creating unit tests is a laborious task, motivating the need for automation. Large Language Models (LLMs) have recently been applied to this problem, utilizing additional training or few-shot learning on examples of existing tests. This paper presents a large-scale empirical evaluation on the effectiveness of LLMs for automated unit test generation without additional training or manual effort, providing the LLM with the signature and implementation of the function under test, along with usage examples extract"},"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":"2302.06527","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-02-13T17:13:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b2cbd4a648ea17bb86112792a38d12248e17493f13ddf298b5c5dbb260f6008","abstract_canon_sha256":"08ece531cddd0ea5a9cd04e3bcd5109fb314b6c699344a0f256da7727fdc836a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:15.421985Z","signature_b64":"FkbjzhoDFKtoZXWJV2dllmi97TrEblHd82SYsQr+YMv2Lja1eD71FnqUGJWvo+JOIvifMCCFnq2wtX7Ea1rPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"880dea492e05f0fd5122d8b1c3d2a8df4bbc27c57c668716325fa9b1b8607a54","last_reissued_at":"2026-07-05T07:22:15.421517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:15.421517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Aryaz Eghbali, Frank Tip, Max Sch\\\"afer, Sarah Nadi","submitted_at":"2023-02-13T17:13:41Z","abstract_excerpt":"Unit tests play a key role in ensuring the correctness of software. However, manually creating unit tests is a laborious task, motivating the need for automation. Large Language Models (LLMs) have recently been applied to this problem, utilizing additional training or few-shot learning on examples of existing tests. This paper presents a large-scale empirical evaluation on the effectiveness of LLMs for automated unit test generation without additional training or manual effort, providing the LLM with the signature and implementation of the function under test, along with usage examples extract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06527","kind":"arxiv","version":4},"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/2302.06527/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":"2302.06527","created_at":"2026-07-05T07:22:15.421572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06527v4","created_at":"2026-07-05T07:22:15.421572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06527","created_at":"2026-07-05T07:22:15.421572+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAG6USJOAXYP","created_at":"2026-07-05T07:22:15.421572+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAG6USJOAXYP2UJC","created_at":"2026-07-05T07:22:15.421572+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAG6USJO","created_at":"2026-07-05T07:22:15.421572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22704","citing_title":"VeriPort: Automated and Verified Patch Backporting at Scale","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18917","citing_title":"ClassInvGen: Class Invariant Synthesis using Large Language Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27098","citing_title":"Ensemble-Based Uncertainty Estimation for Code Correctness Estimation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2407.01489","citing_title":"Agentless: Demystifying LLM-based Software Engineering Agents","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03356","citing_title":"POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24450","citing_title":"On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19826","citing_title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35","json":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35.json","graph_json":"https://pith.science/api/pith-number/RAG6USJOAXYP2UJC3CY4HUVI35/graph.json","events_json":"https://pith.science/api/pith-number/RAG6USJOAXYP2UJC3CY4HUVI35/events.json","paper":"https://pith.science/paper/RAG6USJO"},"agent_actions":{"view_html":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35","download_json":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35.json","view_paper":"https://pith.science/paper/RAG6USJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06527&json=true","fetch_graph":"https://pith.science/api/pith-number/RAG6USJOAXYP2UJC3CY4HUVI35/graph.json","fetch_events":"https://pith.science/api/pith-number/RAG6USJOAXYP2UJC3CY4HUVI35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35/action/storage_attestation","attest_author":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35/action/author_attestation","sign_citation":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35/action/citation_signature","submit_replication":"https://pith.science/pith/RAG6USJOAXYP2UJC3CY4HUVI35/action/replication_record"}},"created_at":"2026-07-05T07:22:15.421572+00:00","updated_at":"2026-07-05T07:22:15.421572+00:00"}