{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2CDMVYOMJW24JBGADW4KC3HZBI","short_pith_number":"pith:2CDMVYOM","schema_version":"1.0","canonical_sha256":"d086cae1cc4db5c484c01db8a16cf90a11036a6be059ef503c651808f603728d","source":{"kind":"arxiv","id":"2410.10628","version":3},"attestation_state":"computed","paper":{"title":"On the Diffusion of Test Smells in LLM-Generated Unit Tests","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Anil Koyuncu, David Lo, Jacques Klein, Tegawend\\'e F. Bissyand\\'e, Wendk\\^uuni C. Ou\\'edraogo, Xueqi Dang, Xunzhu Tang, Yinghua Li","submitted_at":"2024-10-14T15:35:44Z","abstract_excerpt":"LLMs promise to transform unit test generation from a manual burden into an automated solution. Yet, beyond metrics such as compilability or coverage, little is known about the quality of LLM-generated tests, particularly their susceptibility to test smells, design flaws that undermine readability and maintainability. This paper presents the first multi-benchmark, large-scale analysis of test smell diffusion in LLM-generated unit tests. We contrast LLM outputs with human-written suites (as the reference for real-world practices) and SBST-generated tests from EvoSuite (as the automated baseline"},"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":"2410.10628","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-14T15:35:44Z","cross_cats_sorted":[],"title_canon_sha256":"dc97ac7c779a13bcbece05cc22dcbdcbe1a1fe6794833b86f1fbd9e93a9d83ef","abstract_canon_sha256":"2eea89c082bfb5a3809da7c4a618d8ea1a28379932a48ec5bce77248119819c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:35:56.141739Z","signature_b64":"O7W/1EDHt8aIf2Wu/RmqAnWJUQlphiCGXASeL6F4zFALSwThaIzrpIWL0Sx24VL+gfRfl4pogcbnijvTaspgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d086cae1cc4db5c484c01db8a16cf90a11036a6be059ef503c651808f603728d","last_reissued_at":"2026-08-04T00:35:56.140183Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:35:56.140183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Diffusion of Test Smells in LLM-Generated Unit Tests","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Anil Koyuncu, David Lo, Jacques Klein, Tegawend\\'e F. Bissyand\\'e, Wendk\\^uuni C. Ou\\'edraogo, Xueqi Dang, Xunzhu Tang, Yinghua Li","submitted_at":"2024-10-14T15:35:44Z","abstract_excerpt":"LLMs promise to transform unit test generation from a manual burden into an automated solution. Yet, beyond metrics such as compilability or coverage, little is known about the quality of LLM-generated tests, particularly their susceptibility to test smells, design flaws that undermine readability and maintainability. This paper presents the first multi-benchmark, large-scale analysis of test smell diffusion in LLM-generated unit tests. We contrast LLM outputs with human-written suites (as the reference for real-world practices) and SBST-generated tests from EvoSuite (as the automated baseline"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10628","kind":"arxiv","version":3},"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/2410.10628/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":"2410.10628","created_at":"2026-08-04T00:35:56.141337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10628v3","created_at":"2026-08-04T00:35:56.141337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10628","created_at":"2026-08-04T00:35:56.141337+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CDMVYOMJW24","created_at":"2026-08-04T00:35:56.141337+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CDMVYOMJW24JBGA","created_at":"2026-08-04T00:35:56.141337+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CDMVYOM","created_at":"2026-08-04T00:35:56.141337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.08588","citing_title":"LLM vs. Human Unit Tests: Fault Detection on Real Python Bugs","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28229","citing_title":"Humanizing Automatically Generated Unit Test Suites with LLM-Based Refactoring","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28229","citing_title":"Humanizing Automatically Generated Unit Test Suites with LLM-Based Refactoring","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI","json":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI.json","graph_json":"https://pith.science/api/pith-number/2CDMVYOMJW24JBGADW4KC3HZBI/graph.json","events_json":"https://pith.science/api/pith-number/2CDMVYOMJW24JBGADW4KC3HZBI/events.json","paper":"https://pith.science/paper/2CDMVYOM"},"agent_actions":{"view_html":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI","download_json":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI.json","view_paper":"https://pith.science/paper/2CDMVYOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10628&json=true","fetch_graph":"https://pith.science/api/pith-number/2CDMVYOMJW24JBGADW4KC3HZBI/graph.json","fetch_events":"https://pith.science/api/pith-number/2CDMVYOMJW24JBGADW4KC3HZBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI/action/storage_attestation","attest_author":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI/action/author_attestation","sign_citation":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI/action/citation_signature","submit_replication":"https://pith.science/pith/2CDMVYOMJW24JBGADW4KC3HZBI/action/replication_record"}},"created_at":"2026-08-04T00:35:56.141337+00:00","updated_at":"2026-08-04T00:35:56.141337+00:00"}