{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MWWIOXLEE44PLHTR2QLYYOTKDU","short_pith_number":"pith:MWWIOXLE","schema_version":"1.0","canonical_sha256":"65ac875d642738f59e71d4178c3a6a1d1aa57f0ff27b7ee89f756953620ee0af","source":{"kind":"arxiv","id":"2606.08588","version":1},"attestation_state":"computed","paper":{"title":"LLM vs. Human Unit Tests: Fault Detection on Real Python Bugs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Nasir U. Eisty, Phouvadeth Vathana, Prapti Bhatt, Rishi Patel","submitted_at":"2026-06-07T12:01:44Z","abstract_excerpt":"Large language models (LLMs) have shown considerable promise for automated unit test generation, yet their practical effectiveness relative to human-written tests remains poorly understood. Existing evaluations commonly rely on coverage-oriented benchmarks that do not assess fault-detection capability directly. We present an empirical comparison of LLM-generated and human-written unit tests across three complementary Python benchmarks: 29 real historical bugs from BugsInPy, a function-level benchmark drawn from python-slugify and packaging, and a controlled paired benchmark. Our generation pip"},"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":"2606.08588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-07T12:01:44Z","cross_cats_sorted":[],"title_canon_sha256":"2a67e2e95b9cd584be34b743b25d4a788b64586743dd316f4b507b27b2b51305","abstract_canon_sha256":"14b3e0694f9aefa6269152aa0ec8eef88f94de38f8cd093fbdc970a0d921b97a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:40.870574Z","signature_b64":"jC0pfGTumFnVoydPB31gyxCwJjNeKXxYskmgrk3FnY5tigqXeNNgpR+fa7CkAMu1c86M88dpe+/qnlV+ybK+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ac875d642738f59e71d4178c3a6a1d1aa57f0ff27b7ee89f756953620ee0af","last_reissued_at":"2026-06-09T01:05:40.870168Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:40.870168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM vs. Human Unit Tests: Fault Detection on Real Python Bugs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Nasir U. Eisty, Phouvadeth Vathana, Prapti Bhatt, Rishi Patel","submitted_at":"2026-06-07T12:01:44Z","abstract_excerpt":"Large language models (LLMs) have shown considerable promise for automated unit test generation, yet their practical effectiveness relative to human-written tests remains poorly understood. Existing evaluations commonly rely on coverage-oriented benchmarks that do not assess fault-detection capability directly. We present an empirical comparison of LLM-generated and human-written unit tests across three complementary Python benchmarks: 29 real historical bugs from BugsInPy, a function-level benchmark drawn from python-slugify and packaging, and a controlled paired benchmark. Our generation pip"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08588","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/2606.08588/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":"2606.08588","created_at":"2026-06-09T01:05:40.870225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08588v1","created_at":"2026-06-09T01:05:40.870225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08588","created_at":"2026-06-09T01:05:40.870225+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWWIOXLEE44P","created_at":"2026-06-09T01:05:40.870225+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWWIOXLEE44PLHTR","created_at":"2026-06-09T01:05:40.870225+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWWIOXLE","created_at":"2026-06-09T01:05:40.870225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU","json":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU.json","graph_json":"https://pith.science/api/pith-number/MWWIOXLEE44PLHTR2QLYYOTKDU/graph.json","events_json":"https://pith.science/api/pith-number/MWWIOXLEE44PLHTR2QLYYOTKDU/events.json","paper":"https://pith.science/paper/MWWIOXLE"},"agent_actions":{"view_html":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU","download_json":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU.json","view_paper":"https://pith.science/paper/MWWIOXLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08588&json=true","fetch_graph":"https://pith.science/api/pith-number/MWWIOXLEE44PLHTR2QLYYOTKDU/graph.json","fetch_events":"https://pith.science/api/pith-number/MWWIOXLEE44PLHTR2QLYYOTKDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU/action/storage_attestation","attest_author":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU/action/author_attestation","sign_citation":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU/action/citation_signature","submit_replication":"https://pith.science/pith/MWWIOXLEE44PLHTR2QLYYOTKDU/action/replication_record"}},"created_at":"2026-06-09T01:05:40.870225+00:00","updated_at":"2026-06-09T01:05:40.870225+00:00"}