{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FPZ2SDYYQY5QMZQ6LNNPJRCMCY","short_pith_number":"pith:FPZ2SDYY","schema_version":"1.0","canonical_sha256":"2bf3a90f18863b06661e5b5af4c44c16330830244ca03ebe5335e4dda30aa3c1","source":{"kind":"arxiv","id":"2509.04644","version":1},"attestation_state":"computed","paper":{"title":"Comparative Evaluation of Large Language Models for Test-Skeleton Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Edward F. Gehringer, Muhammet Mustafa Olmez, Nitya Naga Sai Atluri, Subhang Boorlagadda","submitted_at":"2025-09-04T20:02:52Z","abstract_excerpt":"This paper explores the use of Large Language Models (LLMs) to automate the generation of test skeletons -- structural templates that outline unit test coverage without implementing full test logic. Test skeletons are especially important in test-driven development (TDD), where they provide an early framework for systematic verification. Traditionally authored manually, their creation can be time-consuming and error-prone, particularly in educational or large-scale development settings. We evaluate four LLMs -- GPT-4, DeepSeek-Chat, Llama4-Maverick, and Gemma2-9B -- on their ability to generat"},"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":"2509.04644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-09-04T20:02:52Z","cross_cats_sorted":[],"title_canon_sha256":"66a5c11e66a73c7df697b84a8ac07242ceef57d9c46352b7b3c6f85cd9dd74b6","abstract_canon_sha256":"8b3056a19d16918709859d36c0f5ab5323579dbbaad1115fc8fa3766af4c70a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:26.807491Z","signature_b64":"nsLUph8h5KoEQ8qoYTxTXQ2C4mGoEdsuu35f3CKNqOzVSwOso+bKdrjTsrhwDVob1i6i82U7EO/LnVS0kkJdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bf3a90f18863b06661e5b5af4c44c16330830244ca03ebe5335e4dda30aa3c1","last_reissued_at":"2026-07-05T12:05:26.806892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:26.806892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparative Evaluation of Large Language Models for Test-Skeleton Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Edward F. Gehringer, Muhammet Mustafa Olmez, Nitya Naga Sai Atluri, Subhang Boorlagadda","submitted_at":"2025-09-04T20:02:52Z","abstract_excerpt":"This paper explores the use of Large Language Models (LLMs) to automate the generation of test skeletons -- structural templates that outline unit test coverage without implementing full test logic. Test skeletons are especially important in test-driven development (TDD), where they provide an early framework for systematic verification. Traditionally authored manually, their creation can be time-consuming and error-prone, particularly in educational or large-scale development settings. We evaluate four LLMs -- GPT-4, DeepSeek-Chat, Llama4-Maverick, and Gemma2-9B -- on their ability to generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04644","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/2509.04644/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":"2509.04644","created_at":"2026-07-05T12:05:26.806969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04644v1","created_at":"2026-07-05T12:05:26.806969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04644","created_at":"2026-07-05T12:05:26.806969+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPZ2SDYYQY5Q","created_at":"2026-07-05T12:05:26.806969+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPZ2SDYYQY5QMZQ6","created_at":"2026-07-05T12:05:26.806969+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPZ2SDYY","created_at":"2026-07-05T12:05:26.806969+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/FPZ2SDYYQY5QMZQ6LNNPJRCMCY","json":"https://pith.science/pith/FPZ2SDYYQY5QMZQ6LNNPJRCMCY.json","graph_json":"https://pith.science/api/pith-number/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/graph.json","events_json":"https://pith.science/api/pith-number/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/events.json","paper":"https://pith.science/paper/FPZ2SDYY"},"agent_actions":{"view_html":"https://pith.science/pith/FPZ2SDYYQY5QMZQ6LNNPJRCMCY","download_json":"https://pith.science/pith/FPZ2SDYYQY5QMZQ6LNNPJRCMCY.json","view_paper":"https://pith.science/paper/FPZ2SDYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04644&json=true","fetch_graph":"https://pith.science/api/pith-number/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/graph.json","fetch_events":"https://pith.science/api/pith-number/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/action/storage_attestation","attest_author":"https://pith.science/pith/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/action/author_attestation","sign_citation":"https://pith.science/pith/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/action/citation_signature","submit_replication":"https://pith.science/pith/FPZ2SDYYQY5QMZQ6LNNPJRCMCY/action/replication_record"}},"created_at":"2026-07-05T12:05:26.806969+00:00","updated_at":"2026-07-05T12:05:26.806969+00:00"}