{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G6UQNRONRJHBJHRZPR3MJVD2QA","short_pith_number":"pith:G6UQNRON","schema_version":"1.0","canonical_sha256":"37a906c5cd8a4e149e397c76c4d47a800c9179d292874f0b4fab148fb0fb14aa","source":{"kind":"arxiv","id":"2412.02735","version":1},"attestation_state":"computed","paper":{"title":"CPP-UT-Bench: Can LLMs Write Complex Unit Tests in C++?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Debojyoti Dutta, Rajat Ghosh, Vaishnavi Bhargava","submitted_at":"2024-12-03T18:35:24Z","abstract_excerpt":"We introduce CPP-UT-Bench, a benchmark dataset to measure C++ unit test generation capability of a large language model (LLM). CPP-UT-Bench aims to reflect a broad and diverse set of C++ codebases found in the real world. The dataset includes 2,653 {code, unit test} pairs drawn from 14 different opensource C++ codebases spanned across nine diverse domains including machine learning, software testing, parsing, standard input-output, data engineering, logging, complete expression evaluation, key value storage, and server protocols. We demonstrated the effectiveness of CPP-UT-Bench as a benchmark"},"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":"2412.02735","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-12-03T18:35:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9e09bf4f2a1d4c9bf43f15a70d3cf97ff46fd7a7262454f6a4aea1ebb12fe411","abstract_canon_sha256":"df50b4272463cae5d2d34c68afad73d09c582dcd866af8c0607e3ed0109bd1b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:18.785215Z","signature_b64":"QLkVXP0NIalfPzzkE4jCO1vqzToigZJrAB1Nd3AKjEyCM4ISQHZUyI8UYolfkOQQm0mtGcQQGwz/M7FHjmxJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37a906c5cd8a4e149e397c76c4d47a800c9179d292874f0b4fab148fb0fb14aa","last_reissued_at":"2026-07-05T09:44:18.784693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:18.784693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CPP-UT-Bench: Can LLMs Write Complex Unit Tests in C++?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Debojyoti Dutta, Rajat Ghosh, Vaishnavi Bhargava","submitted_at":"2024-12-03T18:35:24Z","abstract_excerpt":"We introduce CPP-UT-Bench, a benchmark dataset to measure C++ unit test generation capability of a large language model (LLM). CPP-UT-Bench aims to reflect a broad and diverse set of C++ codebases found in the real world. The dataset includes 2,653 {code, unit test} pairs drawn from 14 different opensource C++ codebases spanned across nine diverse domains including machine learning, software testing, parsing, standard input-output, data engineering, logging, complete expression evaluation, key value storage, and server protocols. We demonstrated the effectiveness of CPP-UT-Bench as a benchmark"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02735","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/2412.02735/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":"2412.02735","created_at":"2026-07-05T09:44:18.784751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02735v1","created_at":"2026-07-05T09:44:18.784751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02735","created_at":"2026-07-05T09:44:18.784751+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6UQNRONRJHB","created_at":"2026-07-05T09:44:18.784751+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6UQNRONRJHBJHRZ","created_at":"2026-07-05T09:44:18.784751+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6UQNRON","created_at":"2026-07-05T09:44:18.784751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24324","citing_title":"SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA","json":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA.json","graph_json":"https://pith.science/api/pith-number/G6UQNRONRJHBJHRZPR3MJVD2QA/graph.json","events_json":"https://pith.science/api/pith-number/G6UQNRONRJHBJHRZPR3MJVD2QA/events.json","paper":"https://pith.science/paper/G6UQNRON"},"agent_actions":{"view_html":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA","download_json":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA.json","view_paper":"https://pith.science/paper/G6UQNRON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02735&json=true","fetch_graph":"https://pith.science/api/pith-number/G6UQNRONRJHBJHRZPR3MJVD2QA/graph.json","fetch_events":"https://pith.science/api/pith-number/G6UQNRONRJHBJHRZPR3MJVD2QA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA/action/storage_attestation","attest_author":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA/action/author_attestation","sign_citation":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA/action/citation_signature","submit_replication":"https://pith.science/pith/G6UQNRONRJHBJHRZPR3MJVD2QA/action/replication_record"}},"created_at":"2026-07-05T09:44:18.784751+00:00","updated_at":"2026-07-05T09:44:18.784751+00:00"}