{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CMAATGMKNRCMI4LGILYY6UQP5Z","short_pith_number":"pith:CMAATGMK","schema_version":"1.0","canonical_sha256":"130009998a6c44c4716642f18f520fee49f657ce6b846cdd02f59f4ad01c35d4","source":{"kind":"arxiv","id":"2511.10868","version":2},"attestation_state":"computed","paper":{"title":"Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debojyoti Dutta, Hritik Raj, Rajat Ghosh, Vaishnavi Bhargava, Yashshi Pipalani","submitted_at":"2025-11-14T00:35:00Z","abstract_excerpt":"Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering tasks, especially in low resource languages like Golang. As a result, models excel at code autocompletion but struggle with real world developer workflows such as unit test generation. To address this gap, we introduce GO UT Bench, a benchmark dataset of 5264 pairs of code and unit tests, drawn from 10 permissively licensed Golang repositories spanning diverse domain. We evaluate its effectiveness as a fine tuning da"},"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":"2511.10868","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-14T00:35:00Z","cross_cats_sorted":[],"title_canon_sha256":"f5273b523056e46dc24319648e509baa2a967e1ac4b147c5b536bc341c6b922e","abstract_canon_sha256":"a6f311707c97964c3da234e4eed24be046ace3fc1f24c164eb20b554800bc129"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:25.349086Z","signature_b64":"JLYefWLFhrmFw1H0r8sci9rfGGgEiz7/hMC6ImVniQ4mf9XUMF5YzDzaznZzmZ+CO0EusODCyg15AQtCNgK7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"130009998a6c44c4716642f18f520fee49f657ce6b846cdd02f59f4ad01c35d4","last_reissued_at":"2026-06-01T01:02:25.347673Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:25.347673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debojyoti Dutta, Hritik Raj, Rajat Ghosh, Vaishnavi Bhargava, Yashshi Pipalani","submitted_at":"2025-11-14T00:35:00Z","abstract_excerpt":"Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering tasks, especially in low resource languages like Golang. As a result, models excel at code autocompletion but struggle with real world developer workflows such as unit test generation. To address this gap, we introduce GO UT Bench, a benchmark dataset of 5264 pairs of code and unit tests, drawn from 10 permissively licensed Golang repositories spanning diverse domain. We evaluate its effectiveness as a fine tuning da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.10868","kind":"arxiv","version":2},"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/2511.10868/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":"2511.10868","created_at":"2026-06-01T01:02:25.347845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.10868v2","created_at":"2026-06-01T01:02:25.347845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.10868","created_at":"2026-06-01T01:02:25.347845+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMAATGMKNRCM","created_at":"2026-06-01T01:02:25.347845+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMAATGMKNRCMI4LG","created_at":"2026-06-01T01:02:25.347845+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMAATGMK","created_at":"2026-06-01T01:02:25.347845+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/CMAATGMKNRCMI4LGILYY6UQP5Z","json":"https://pith.science/pith/CMAATGMKNRCMI4LGILYY6UQP5Z.json","graph_json":"https://pith.science/api/pith-number/CMAATGMKNRCMI4LGILYY6UQP5Z/graph.json","events_json":"https://pith.science/api/pith-number/CMAATGMKNRCMI4LGILYY6UQP5Z/events.json","paper":"https://pith.science/paper/CMAATGMK"},"agent_actions":{"view_html":"https://pith.science/pith/CMAATGMKNRCMI4LGILYY6UQP5Z","download_json":"https://pith.science/pith/CMAATGMKNRCMI4LGILYY6UQP5Z.json","view_paper":"https://pith.science/paper/CMAATGMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.10868&json=true","fetch_graph":"https://pith.science/api/pith-number/CMAATGMKNRCMI4LGILYY6UQP5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/CMAATGMKNRCMI4LGILYY6UQP5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMAATGMKNRCMI4LGILYY6UQP5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMAATGMKNRCMI4LGILYY6UQP5Z/action/storage_attestation","attest_author":"https://pith.science/pith/CMAATGMKNRCMI4LGILYY6UQP5Z/action/author_attestation","sign_citation":"https://pith.science/pith/CMAATGMKNRCMI4LGILYY6UQP5Z/action/citation_signature","submit_replication":"https://pith.science/pith/CMAATGMKNRCMI4LGILYY6UQP5Z/action/replication_record"}},"created_at":"2026-06-01T01:02:25.347845+00:00","updated_at":"2026-06-01T01:02:25.347845+00:00"}