{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I3KSKT3OTRNVNNESGVYNS4ID3X","short_pith_number":"pith:I3KSKT3O","schema_version":"1.0","canonical_sha256":"46d5254f6e9c5b56b4923570d97103dde8508fca62b7528834eb406f568dafb6","source":{"kind":"arxiv","id":"2403.19287","version":1},"attestation_state":"computed","paper":{"title":"CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Rui Xie, Shikun Zhang, Wei Ye, Yidong Wang, Zhengran Zeng","submitted_at":"2024-03-28T10:19:18Z","abstract_excerpt":"In the evolving landscape of large language models (LLMs) tailored for software engineering, the need for benchmarks that accurately reflect real-world development scenarios is paramount. Current benchmarks are either too simplistic or fail to capture the multi-tasking nature of software development. To address this, we introduce CoderUJB, a new benchmark designed to evaluate LLMs across diverse Java programming tasks that are executable and reflective of actual development scenarios, acknowledging Java's prevalence in real-world software production. CoderUJB comprises 2,239 programming questi"},"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":"2403.19287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-28T10:19:18Z","cross_cats_sorted":[],"title_canon_sha256":"e0ddd26c91609a9e8b1720b775490a754d7d4837346530f29b5fb275f4b62d42","abstract_canon_sha256":"acc50e71211efa58342e8f2907c8a2687f8948b722bf6fc6206c56906823983c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:47.330437Z","signature_b64":"McQldRp5mmz+lx2nKAsBVQgr26uG5HRaEdlkgG89ONEw96MhQaUq8FfbeM0yeklfDWAMNp9p1XI9N95KRU9pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46d5254f6e9c5b56b4923570d97103dde8508fca62b7528834eb406f568dafb6","last_reissued_at":"2026-07-05T08:01:47.329941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:47.329941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Rui Xie, Shikun Zhang, Wei Ye, Yidong Wang, Zhengran Zeng","submitted_at":"2024-03-28T10:19:18Z","abstract_excerpt":"In the evolving landscape of large language models (LLMs) tailored for software engineering, the need for benchmarks that accurately reflect real-world development scenarios is paramount. Current benchmarks are either too simplistic or fail to capture the multi-tasking nature of software development. To address this, we introduce CoderUJB, a new benchmark designed to evaluate LLMs across diverse Java programming tasks that are executable and reflective of actual development scenarios, acknowledging Java's prevalence in real-world software production. CoderUJB comprises 2,239 programming questi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19287","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/2403.19287/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":"2403.19287","created_at":"2026-07-05T08:01:47.330003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19287v1","created_at":"2026-07-05T08:01:47.330003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19287","created_at":"2026-07-05T08:01:47.330003+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3KSKT3OTRNV","created_at":"2026-07-05T08:01:47.330003+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3KSKT3OTRNVNNES","created_at":"2026-07-05T08:01:47.330003+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3KSKT3O","created_at":"2026-07-05T08:01:47.330003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02998","citing_title":"MRG-Bench: Evaluating and Exploring the Requirements of Context for Repository-Level Code Generation","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X","json":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X.json","graph_json":"https://pith.science/api/pith-number/I3KSKT3OTRNVNNESGVYNS4ID3X/graph.json","events_json":"https://pith.science/api/pith-number/I3KSKT3OTRNVNNESGVYNS4ID3X/events.json","paper":"https://pith.science/paper/I3KSKT3O"},"agent_actions":{"view_html":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X","download_json":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X.json","view_paper":"https://pith.science/paper/I3KSKT3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19287&json=true","fetch_graph":"https://pith.science/api/pith-number/I3KSKT3OTRNVNNESGVYNS4ID3X/graph.json","fetch_events":"https://pith.science/api/pith-number/I3KSKT3OTRNVNNESGVYNS4ID3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X/action/storage_attestation","attest_author":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X/action/author_attestation","sign_citation":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X/action/citation_signature","submit_replication":"https://pith.science/pith/I3KSKT3OTRNVNNESGVYNS4ID3X/action/replication_record"}},"created_at":"2026-07-05T08:01:47.330003+00:00","updated_at":"2026-07-05T08:01:47.330003+00:00"}