{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I3KSKT3OTRNVNNESGVYNS4ID3X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"acc50e71211efa58342e8f2907c8a2687f8948b722bf6fc6206c56906823983c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-28T10:19:18Z","title_canon_sha256":"e0ddd26c91609a9e8b1720b775490a754d7d4837346530f29b5fb275f4b62d42"},"schema_version":"1.0","source":{"id":"2403.19287","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19287","created_at":"2026-07-05T08:01:47Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19287v1","created_at":"2026-07-05T08:01:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19287","created_at":"2026-07-05T08:01:47Z"},{"alias_kind":"pith_short_12","alias_value":"I3KSKT3OTRNV","created_at":"2026-07-05T08:01:47Z"},{"alias_kind":"pith_short_16","alias_value":"I3KSKT3OTRNVNNES","created_at":"2026-07-05T08:01:47Z"},{"alias_kind":"pith_short_8","alias_value":"I3KSKT3O","created_at":"2026-07-05T08:01:47Z"}],"graph_snapshots":[{"event_id":"sha256:5d31e61de29f1d1f3392ae415ed04eae380858b906b255fabbd3b3853683bfc8","target":"graph","created_at":"2026-07-05T08:01:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.19287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Rui Xie, Shikun Zhang, Wei Ye, Yidong Wang, Zhengran Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-28T10:19:18Z","title":"CoderUJB: An Executable and Unified Java Benchmark for Practical Programming Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19287","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:66d79e07baa7b96a6daf0f1fbc50e430ae223341a6bf78e8d5be3a4b77292d6a","target":"record","created_at":"2026-07-05T08:01:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"acc50e71211efa58342e8f2907c8a2687f8948b722bf6fc6206c56906823983c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-28T10:19:18Z","title_canon_sha256":"e0ddd26c91609a9e8b1720b775490a754d7d4837346530f29b5fb275f4b62d42"},"schema_version":"1.0","source":{"id":"2403.19287","kind":"arxiv","version":1}},"canonical_sha256":"46d5254f6e9c5b56b4923570d97103dde8508fca62b7528834eb406f568dafb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46d5254f6e9c5b56b4923570d97103dde8508fca62b7528834eb406f568dafb6","first_computed_at":"2026-07-05T08:01:47.329941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:47.329941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"McQldRp5mmz+lx2nKAsBVQgr26uG5HRaEdlkgG89ONEw96MhQaUq8FfbeM0yeklfDWAMNp9p1XI9N95KRU9pDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:47.330437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19287","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66d79e07baa7b96a6daf0f1fbc50e430ae223341a6bf78e8d5be3a4b77292d6a","sha256:5d31e61de29f1d1f3392ae415ed04eae380858b906b255fabbd3b3853683bfc8"],"state_sha256":"a25e50e189671d86b09c33ee01e38a3a7ab134a2be47ec7842b976f391ea3500"}