{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RSB7EMA3OPXLGRJMC6PL3QINCB","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":"a36e7868af857c46ae28c7e0ebffda20b9b9871445425b7e38432889626e6a08","cross_cats_sorted":["cs.AI","cs.PL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T06:43:25Z","title_canon_sha256":"060c50e2c1811eaf1b414a63017bf116fdc0cbfc2578b4a3754b10980ba56b28"},"schema_version":"1.0","source":{"id":"2406.12902","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12902","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12902v2","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12902","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"RSB7EMA3OPXL","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"RSB7EMA3OPXLGRJM","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"RSB7EMA3","created_at":"2026-07-05T09:19:10Z"}],"graph_snapshots":[{"event_id":"sha256:46d70df3722095815475636f6ee09b84fb8ba310745b85f2799e15b5cf2204e1","target":"graph","created_at":"2026-07-05T09:19:10Z","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/2406.12902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code generation benchmarks such as HumanEval are widely adopted to evaluate LLMs' capabilities. However, after consolidating the latest 24 benchmarks, we noticed three significant imbalances. First, imbalanced programming language. 95.8% of benchmarks involve Python, while only 5 benchmarks involve Java. Second, imbalanced code granularity. Function-/statement-level benchmarks account for over 83.3% of benchmarks. Only a mere handful extends to class-/project-levels, and all are limited to Python. Third, lacking advanced features. Existing benchmarks primarily assess basic coding skills, while","authors_text":"Chang Xu, Jialun Cao, Jiarong Wu, Shing-Chi Cheung, Zhiyong Chen","cross_cats":["cs.AI","cs.PL","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T06:43:25Z","title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12902","kind":"arxiv","version":2},"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":"sha256:839a0b9bdfb71d837106fe5e29ae16dd6a8379159026a0558784baadd590042e","target":"record","created_at":"2026-07-05T09:19:10Z","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":"a36e7868af857c46ae28c7e0ebffda20b9b9871445425b7e38432889626e6a08","cross_cats_sorted":["cs.AI","cs.PL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T06:43:25Z","title_canon_sha256":"060c50e2c1811eaf1b414a63017bf116fdc0cbfc2578b4a3754b10980ba56b28"},"schema_version":"1.0","source":{"id":"2406.12902","kind":"arxiv","version":2}},"canonical_sha256":"8c83f2301b73eeb3452c179ebdc10d104fa8f19372ec481f2a026a9fe7048aac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c83f2301b73eeb3452c179ebdc10d104fa8f19372ec481f2a026a9fe7048aac","first_computed_at":"2026-07-05T09:19:10.553163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:10.553163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nKF+1gvHay1ojvhWfOc9WdJdpu3iX432bRiO2HdY9CANPH9jZsBKOS9v5eFFNfdDpjd/xE9zMek7MTAswjc5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:10.553684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12902","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:839a0b9bdfb71d837106fe5e29ae16dd6a8379159026a0558784baadd590042e","sha256:46d70df3722095815475636f6ee09b84fb8ba310745b85f2799e15b5cf2204e1"],"state_sha256":"d5d9b9f4123b19b4b938d32a486cc38c0b0a21fb6025a2880656e88dbd4a2f54"}