{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RSB7EMA3OPXLGRJMC6PL3QINCB","short_pith_number":"pith:RSB7EMA3","schema_version":"1.0","canonical_sha256":"8c83f2301b73eeb3452c179ebdc10d104fa8f19372ec481f2a026a9fe7048aac","source":{"kind":"arxiv","id":"2406.12902","version":2},"attestation_state":"computed","paper":{"title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Chang Xu, Jialun Cao, Jiarong Wu, Shing-Chi Cheung, Zhiyong Chen","submitted_at":"2024-06-10T06:43:25Z","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"},"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":"2406.12902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T06:43:25Z","cross_cats_sorted":["cs.AI","cs.PL","cs.SE"],"title_canon_sha256":"060c50e2c1811eaf1b414a63017bf116fdc0cbfc2578b4a3754b10980ba56b28","abstract_canon_sha256":"a36e7868af857c46ae28c7e0ebffda20b9b9871445425b7e38432889626e6a08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:10.553684Z","signature_b64":"nKF+1gvHay1ojvhWfOc9WdJdpu3iX432bRiO2HdY9CANPH9jZsBKOS9v5eFFNfdDpjd/xE9zMek7MTAswjc5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c83f2301b73eeb3452c179ebdc10d104fa8f19372ec481f2a026a9fe7048aac","last_reissued_at":"2026-07-05T09:19:10.553163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:10.553163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Chang Xu, Jialun Cao, Jiarong Wu, Shing-Chi Cheung, Zhiyong Chen","submitted_at":"2024-06-10T06:43:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12902","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/2406.12902/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":"2406.12902","created_at":"2026-07-05T09:19:10.553227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12902v2","created_at":"2026-07-05T09:19:10.553227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12902","created_at":"2026-07-05T09:19:10.553227+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSB7EMA3OPXL","created_at":"2026-07-05T09:19:10.553227+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSB7EMA3OPXLGRJM","created_at":"2026-07-05T09:19:10.553227+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSB7EMA3","created_at":"2026-07-05T09:19:10.553227+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":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB","json":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB.json","graph_json":"https://pith.science/api/pith-number/RSB7EMA3OPXLGRJMC6PL3QINCB/graph.json","events_json":"https://pith.science/api/pith-number/RSB7EMA3OPXLGRJMC6PL3QINCB/events.json","paper":"https://pith.science/paper/RSB7EMA3"},"agent_actions":{"view_html":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB","download_json":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB.json","view_paper":"https://pith.science/paper/RSB7EMA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12902&json=true","fetch_graph":"https://pith.science/api/pith-number/RSB7EMA3OPXLGRJMC6PL3QINCB/graph.json","fetch_events":"https://pith.science/api/pith-number/RSB7EMA3OPXLGRJMC6PL3QINCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB/action/storage_attestation","attest_author":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB/action/author_attestation","sign_citation":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB/action/citation_signature","submit_replication":"https://pith.science/pith/RSB7EMA3OPXLGRJMC6PL3QINCB/action/replication_record"}},"created_at":"2026-07-05T09:19:10.553227+00:00","updated_at":"2026-07-05T09:19:10.553227+00:00"}