{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I6HBJCNRE3AMX6CUKXXERYPZ4D","short_pith_number":"pith:I6HBJCNR","schema_version":"1.0","canonical_sha256":"478e1489b126c0cbf85455ee48e1f9e0ee98948baab8c5b97fb236409c0d1d13","source":{"kind":"arxiv","id":"2412.18573","version":2},"attestation_state":"computed","paper":{"title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Dewu Zheng, Ensheng Shi, Hongyu Zhang, Xilin Liu, Yanlin Wang, Yuchi Ma, Zibin Zheng","submitted_at":"2024-12-24T17:56:08Z","abstract_excerpt":"With the rapid advancement of large language models (LLMs), extensive research has been conducted to investigate the code generation capabilities of LLMs. However, existing efforts primarily focus on general-domain tasks, leaving LLMs' code generation performance in real-world application domains underexplored. This raises a critical question: can a model's general-domain coding ability reliably represent its ability in specialized domains? In this paper, we introduce DomainCodeBench, a multi-domain code generation benchmark designed to systematically evaluate LLMs across 12 software applicati"},"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":"2412.18573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-24T17:56:08Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a765d42b87a728cfd5f86bdea30bec6193d5e8626ce043f6adcf9f8d58aeff42","abstract_canon_sha256":"54cfb6190f33f562cd1e29845b580d8d24d41fed8969f41b17acf16e13fd1df7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:36.202426Z","signature_b64":"b9K12/cdFSve3FRK1M76UOA8rjqzFd8b+/HVDlAXkRa6fvrsd7vOZIZDWNekTnDnbB1iHUn9ok9YlFB50piWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"478e1489b126c0cbf85455ee48e1f9e0ee98948baab8c5b97fb236409c0d1d13","last_reissued_at":"2026-07-05T10:32:36.201909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:36.201909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Dewu Zheng, Ensheng Shi, Hongyu Zhang, Xilin Liu, Yanlin Wang, Yuchi Ma, Zibin Zheng","submitted_at":"2024-12-24T17:56:08Z","abstract_excerpt":"With the rapid advancement of large language models (LLMs), extensive research has been conducted to investigate the code generation capabilities of LLMs. However, existing efforts primarily focus on general-domain tasks, leaving LLMs' code generation performance in real-world application domains underexplored. This raises a critical question: can a model's general-domain coding ability reliably represent its ability in specialized domains? In this paper, we introduce DomainCodeBench, a multi-domain code generation benchmark designed to systematically evaluate LLMs across 12 software applicati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18573","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/2412.18573/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":"2412.18573","created_at":"2026-07-05T10:32:36.201970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18573v2","created_at":"2026-07-05T10:32:36.201970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18573","created_at":"2026-07-05T10:32:36.201970+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6HBJCNRE3AM","created_at":"2026-07-05T10:32:36.201970+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6HBJCNRE3AMX6CU","created_at":"2026-07-05T10:32:36.201970+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6HBJCNR","created_at":"2026-07-05T10:32:36.201970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15248","citing_title":"Probing Privacy Leaks in LLM-based Code Generation via Test Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05867","citing_title":"On Fixing Insecure AI-Generated Code through Model Fine-Tuning and Prompting Strategies","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D","json":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D.json","graph_json":"https://pith.science/api/pith-number/I6HBJCNRE3AMX6CUKXXERYPZ4D/graph.json","events_json":"https://pith.science/api/pith-number/I6HBJCNRE3AMX6CUKXXERYPZ4D/events.json","paper":"https://pith.science/paper/I6HBJCNR"},"agent_actions":{"view_html":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D","download_json":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D.json","view_paper":"https://pith.science/paper/I6HBJCNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18573&json=true","fetch_graph":"https://pith.science/api/pith-number/I6HBJCNRE3AMX6CUKXXERYPZ4D/graph.json","fetch_events":"https://pith.science/api/pith-number/I6HBJCNRE3AMX6CUKXXERYPZ4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D/action/storage_attestation","attest_author":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D/action/author_attestation","sign_citation":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D/action/citation_signature","submit_replication":"https://pith.science/pith/I6HBJCNRE3AMX6CUKXXERYPZ4D/action/replication_record"}},"created_at":"2026-07-05T10:32:36.201970+00:00","updated_at":"2026-07-05T10:32:36.201970+00:00"}