{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:W4WXONHPRTVPLRMDUDCYOPHX56","short_pith_number":"pith:W4WXONHP","schema_version":"1.0","canonical_sha256":"b72d7734ef8ceaf5c583a0c5873cf7ef89940bb2ed8ebd307cb53c96765af9b1","source":{"kind":"arxiv","id":"2312.14187","version":5},"attestation_state":"computed","paper":{"title":"WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Can Xu, Ning Shang, Qiufeng Yin, Wenxiang Hu, Xin Zhang, Yangyu Huang, Yishujie Zhao, Zhaojian Yu","submitted_at":"2023-12-20T09:02:29Z","abstract_excerpt":"Recent work demonstrates that, after instruction tuning, Code Large Language Models (Code LLMs) can obtain impressive capabilities to address a wide range of code-related tasks. However, current instruction tuning methods for Code LLMs mainly focus on the traditional code generation task, resulting in poor performance in complex multi-task scenarios. In this paper, we concentrate on multiple code-related tasks and present WaveCoder, a series of Code LLMs trained with Widespread And Versatile Enhanced instruction data. To enable the models to tackle complex code-related tasks, we propose a meth"},"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":"2312.14187","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-20T09:02:29Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"d72175d5c89556e9725a2cd750586b6b9c7ef85c3fc5cf14b3ecd56e999e9418","abstract_canon_sha256":"bf84f561208d77bcaf5d9e9ff0868bbdf7c4e73e9899e14a4e346f1a9f9fe884"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:36.449861Z","signature_b64":"e7iwrXs7lJtWR+D2IJdJhaMDtj4eimdIsZcMAypQvO0lLXIQP3kTxqCDjpgauoYhkEUcZ7YFXzlk6mMCp6E/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b72d7734ef8ceaf5c583a0c5873cf7ef89940bb2ed8ebd307cb53c96765af9b1","last_reissued_at":"2026-07-05T08:28:36.449377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:36.449377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Can Xu, Ning Shang, Qiufeng Yin, Wenxiang Hu, Xin Zhang, Yangyu Huang, Yishujie Zhao, Zhaojian Yu","submitted_at":"2023-12-20T09:02:29Z","abstract_excerpt":"Recent work demonstrates that, after instruction tuning, Code Large Language Models (Code LLMs) can obtain impressive capabilities to address a wide range of code-related tasks. However, current instruction tuning methods for Code LLMs mainly focus on the traditional code generation task, resulting in poor performance in complex multi-task scenarios. In this paper, we concentrate on multiple code-related tasks and present WaveCoder, a series of Code LLMs trained with Widespread And Versatile Enhanced instruction data. To enable the models to tackle complex code-related tasks, we propose a meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14187","kind":"arxiv","version":5},"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/2312.14187/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":"2312.14187","created_at":"2026-07-05T08:28:36.449439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14187v5","created_at":"2026-07-05T08:28:36.449439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14187","created_at":"2026-07-05T08:28:36.449439+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4WXONHPRTVP","created_at":"2026-07-05T08:28:36.449439+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4WXONHPRTVPLRMD","created_at":"2026-07-05T08:28:36.449439+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4WXONHP","created_at":"2026-07-05T08:28:36.449439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2405.15793","citing_title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56","json":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56.json","graph_json":"https://pith.science/api/pith-number/W4WXONHPRTVPLRMDUDCYOPHX56/graph.json","events_json":"https://pith.science/api/pith-number/W4WXONHPRTVPLRMDUDCYOPHX56/events.json","paper":"https://pith.science/paper/W4WXONHP"},"agent_actions":{"view_html":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56","download_json":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56.json","view_paper":"https://pith.science/paper/W4WXONHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14187&json=true","fetch_graph":"https://pith.science/api/pith-number/W4WXONHPRTVPLRMDUDCYOPHX56/graph.json","fetch_events":"https://pith.science/api/pith-number/W4WXONHPRTVPLRMDUDCYOPHX56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56/action/storage_attestation","attest_author":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56/action/author_attestation","sign_citation":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56/action/citation_signature","submit_replication":"https://pith.science/pith/W4WXONHPRTVPLRMDUDCYOPHX56/action/replication_record"}},"created_at":"2026-07-05T08:28:36.449439+00:00","updated_at":"2026-07-05T08:28:36.449439+00:00"}